Skip to content

Instantly share code, notes, and snippets.

@richardstartin
Created January 3, 2018 19:14
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save richardstartin/9b019f61aee901b20d7fbae9ae76c25d to your computer and use it in GitHub Desktop.
Save richardstartin/9b019f61aee901b20d7fbae9ae76c25d to your computer and use it in GitHub Desktop.
Benchmarks:
com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 0, size = 1000)
# Run progress: 0.00% complete, ETA 00:18:20
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 2.086 ops/us
# Warmup Iteration 2: 2.305 ops/us
# Warmup Iteration 3: 2.248 ops/us
# Warmup Iteration 4: 2.279 ops/us
# Warmup Iteration 5: 2.307 ops/us
# Warmup Iteration 6: 2.335 ops/us
# Warmup Iteration 7: 2.353 ops/us
# Warmup Iteration 8: 2.361 ops/us
# Warmup Iteration 9: 2.470 ops/us
# Warmup Iteration 10: 2.464 ops/us
Iteration 1: 2.621 ops/us
Iteration 2: 2.642 ops/us
Iteration 3: 2.667 ops/us
Iteration 4: 2.648 ops/us
Iteration 5: 2.688 ops/us
Iteration 6: 2.664 ops/us
Iteration 7: 2.650 ops/us
Iteration 8: 2.667 ops/us
Iteration 9: 2.678 ops/us
Iteration 10: 2.691 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
2.662 ±(99.9%) 0.033 ops/us [Average]
(min, avg, max) = (2.621, 2.662, 2.691), stdev = 0.022
CI (99.9%): [2.629, 2.694] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48239 total address lines.
Perf output processed (skipped 15.018 seconds):
Column 1: SampledProfile (99381 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 160 (420 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000002d1a946f3d0: vzeroupper
0x000002d1a946f3d3: add rsp,50h
0x000002d1a946f3d7: pop rbp
0x000002d1a946f3d8: test dword ptr [2d19d370000h],eax
; {poll_return}
0x000002d1a946f3de: ret
0x000002d1a946f3df: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000002d1a946f3e0: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.01% 0x000002d1a946f3e7: vmulpd ymm0,ymm0,ymm2
0.04% 0x000002d1a946f3eb: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
0.12% 0x000002d1a946f3f2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.09% 0x000002d1a946f3f9: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f3fd: cmp r8d,r9d
0.00% 0x000002d1a946f400: jl 2d1a946f3e0h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f402: cmp r8d,edx
0x000002d1a946f405: jnl 2d1a946f429h
0.08% 0x000002d1a946f407: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f408: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f40f: vmulsd xmm0,xmm0,xmm1
0.00% 0x000002d1a946f413: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.09% 0x000002d1a946f41a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f421: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000002d1a946f424: cmp r8d,edx
0x000002d1a946f427: jl 2d1a946f408h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000002d1a946f429: mov r8,rbx
0.00% 0x000002d1a946f42c: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000002d1a946f430: mov rdx,qword ptr [rsp+30h]
0.01% 0x000002d1a946f435: nop
0.09% 0x000002d1a946f438: vzeroupper
0.08% 0x000002d1a946f43b: call 2d1a93ec480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.01% 0x000002d1a946f440: mov r10,qword ptr [rsp+60h]
0.09% 0x000002d1a946f445: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.00% 0x000002d1a946f44d: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.00% 0x000002d1a946f451: test dword ptr [2d19d370000h],eax
; {poll}
0.07% 0x000002d1a946f457: test r10d,r10d
0x000002d1a946f45a: jne 2d1a946f3afh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0.00% 0x000002d1a946f460: mov r10,qword ptr [rsp+70h]
0.00% 0x000002d1a946f465: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f469: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000002d1a946f5ed
0.08% 0x000002d1a946f46e: test edx,edx
0x000002d1a946f470: jbe 2d1a946f429h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000002d1a946f472: mov r11d,edx
0.00% 0x000002d1a946f475: dec r11d
0.01% 0x000002d1a946f478: cmp r11d,edx
0x000002d1a946f47b: jnb 2d1a946f592h
0.08% 0x000002d1a946f481: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f485: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000002d1a946f592
0.01% 0x000002d1a946f48a: test r9d,r9d
0x000002d1a946f48d: jbe 2d1a946f592h
0.00% 0x000002d1a946f493: cmp r11d,r9d
0x000002d1a946f496: jnb 2d1a946f592h
0.08% 0x000002d1a946f49c: mov r11,qword ptr [rsp+70h]
0.00% 0x000002d1a946f4a1: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000002d1a946f4a7: lea r11,[r12+rbx*8]
0.00% 0x000002d1a946f4ab: shl r10,3h
0.07% 0x000002d1a946f4af: mov r8d,r11d
0.00% 0x000002d1a946f4b2: shr r8d,3h
0.00% 0x000002d1a946f4b6: and r8d,3h
0.00% 0x000002d1a946f4ba: mov ecx,1h
0.06% 0x000002d1a946f4bf: sub ecx,r8d
0.00% 0x000002d1a946f4c2: and ecx,3h
0.00% 0x000002d1a946f4c5: inc ecx
0.01% 0x000002d1a946f4c7: cmp ecx,edx
0.09% 0x000002d1a946f4c9: cmovnle ecx,edx
0.00% 0x000002d1a946f4cc: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000002d1a946f4cf: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000002d1a946f4d6: vmulsd xmm0,xmm0,xmm1
0.08% 0x000002d1a946f4da: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.18% 0x000002d1a946f4e1: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000002d1a946f4e8: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000002d1a946f4eb: cmp r8d,ecx
0x000002d1a946f4ee: jl 2d1a946f4cfh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f4f0: mov ecx,edx
0.08% 0x000002d1a946f4f2: add ecx,0fffffff1h
0.00% 0x000002d1a946f4f5: cmp r8d,ecx
0x000002d1a946f4f8: jnl 2d1a946f402h
0.00% 0x000002d1a946f4fe: vpshufd xmm2,xmm1,44h
0.00% 0x000002d1a946f503: vinsertf128 ymm2,ymm2,xmm2,1h
0.06% 0x000002d1a946f509: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.24% 0x000002d1a946f510: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
3.61% 0x000002d1a946f517: vmulpd ymm0,ymm0,ymm2
4.63% 0x000002d1a946f51b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
9.73% 0x000002d1a946f522: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
4.34% 0x000002d1a946f529: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
2.13% 0x000002d1a946f530: vmulpd ymm0,ymm0,ymm2
7.77% 0x000002d1a946f534: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
13.46% 0x000002d1a946f53b: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
3.37% 0x000002d1a946f542: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
0.47% 0x000002d1a946f549: vmulpd ymm0,ymm0,ymm2
1.47% 0x000002d1a946f54d: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
13.00% 0x000002d1a946f554: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
4.24% 0x000002d1a946f55b: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
2.40% 0x000002d1a946f562: vmulpd ymm0,ymm0,ymm2
8.92% 0x000002d1a946f566: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
14.10% 0x000002d1a946f56d: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
3.24% 0x000002d1a946f574: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.22% 0x000002d1a946f578: cmp r8d,ecx
0x000002d1a946f57b: jl 2d1a946f510h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000002d1a946f57d: mov r9d,edx
0.01% 0x000002d1a946f580: add r9d,0fffffffdh
0.07% 0x000002d1a946f584: cmp r8d,r9d
0x000002d1a946f587: jl 2d1a946f3e0h
0x000002d1a946f58d: jmp 2d1a946f402h
0x000002d1a946f592: mov edx,0ffffff86h
0x000002d1a946f597: nop
0x000002d1a946f598: vzeroupper
0x000002d1a946f59b: call 2d1a93ede80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
99.42% <total for region 1>
....[Hottest Regions]...............................................................................
99.42% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 160 (420 bytes)
0.37% c2 org.openjdk.jmh.infra.Blackhole::consume, version 158 (72 bytes)
0.19% <unknown> (0 bytes)
0.00% KernelBase.dll WaitForSingleObjectEx (0 bytes)
0.00% jvm.dll 0x00000000709ab570 (26 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% jvm.dll 0x00000000707d873e (0 bytes)
0.00% jvm.dll 0x00000000709955bf (0 bytes)
0.00% jvm.dll 0x00000000709ac6a0 (0 bytes)
0.00% jvm.dll 0x0000000070b42712 (0 bytes)
0.00% jvm.dll 0x0000000070c51797 (0 bytes)
0.00% jvm.dll 0x0000000070c517d5 (0 bytes)
0.00% jvm.dll 0x0000000070c737c7 (0 bytes)
0.00% jvm.dll 0x0000000070c74829 (0 bytes)
0.00% jvm.dll 0x0000000070d28e9d (0 bytes)
0.00% runtime stub StubRoutines::atomic_cmpxchg_long (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% interpreter aaload 50 aaload (0 bytes)
0.00% interpreter iflt 155 iflt (0 bytes)
0.00% interpreter lreturn 173 lreturn (0 bytes)
0.00% <...other 3 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
99.42% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 160
0.37% c2 org.openjdk.jmh.infra.Blackhole::consume, version 158
0.19% <unknown>
0.00% KernelBase.dll WaitForSingleObjectEx
0.00% interpreter method entry point (kind = zerolocals)
0.00% jvm.dll 0x00000000709ab570
0.00% jvm.dll 0x0000000070c51797
0.00% interpreter fast_zputfield 213 fast_zputfield
0.00% jvm.dll 0x0000000070c74829
0.00% interpreter aaload 50 aaload
0.00% jvm.dll 0x0000000070b42712
0.00% jvm.dll 0x0000000070c737c7
0.00% jvm.dll 0x0000000070c517d5
0.00% jvm.dll 0x0000000070d28e9d
0.00% interpreter invokestatic 184 invokestatic
0.00% interpreter iflt 155 iflt
0.00% jvm.dll 0x00000000709955bf
0.00% KernelBase.dll GetThreadTimes
0.00% jvm.dll 0x00000000707d873e
0.00% jvm.dll 0x00000000709ac6a0
0.00% <...other 2 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.78% c2
0.19%
0.01% jvm.dll
0.01% interpreter
0.01% KernelBase.dll
0.00% runtime stub
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 0, size = 1024)
# Run progress: 10.00% complete, ETA 00:26:19
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 7.084 ops/us
# Warmup Iteration 2: 7.083 ops/us
# Warmup Iteration 3: 7.069 ops/us
# Warmup Iteration 4: 6.801 ops/us
# Warmup Iteration 5: 6.647 ops/us
# Warmup Iteration 6: 7.030 ops/us
# Warmup Iteration 7: 7.129 ops/us
# Warmup Iteration 8: 6.834 ops/us
# Warmup Iteration 9: 7.144 ops/us
# Warmup Iteration 10: 6.842 ops/us
Iteration 1: 7.016 ops/us
Iteration 2: 6.984 ops/us
Iteration 3: 7.052 ops/us
Iteration 4: 7.042 ops/us
Iteration 5: 7.094 ops/us
Iteration 6: 7.082 ops/us
Iteration 7: 6.626 ops/us
Iteration 8: 7.060 ops/us
Iteration 9: 6.331 ops/us
Iteration 10: 6.618 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
6.891 ±(99.9%) 0.403 ops/us [Average]
(min, avg, max) = (6.331, 6.891, 7.094), stdev = 0.266
CI (99.9%): [6.488, 7.293] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48573 total address lines.
Perf output processed (skipped 14.151 seconds):
Column 1: SampledProfile (99436 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (420 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000020dddc5ae50: vzeroupper
0x0000020dddc5ae53: add rsp,50h
0x0000020dddc5ae57: pop rbp
0x0000020dddc5ae58: test dword ptr [20dd1c90000h],eax
; {poll_return}
0x0000020dddc5ae5e: ret
0x0000020dddc5ae5f: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000020dddc5ae60: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
1.67% 0x0000020dddc5ae67: vmulpd ymm0,ymm0,ymm2
1.39% 0x0000020dddc5ae6b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
1.64% 0x0000020dddc5ae72: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.66% 0x0000020dddc5ae79: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000020dddc5ae7d: cmp r8d,r9d
0x0000020dddc5ae80: jl 20dddc5ae60h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000020dddc5ae82: cmp r8d,edx
0x0000020dddc5ae85: jnl 20dddc5aea9h
0.20% 0x0000020dddc5ae87: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000020dddc5ae88: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000020dddc5ae8f: vmulsd xmm0,xmm0,xmm1
0x0000020dddc5ae93: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.23% 0x0000020dddc5ae9a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000020dddc5aea1: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000020dddc5aea4: cmp r8d,edx
0x0000020dddc5aea7: jl 20dddc5ae88h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.21% 0x0000020dddc5aea9: mov r8,rbx
0.00% 0x0000020dddc5aeac: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000020dddc5aeb0: mov rdx,qword ptr [rsp+30h]
0.00% 0x0000020dddc5aeb5: nop
0.23% 0x0000020dddc5aeb8: vzeroupper
0.22% 0x0000020dddc5aebb: call 20dddbdc480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.30% 0x0000020dddc5aec0: mov r10,qword ptr [rsp+60h]
0.06% 0x0000020dddc5aec5: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.00% 0x0000020dddc5aecd: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.17% 0x0000020dddc5aed1: test dword ptr [20dd1c90000h],eax
; {poll}
0.08% 0x0000020dddc5aed7: test r10d,r10d
0x0000020dddc5aeda: jne 20dddc5ae2fh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0x0000020dddc5aee0: mov r10,qword ptr [rsp+70h]
0.00% 0x0000020dddc5aee5: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.16% 0x0000020dddc5aee9: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x0000020dddc5b06d
0.26% 0x0000020dddc5aeee: test edx,edx
0x0000020dddc5aef0: jbe 20dddc5aea9h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.29% 0x0000020dddc5aef2: mov r11d,edx
0x0000020dddc5aef5: dec r11d
0.00% 0x0000020dddc5aef8: cmp r11d,edx
0x0000020dddc5aefb: jnb 20dddc5b012h
0.22% 0x0000020dddc5af01: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.02% 0x0000020dddc5af05: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x0000020dddc5b012
0.00% 0x0000020dddc5af0a: test r9d,r9d
0x0000020dddc5af0d: jbe 20dddc5b012h
0.00% 0x0000020dddc5af13: cmp r11d,r9d
0x0000020dddc5af16: jnb 20dddc5b012h
0.20% 0x0000020dddc5af1c: mov r11,qword ptr [rsp+70h]
0.02% 0x0000020dddc5af21: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000020dddc5af27: lea r11,[r12+rbx*8]
0.00% 0x0000020dddc5af2b: shl r10,3h
0.20% 0x0000020dddc5af2f: mov r8d,r11d
0.02% 0x0000020dddc5af32: shr r8d,3h
0x0000020dddc5af36: and r8d,3h
0x0000020dddc5af3a: mov ecx,1h
0.23% 0x0000020dddc5af3f: sub ecx,r8d
0.02% 0x0000020dddc5af42: and ecx,3h
0x0000020dddc5af45: inc ecx
0x0000020dddc5af47: cmp ecx,edx
0.22% 0x0000020dddc5af49: cmovnle ecx,edx
0.03% 0x0000020dddc5af4c: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.15% 0x0000020dddc5af4f: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x0000020dddc5af56: vmulsd xmm0,xmm0,xmm1
0.26% 0x0000020dddc5af5a: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.39% 0x0000020dddc5af61: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.07% 0x0000020dddc5af68: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.21% 0x0000020dddc5af6b: cmp r8d,ecx
0x0000020dddc5af6e: jl 20dddc5af4fh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.07% 0x0000020dddc5af70: mov ecx,edx
0.16% 0x0000020dddc5af72: add ecx,0fffffff1h
0.03% 0x0000020dddc5af75: cmp r8d,ecx
0x0000020dddc5af78: jnl 20dddc5ae82h
0.00% 0x0000020dddc5af7e: vpshufd xmm2,xmm1,44h
0.06% 0x0000020dddc5af83: vinsertf128 ymm2,ymm2,xmm2,1h
0.16% 0x0000020dddc5af89: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.18% 0x0000020dddc5af90: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
9.27% 0x0000020dddc5af97: vmulpd ymm0,ymm0,ymm2
0.22% 0x0000020dddc5af9b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
7.48% 0x0000020dddc5afa2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
10.16% 0x0000020dddc5afa9: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
0.09% 0x0000020dddc5afb0: vmulpd ymm0,ymm0,ymm2
3.62% 0x0000020dddc5afb4: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
10.60% 0x0000020dddc5afbb: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
0.26% 0x0000020dddc5afc2: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
3.76% 0x0000020dddc5afc9: vmulpd ymm0,ymm0,ymm2
0.20% 0x0000020dddc5afcd: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
13.23% 0x0000020dddc5afd4: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
9.46% 0x0000020dddc5afdb: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
0.11% 0x0000020dddc5afe2: vmulpd ymm0,ymm0,ymm2
4.63% 0x0000020dddc5afe6: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
9.78% 0x0000020dddc5afed: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.14% 0x0000020dddc5aff4: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
4.69% 0x0000020dddc5aff8: cmp r8d,ecx
0x0000020dddc5affb: jl 20dddc5af90h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000020dddc5affd: mov r9d,edx
0.23% 0x0000020dddc5b000: add r9d,0fffffffdh
0.02% 0x0000020dddc5b004: cmp r8d,r9d
0x0000020dddc5b007: jl 20dddc5ae60h
0x0000020dddc5b00d: jmp 20dddc5ae82h
0x0000020dddc5b012: mov edx,0ffffff86h
0x0000020dddc5b017: nop
0x0000020dddc5b018: vzeroupper
0x0000020dddc5b01b: call 20dddbdde80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
98.69% <total for region 1>
....[Hottest Regions]...............................................................................
98.69% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (420 bytes)
0.96% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159 (72 bytes)
0.32% <unknown> (0 bytes)
0.00% runtime stub StubRoutines::atomic_cmpxchg_long (8 bytes)
0.00% jvm.dll 0x0000000070cfb2c6 (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% KernelBase.dll WaitForSingleObjectEx (2 bytes)
0.00% ntdll.dll RtlQueryPerformanceCounter (13 bytes)
0.00% jvm.dll 0x00000000708917b4 (0 bytes)
0.00% jvm.dll 0x000000007090cc27 (0 bytes)
0.00% jvm.dll 0x000000007091fee0 (0 bytes)
0.00% jvm.dll 0x00000000709aaca7 (0 bytes)
0.00% jvm.dll 0x00000000709c97eb (0 bytes)
0.00% jvm.dll 0x0000000070a0b3ea (0 bytes)
0.00% jvm.dll 0x0000000070a0b4d2 (0 bytes)
0.00% jvm.dll 0x0000000070c51797 (0 bytes)
0.00% jvm.dll 0x0000000070c517d5 (0 bytes)
0.00% jvm.dll 0x0000000070c73790 (0 bytes)
0.00% jvm.dll 0x0000000070d383a7 (0 bytes)
0.00% jvm.dll 0x0000000070d5b0ce (0 bytes)
0.01% <...other 7 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
98.69% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161
0.96% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159
0.32% <unknown>
0.00% runtime stub StubRoutines::atomic_cmpxchg_long
0.00% interpreter method entry point (kind = zerolocals)
0.00% ntdll.dll RtlQueryPerformanceCounter
0.00% KernelBase.dll WaitForSingleObjectEx
0.00% jvm.dll 0x0000000070cfb2c6
0.00% jvm.dll 0x0000000070c73790
0.00% interpreter aaload 50 aaload
0.00% interpreter invokespecial 183 invokespecial
0.00% interpreter ldiv 109 ldiv
0.00% jvm.dll 0x0000000070d383a7
0.00% jvm.dll 0x0000000070c517d5
0.00% jvm.dll 0x00000000708917b4
0.00% jvm.dll 0x000000007090cc27
0.00% jvm.dll 0x00000000709c97eb
0.00% interpreter invokeinterface 185 invokeinterface
0.00% kernel32.dll QueryPerformanceCounterStub
0.00% jvm.dll 0x0000000070c51797
0.01% <...other 7 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.65% c2
0.32%
0.01% jvm.dll
0.01% interpreter
0.00% runtime stub
0.00% KernelBase.dll
0.00% ntdll.dll
0.00% kernel32.dll
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 6, size = 1000)
# Run progress: 20.00% complete, ETA 00:24:06
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 2.157 ops/us
# Warmup Iteration 2: 2.517 ops/us
# Warmup Iteration 3: 2.467 ops/us
# Warmup Iteration 4: 2.498 ops/us
# Warmup Iteration 5: 2.458 ops/us
# Warmup Iteration 6: 2.515 ops/us
# Warmup Iteration 7: 2.495 ops/us
# Warmup Iteration 8: 2.598 ops/us
# Warmup Iteration 9: 2.554 ops/us
# Warmup Iteration 10: 2.610 ops/us
Iteration 1: 2.585 ops/us
Iteration 2: 2.452 ops/us
Iteration 3: 2.483 ops/us
Iteration 4: 2.492 ops/us
Iteration 5: 2.565 ops/us
Iteration 6: 2.603 ops/us
Iteration 7: 2.594 ops/us
Iteration 8: 2.565 ops/us
Iteration 9: 2.613 ops/us
Iteration 10: 2.676 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
2.563 ±(99.9%) 0.104 ops/us [Average]
(min, avg, max) = (2.452, 2.563, 2.676), stdev = 0.069
CI (99.9%): [2.459, 2.667] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48541 total address lines.
Perf output processed (skipped 15.242 seconds):
Column 1: SampledProfile (99367 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159 (420 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001d8651de8d0: vzeroupper
0x000001d8651de8d3: add rsp,50h
0x000001d8651de8d7: pop rbp
0x000001d8651de8d8: test dword ptr [1d85aa80000h],eax
; {poll_return}
0x000001d8651de8de: ret
0x000001d8651de8df: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000001d8651de8e0: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.00% 0x000001d8651de8e7: vmulpd ymm0,ymm0,ymm2
0.09% 0x000001d8651de8eb: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
0.23% 0x000001d8651de8f2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.04% 0x000001d8651de8f9: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001d8651de8fd: cmp r8d,r9d
0.03% 0x000001d8651de900: jl 1d8651de8e0h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001d8651de902: cmp r8d,edx
0x000001d8651de905: jnl 1d8651de929h
0.05% 0x000001d8651de907: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001d8651de908: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x000001d8651de90f: vmulsd xmm0,xmm0,xmm1
0x000001d8651de913: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.06% 0x000001d8651de91a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x000001d8651de921: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001d8651de924: cmp r8d,edx
0x000001d8651de927: jl 1d8651de908h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.06% 0x000001d8651de929: mov r8,rbx
0.00% 0x000001d8651de92c: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.04% 0x000001d8651de930: mov rdx,qword ptr [rsp+30h]
0.00% 0x000001d8651de935: nop
0.05% 0x000001d8651de938: vzeroupper
0.08% 0x000001d8651de93b: call 1d86515c480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.00% 0x000001d8651de940: mov r10,qword ptr [rsp+60h]
0.05% 0x000001d8651de945: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.03% 0x000001d8651de94d: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0x000001d8651de951: test dword ptr [1d85aa80000h],eax
; {poll}
0.05% 0x000001d8651de957: test r10d,r10d
0x000001d8651de95a: jne 1d8651de8afh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0x000001d8651de960: mov r10,qword ptr [rsp+70h]
0.03% 0x000001d8651de965: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001d8651de969: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000001d8651deaed
0.06% 0x000001d8651de96e: test edx,edx
0x000001d8651de970: jbe 1d8651de929h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001d8651de972: mov r11d,edx
0.04% 0x000001d8651de975: dec r11d
0x000001d8651de978: cmp r11d,edx
0.00% 0x000001d8651de97b: jnb 1d8651dea92h
0.05% 0x000001d8651de981: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001d8651de985: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000001d8651dea92
0.03% 0x000001d8651de98a: test r9d,r9d
0x000001d8651de98d: jbe 1d8651dea92h
0x000001d8651de993: cmp r11d,r9d
0x000001d8651de996: jnb 1d8651dea92h
0.06% 0x000001d8651de99c: mov r11,qword ptr [rsp+70h]
0.00% 0x000001d8651de9a1: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.04% 0x000001d8651de9a7: lea r11,[r12+rbx*8]
0x000001d8651de9ab: shl r10,3h
0.06% 0x000001d8651de9af: mov r8d,r11d
0x000001d8651de9b2: shr r8d,3h
0.03% 0x000001d8651de9b6: and r8d,3h
0.00% 0x000001d8651de9ba: mov ecx,1h
0.05% 0x000001d8651de9bf: sub ecx,r8d
0x000001d8651de9c2: and ecx,3h
0.03% 0x000001d8651de9c5: inc ecx
0x000001d8651de9c7: cmp ecx,edx
0.06% 0x000001d8651de9c9: cmovnle ecx,edx
0x000001d8651de9cc: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000001d8651de9cf: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x000001d8651de9d6: vmulsd xmm0,xmm0,xmm1
0.10% 0x000001d8651de9da: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.15% 0x000001d8651de9e1: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.05% 0x000001d8651de9e8: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000001d8651de9eb: cmp r8d,ecx
0x000001d8651de9ee: jl 1d8651de9cfh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001d8651de9f0: mov ecx,edx
0.05% 0x000001d8651de9f2: add ecx,0fffffff1h
0.00% 0x000001d8651de9f5: cmp r8d,ecx
0x000001d8651de9f8: jnl 1d8651de902h
0.04% 0x000001d8651de9fe: vpshufd xmm2,xmm1,44h
0x000001d8651dea03: vinsertf128 ymm2,ymm2,xmm2,1h
0.05% 0x000001d8651dea09: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.52% 0x000001d8651dea10: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.39% 0x000001d8651dea17: vmulpd ymm0,ymm0,ymm2
9.90% 0x000001d8651dea1b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
11.75% 0x000001d8651dea22: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
3.11% 0x000001d8651dea29: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
3.23% 0x000001d8651dea30: vmulpd ymm0,ymm0,ymm2
1.39% 0x000001d8651dea34: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
11.49% 0x000001d8651dea3b: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
4.98% 0x000001d8651dea42: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
0.23% 0x000001d8651dea49: vmulpd ymm0,ymm0,ymm2
8.37% 0x000001d8651dea4d: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
14.33% 0x000001d8651dea54: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
3.34% 0x000001d8651dea5b: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
3.85% 0x000001d8651dea62: vmulpd ymm0,ymm0,ymm2
1.80% 0x000001d8651dea66: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
13.73% 0x000001d8651dea6d: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
4.65% 0x000001d8651dea74: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.02% 0x000001d8651dea78: cmp r8d,ecx
0.00% 0x000001d8651dea7b: jl 1d8651dea10h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001d8651dea7d: mov r9d,edx
0.01% 0x000001d8651dea80: add r9d,0fffffffdh
0.07% 0x000001d8651dea84: cmp r8d,r9d
0x000001d8651dea87: jl 1d8651de8e0h
0x000001d8651dea8d: jmp 1d8651de902h
0x000001d8651dea92: mov edx,0ffffff86h
0x000001d8651dea97: nop
0x000001d8651dea98: vzeroupper
0x000001d8651dea9b: call 1d86515de80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
99.26% <total for region 1>
....[Hottest Regions]...............................................................................
99.26% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159 (420 bytes)
0.38% c2 org.openjdk.jmh.infra.Blackhole::consume, version 157 (72 bytes)
0.33% <unknown> (0 bytes)
0.01% runtime stub StubRoutines::atomic_cmpxchg_long (28 bytes)
0.00% jvm.dll 0x0000000070c74821 (8 bytes)
0.00% jvm.dll 0x0000000070cfb2c6 (19 bytes)
0.00% jvm.dll 0x0000000070d5a7b7 (23 bytes)
0.00% ntdll.dll RtlQueryPerformanceCounter (13 bytes)
0.00% jvm.dll 0x00000000709ab58a (0 bytes)
0.00% jvm.dll 0x0000000070a38c40 (0 bytes)
0.00% jvm.dll 0x0000000070c51d89 (0 bytes)
0.00% jvm.dll 0x0000000070c9e655 (0 bytes)
0.00% jvm.dll 0x0000000070d383d7 (0 bytes)
0.00% jvm.dll 0x0000000070d583a5 (0 bytes)
0.00% jvm.dll 0x0000000070d58588 (0 bytes)
0.00% interpreter invoke return entry points (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% interpreter aload_1 43 aload_1 (0 bytes)
0.00% interpreter new 187 new (0 bytes)
0.00% interpreter fast_agetfield 203 fast_agetfield (0 bytes)
0.00% <...other 2 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
99.26% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159
0.38% c2 org.openjdk.jmh.infra.Blackhole::consume, version 157
0.33% <unknown>
0.01% runtime stub StubRoutines::atomic_cmpxchg_long
0.00% jvm.dll 0x0000000070c74821
0.00% jvm.dll 0x0000000070d5a7b7
0.00% jvm.dll 0x0000000070cfb2c6
0.00% ntdll.dll RtlQueryPerformanceCounter
0.00% jvm.dll 0x0000000070d58588
0.00% interpreter aload_1 43 aload_1
0.00% jvm.dll 0x0000000070c51d89
0.00% interpreter invoke return entry points
0.00% jvm.dll 0x0000000070d383d7
0.00% interpreter fast_agetfield 203 fast_agetfield
0.00% jvm.dll 0x00000000709ab58a
0.00% interpreter method entry point (kind = zerolocals)
0.00% msvcr120.dll sqrt
0.00% interpreter new 187 new
0.00% jvm.dll 0x0000000070a38c40
0.00% interpreter fast_igetfield 208 fast_igetfield
0.00% <...other 2 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.64% c2
0.33%
0.01% jvm.dll
0.01% interpreter
0.01% runtime stub
0.00% ntdll.dll
0.00% msvcr120.dll
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 6, size = 1024)
# Run progress: 30.00% complete, ETA 00:20:57
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 6.598 ops/us
# Warmup Iteration 2: 7.063 ops/us
# Warmup Iteration 3: 7.160 ops/us
# Warmup Iteration 4: 6.923 ops/us
# Warmup Iteration 5: 7.090 ops/us
# Warmup Iteration 6: 7.059 ops/us
# Warmup Iteration 7: 7.198 ops/us
# Warmup Iteration 8: 7.005 ops/us
# Warmup Iteration 9: 7.133 ops/us
# Warmup Iteration 10: 7.035 ops/us
Iteration 1: 7.052 ops/us
Iteration 2: 7.051 ops/us
Iteration 3: 7.038 ops/us
Iteration 4: 7.024 ops/us
Iteration 5: 7.022 ops/us
Iteration 6: 6.975 ops/us
Iteration 7: 6.897 ops/us
Iteration 8: 7.097 ops/us
Iteration 9: 6.776 ops/us
Iteration 10: 6.806 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
6.974 ±(99.9%) 0.167 ops/us [Average]
(min, avg, max) = (6.776, 6.974, 7.097), stdev = 0.110
CI (99.9%): [6.807, 7.140] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48534 total address lines.
Perf output processed (skipped 14.124 seconds):
Column 1: SampledProfile (99402 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (420 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001fc0a7220d0: vzeroupper
0x000001fc0a7220d3: add rsp,50h
0x000001fc0a7220d7: pop rbp
0x000001fc0a7220d8: test dword ptr [1fc7de70000h],eax
; {poll_return}
0x000001fc0a7220de: ret
0x000001fc0a7220df: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001fc0a7220e0: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
1.83% 0x000001fc0a7220e7: vmulpd ymm0,ymm0,ymm2
1.42% 0x000001fc0a7220eb: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
1.60% 0x000001fc0a7220f2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.71% 0x000001fc0a7220f9: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001fc0a7220fd: cmp r8d,r9d
0x000001fc0a722100: jl 1fc0a7220e0h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001fc0a722102: cmp r8d,edx
0x000001fc0a722105: jnl 1fc0a722129h
0.23% 0x000001fc0a722107: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001fc0a722108: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001fc0a72210f: vmulsd xmm0,xmm0,xmm1
0.00% 0x000001fc0a722113: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.22% 0x000001fc0a72211a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001fc0a722121: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001fc0a722124: cmp r8d,edx
0.00% 0x000001fc0a722127: jl 1fc0a722108h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.20% 0x000001fc0a722129: mov r8,rbx
0.00% 0x000001fc0a72212c: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001fc0a722130: mov rdx,qword ptr [rsp+30h]
0.00% 0x000001fc0a722135: nop
0.23% 0x000001fc0a722138: vzeroupper
0.21% 0x000001fc0a72213b: call 1fc0a69c480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.23% 0x000001fc0a722140: mov r10,qword ptr [rsp+60h]
0.09% 0x000001fc0a722145: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.00% 0x000001fc0a72214d: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.12% 0x000001fc0a722151: test dword ptr [1fc7de70000h],eax
; {poll}
0.08% 0x000001fc0a722157: test r10d,r10d
0x000001fc0a72215a: jne 1fc0a7220afh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0x000001fc0a722160: mov r10,qword ptr [rsp+70h]
0x000001fc0a722165: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.13% 0x000001fc0a722169: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000001fc0a7222ed
0.44% 0x000001fc0a72216e: test edx,edx
0x000001fc0a722170: jbe 1fc0a722129h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.28% 0x000001fc0a722172: mov r11d,edx
0.00% 0x000001fc0a722175: dec r11d
0.00% 0x000001fc0a722178: cmp r11d,edx
0.00% 0x000001fc0a72217b: jnb 1fc0a722292h
0.19% 0x000001fc0a722181: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.02% 0x000001fc0a722185: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000001fc0a722292
0.00% 0x000001fc0a72218a: test r9d,r9d
0x000001fc0a72218d: jbe 1fc0a722292h
0x000001fc0a722193: cmp r11d,r9d
0x000001fc0a722196: jnb 1fc0a722292h
0.21% 0x000001fc0a72219c: mov r11,qword ptr [rsp+70h]
0.03% 0x000001fc0a7221a1: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001fc0a7221a7: lea r11,[r12+rbx*8]
0.00% 0x000001fc0a7221ab: shl r10,3h
0.19% 0x000001fc0a7221af: mov r8d,r11d
0.02% 0x000001fc0a7221b2: shr r8d,3h
0x000001fc0a7221b6: and r8d,3h
0x000001fc0a7221ba: mov ecx,1h
0.21% 0x000001fc0a7221bf: sub ecx,r8d
0.04% 0x000001fc0a7221c2: and ecx,3h
0x000001fc0a7221c5: inc ecx
0.00% 0x000001fc0a7221c7: cmp ecx,edx
0.21% 0x000001fc0a7221c9: cmovnle ecx,edx
0.02% 0x000001fc0a7221cc: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.15% 0x000001fc0a7221cf: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.02% 0x000001fc0a7221d6: vmulsd xmm0,xmm0,xmm1
0.27% 0x000001fc0a7221da: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.37% 0x000001fc0a7221e1: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.09% 0x000001fc0a7221e8: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.22% 0x000001fc0a7221eb: cmp r8d,ecx
0x000001fc0a7221ee: jl 1fc0a7221cfh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.07% 0x000001fc0a7221f0: mov ecx,edx
0.11% 0x000001fc0a7221f2: add ecx,0fffffff1h
0.02% 0x000001fc0a7221f5: cmp r8d,ecx
0x000001fc0a7221f8: jnl 1fc0a722102h
0x000001fc0a7221fe: vpshufd xmm2,xmm1,44h
0.08% 0x000001fc0a722203: vinsertf128 ymm2,ymm2,xmm2,1h
0.11% 0x000001fc0a722209: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.36% 0x000001fc0a722210: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
8.93% 0x000001fc0a722217: vmulpd ymm0,ymm0,ymm2
0.32% 0x000001fc0a72221b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
7.89% 0x000001fc0a722222: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
9.64% 0x000001fc0a722229: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
0.18% 0x000001fc0a722230: vmulpd ymm0,ymm0,ymm2
4.37% 0x000001fc0a722234: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
10.06% 0x000001fc0a72223b: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
0.47% 0x000001fc0a722242: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
4.13% 0x000001fc0a722249: vmulpd ymm0,ymm0,ymm2
0.34% 0x000001fc0a72224d: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
12.62% 0x000001fc0a722254: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
8.95% 0x000001fc0a72225b: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
0.14% 0x000001fc0a722262: vmulpd ymm0,ymm0,ymm2
4.89% 0x000001fc0a722266: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
9.50% 0x000001fc0a72226d: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.21% 0x000001fc0a722274: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
4.85% 0x000001fc0a722278: cmp r8d,ecx
0x000001fc0a72227b: jl 1fc0a722210h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001fc0a72227d: mov r9d,edx
0.24% 0x000001fc0a722280: add r9d,0fffffffdh
0.02% 0x000001fc0a722284: cmp r8d,r9d
0x000001fc0a722287: jl 1fc0a7220e0h
0x000001fc0a72228d: jmp 1fc0a722102h
0x000001fc0a722292: mov edx,0ffffff86h
0x000001fc0a722297: nop
0x000001fc0a722298: vzeroupper
0x000001fc0a72229b: call 1fc0a69de80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
98.82% <total for region 1>
....[Hottest Regions]...............................................................................
98.82% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (420 bytes)
0.94% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159 (72 bytes)
0.22% <unknown> (0 bytes)
0.00% runtime stub StubRoutines::atomic_cmpxchg_long (8 bytes)
0.00% jvm.dll 0x000000007090cc27 (0 bytes)
0.00% KernelBase.dll WaitForSingleObjectEx (0 bytes)
0.00% ntdll.dll RtlQueryPerformanceCounter (11 bytes)
0.00% jvm.dll 0x00000000707d8730 (0 bytes)
0.00% jvm.dll 0x000000007099e240 (0 bytes)
0.00% jvm.dll 0x00000000709aa954 (0 bytes)
0.00% jvm.dll 0x00000000709c9960 (0 bytes)
0.00% jvm.dll 0x0000000070a0b4d2 (0 bytes)
0.00% jvm.dll 0x0000000070aa5e2c (0 bytes)
0.00% jvm.dll 0x0000000070c9e640 (0 bytes)
0.00% jvm.dll 0x0000000070cfb2ca (0 bytes)
0.00% jvm.dll 0x0000000070d583a0 (0 bytes)
0.00% jvm.dll 0x0000000070d58524 (0 bytes)
0.00% jvm.dll 0x0000000070d6e9af (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% interpreter invokevirtual 182 invokevirtual (0 bytes)
0.00% <...other 2 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
98.82% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161
0.94% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159
0.22% <unknown>
0.00% runtime stub StubRoutines::atomic_cmpxchg_long
0.00% KernelBase.dll WaitForSingleObjectEx
0.00% jvm.dll 0x000000007090cc27
0.00% ntdll.dll RtlQueryPerformanceCounter
0.00% kernel32.dll GetCurrentThread
0.00% jvm.dll 0x00000000709aa954
0.00% interpreter invokevirtual 182 invokevirtual
0.00% jvm.dll 0x0000000070aa5e2c
0.00% jvm.dll 0x0000000070c9e640
0.00% jvm.dll 0x000000007099e240
0.00% jvm.dll 0x00000000707d8730
0.00% kernel32.dll WaitForSingleObject
0.00% jvm.dll 0x0000000070cfb2ca
0.00% jvm.dll 0x0000000070d58524
0.00% jvm.dll 0x0000000070d6e9af
0.00% jvm.dll 0x0000000070d583a0
0.00% interpreter method entry point (kind = zerolocals)
0.00% <...other 2 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.75% c2
0.22%
0.01% jvm.dll
0.00% runtime stub
0.00% KernelBase.dll
0.00% ntdll.dll
0.00% interpreter
0.00% kernel32.dll
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 12, size = 1000)
# Run progress: 40.00% complete, ETA 00:17:39
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 3.636 ops/us
# Warmup Iteration 2: 3.698 ops/us
# Warmup Iteration 3: 3.776 ops/us
# Warmup Iteration 4: 3.959 ops/us
# Warmup Iteration 5: 3.649 ops/us
# Warmup Iteration 6: 3.964 ops/us
# Warmup Iteration 7: 3.993 ops/us
# Warmup Iteration 8: 3.881 ops/us
# Warmup Iteration 9: 3.967 ops/us
# Warmup Iteration 10: 3.897 ops/us
Iteration 1: 3.915 ops/us
Iteration 2: 3.862 ops/us
Iteration 3: 3.839 ops/us
Iteration 4: 3.843 ops/us
Iteration 5: 3.842 ops/us
Iteration 6: 3.884 ops/us
Iteration 7: 3.865 ops/us
Iteration 8: 3.660 ops/us
Iteration 9: 3.785 ops/us
Iteration 10: 3.917 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
3.841 ±(99.9%) 0.113 ops/us [Average]
(min, avg, max) = (3.660, 3.841, 3.917), stdev = 0.075
CI (99.9%): [3.729, 3.954] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48341 total address lines.
Perf output processed (skipped 14.915 seconds):
Column 1: SampledProfile (99307 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159 (420 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001b375c11650: vzeroupper
0x000001b375c11653: add rsp,50h
0x000001b375c11657: pop rbp
0x000001b375c11658: test dword ptr [1b369a80000h],eax
; {poll_return}
0x000001b375c1165e: ret
0x000001b375c1165f: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001b375c11660: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.00% 0x000001b375c11667: vmulpd ymm0,ymm0,ymm2
0.06% 0x000001b375c1166b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
0.12% 0x000001b375c11672: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000001b375c11679: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.04% 0x000001b375c1167d: cmp r8d,r9d
0.07% 0x000001b375c11680: jl 1b375c11660h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001b375c11682: cmp r8d,edx
0x000001b375c11685: jnl 1b375c116a9h
0.02% 0x000001b375c11687: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x000001b375c11688: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000001b375c1168f: vmulsd xmm0,xmm0,xmm1
0.00% 0x000001b375c11693: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.07% 0x000001b375c1169a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.09% 0x000001b375c116a1: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001b375c116a4: cmp r8d,edx
0x000001b375c116a7: jl 1b375c11688h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.02% 0x000001b375c116a9: mov r8,rbx
0.03% 0x000001b375c116ac: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000001b375c116b0: mov rdx,qword ptr [rsp+30h]
0.00% 0x000001b375c116b5: nop
0.02% 0x000001b375c116b8: vzeroupper
0.15% 0x000001b375c116bb: call 1b375b8c480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.00% 0x000001b375c116c0: mov r10,qword ptr [rsp+60h]
0.06% 0x000001b375c116c5: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.07% 0x000001b375c116cd: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.00% 0x000001b375c116d1: test dword ptr [1b369a80000h],eax
; {poll}
0.02% 0x000001b375c116d7: test r10d,r10d
0x000001b375c116da: jne 1b375c1162fh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0.02% 0x000001b375c116e0: mov r10,qword ptr [rsp+70h]
0.08% 0x000001b375c116e5: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001b375c116e9: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000001b375c1186d
0.02% 0x000001b375c116ee: test edx,edx
0x000001b375c116f0: jbe 1b375c116a9h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x000001b375c116f2: mov r11d,edx
0.08% 0x000001b375c116f5: dec r11d
0x000001b375c116f8: cmp r11d,edx
0.00% 0x000001b375c116fb: jnb 1b375c11812h
0.01% 0x000001b375c11701: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x000001b375c11705: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000001b375c11812
0.08% 0x000001b375c1170a: test r9d,r9d
0x000001b375c1170d: jbe 1b375c11812h
0x000001b375c11713: cmp r11d,r9d
0x000001b375c11716: jnb 1b375c11812h
0.01% 0x000001b375c1171c: mov r11,qword ptr [rsp+70h]
0.03% 0x000001b375c11721: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000001b375c11727: lea r11,[r12+rbx*8]
0x000001b375c1172b: shl r10,3h
0.01% 0x000001b375c1172f: mov r8d,r11d
0.03% 0x000001b375c11732: shr r8d,3h
0.10% 0x000001b375c11736: and r8d,3h
0x000001b375c1173a: mov ecx,1h
0.01% 0x000001b375c1173f: sub ecx,r8d
0.03% 0x000001b375c11742: and ecx,3h
0.11% 0x000001b375c11745: inc ecx
0x000001b375c11747: cmp ecx,edx
0.02% 0x000001b375c11749: cmovnle ecx,edx
0.03% 0x000001b375c1174c: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.13% 0x000001b375c1174f: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.13% 0x000001b375c11756: vmulsd xmm0,xmm0,xmm1
0.16% 0x000001b375c1175a: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.53% 0x000001b375c11761: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.20% 0x000001b375c11768: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x000001b375c1176b: cmp r8d,ecx
0x000001b375c1176e: jl 1b375c1174fh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001b375c11770: mov ecx,edx
0.01% 0x000001b375c11772: add ecx,0fffffff1h
0.09% 0x000001b375c11775: cmp r8d,ecx
0x000001b375c11778: jnl 1b375c11682h
0.02% 0x000001b375c1177e: vpshufd xmm2,xmm1,44h
0x000001b375c11783: vinsertf128 ymm2,ymm2,xmm2,1h
0.01% 0x000001b375c11789: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
1.48% 0x000001b375c11790: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.47% 0x000001b375c11797: vmulpd ymm0,ymm0,ymm2
8.86% 0x000001b375c1179b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
7.64% 0x000001b375c117a2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
3.76% 0x000001b375c117a9: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
8.38% 0x000001b375c117b0: vmulpd ymm0,ymm0,ymm2
1.69% 0x000001b375c117b4: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
13.64% 0x000001b375c117bb: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
6.62% 0x000001b375c117c2: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
0.02% 0x000001b375c117c9: vmulpd ymm0,ymm0,ymm2
4.56% 0x000001b375c117cd: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
12.03% 0x000001b375c117d4: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
3.69% 0x000001b375c117db: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
0.67% 0x000001b375c117e2: vmulpd ymm0,ymm0,ymm2
0.30% 0x000001b375c117e6: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
15.85% 0x000001b375c117ed: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
6.11% 0x000001b375c117f4: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000001b375c117f8: cmp r8d,ecx
0x000001b375c117fb: jl 1b375c11790h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001b375c117fd: mov r9d,edx
0.02% 0x000001b375c11800: add r9d,0fffffffdh
0.09% 0x000001b375c11804: cmp r8d,r9d
0x000001b375c11807: jl 1b375c11660h
0x000001b375c1180d: jmp 1b375c11682h
0x000001b375c11812: mov edx,0ffffff86h
0x000001b375c11817: nop
0x000001b375c11818: vzeroupper
0x000001b375c1181b: call 1b375b8de80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
99.05% <total for region 1>
....[Hottest Regions]...............................................................................
99.05% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159 (420 bytes)
0.63% c2 org.openjdk.jmh.infra.Blackhole::consume, version 157 (72 bytes)
0.27% <unknown> (0 bytes)
0.01% runtime stub StubRoutines::atomic_cmpxchg_long (36 bytes)
0.01% jvm.dll 0x0000000070c7481f (10 bytes)
0.00% jvm.dll 0x0000000070c9e640 (30 bytes)
0.00% jvm.dll 0x0000000070c51d79 (16 bytes)
0.00% kernel32.dll QueryPerformanceCounterStub (0 bytes)
0.00% jvm.dll 0x000000007090cc27 (0 bytes)
0.00% jvm.dll 0x0000000070c514c0 (0 bytes)
0.00% jvm.dll 0x0000000070c51797 (0 bytes)
0.00% jvm.dll 0x0000000070c517d5 (0 bytes)
0.00% jvm.dll 0x0000000070c71630 (0 bytes)
0.00% jvm.dll 0x0000000070cfb2dc (0 bytes)
0.00% jvm.dll 0x0000000070d383d7 (0 bytes)
0.00% jvm.dll 0x0000000070d583a0 (0 bytes)
0.00% jvm.dll 0x0000000070d5a7b7 (0 bytes)
0.00% interpreter invoke return entry points (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.01% <...other 6 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
99.05% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159
0.63% c2 org.openjdk.jmh.infra.Blackhole::consume, version 157
0.27% <unknown>
0.01% runtime stub StubRoutines::atomic_cmpxchg_long
0.01% jvm.dll 0x0000000070c7481f
0.00% jvm.dll 0x0000000070c9e640
0.00% interpreter method entry point (kind = zerolocals)
0.00% jvm.dll 0x0000000070c51d79
0.00% kernel32.dll QueryPerformanceCounterStub
0.00% interpreter invoke return entry points
0.00% jvm.dll 0x0000000070d383d7
0.00% interpreter invokespecial 183 invokespecial
0.00% interpreter method entry point (kind = native)
0.00% jvm.dll 0x0000000070c71630
0.00% jvm.dll 0x0000000070c517d5
0.00% jvm.dll 0x0000000070c514c0
0.00% jvm.dll 0x000000007090cc27
0.00% jvm.dll 0x0000000070c51797
0.00% interpreter invokevirtual 182 invokevirtual
0.00% jvm.dll 0x0000000070cfb2dc
0.01% <...other 5 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.69% c2
0.27%
0.02% jvm.dll
0.01% runtime stub
0.01% interpreter
0.00% kernel32.dll
0.00% msvcr120.dll
0.00% KernelBase.dll
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 12, size = 1024)
# Run progress: 50.00% complete, ETA 00:14:37
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 6.604 ops/us
# Warmup Iteration 2: 6.632 ops/us
# Warmup Iteration 3: 6.613 ops/us
# Warmup Iteration 4: 6.907 ops/us
# Warmup Iteration 5: 6.689 ops/us
# Warmup Iteration 6: 6.039 ops/us
# Warmup Iteration 7: 6.595 ops/us
# Warmup Iteration 8: 6.055 ops/us
# Warmup Iteration 9: 6.640 ops/us
# Warmup Iteration 10: 6.749 ops/us
Iteration 1: 6.853 ops/us
Iteration 2: 6.621 ops/us
Iteration 3: 6.759 ops/us
Iteration 4: 6.528 ops/us
Iteration 5: 6.647 ops/us
Iteration 6: 6.898 ops/us
Iteration 7: 5.874 ops/us
Iteration 8: 6.490 ops/us
Iteration 9: 6.196 ops/us
Iteration 10: 6.699 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
6.556 ±(99.9%) 0.472 ops/us [Average]
(min, avg, max) = (5.874, 6.556, 6.898), stdev = 0.312
CI (99.9%): [6.084, 7.029] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48339 total address lines.
Perf output processed (skipped 14.092 seconds):
Column 1: SampledProfile (99507 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159 (420 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000235b17eb550: vzeroupper
0x00000235b17eb553: add rsp,50h
0x00000235b17eb557: pop rbp
0x00000235b17eb558: test dword ptr [235a5860000h],eax
; {poll_return}
0x00000235b17eb55e: ret
0x00000235b17eb55f: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x00000235b17eb560: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.65% 0x00000235b17eb567: vmulpd ymm0,ymm0,ymm2
0.99% 0x00000235b17eb56b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
1.75% 0x00000235b17eb572: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.68% 0x00000235b17eb579: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000235b17eb57d: cmp r8d,r9d
0.01% 0x00000235b17eb580: jl 235b17eb560h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000235b17eb582: cmp r8d,edx
0x00000235b17eb585: jnl 235b17eb5a9h
0.24% 0x00000235b17eb587: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.21% 0x00000235b17eb588: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.23% 0x00000235b17eb58f: vmulsd xmm0,xmm0,xmm1
0.00% 0x00000235b17eb593: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.51% 0x00000235b17eb59a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.24% 0x00000235b17eb5a1: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000235b17eb5a4: cmp r8d,edx
0x00000235b17eb5a7: jl 235b17eb588h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000235b17eb5a9: mov r8,rbx
0x00000235b17eb5ac: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.22% 0x00000235b17eb5b0: mov rdx,qword ptr [rsp+30h]
0.00% 0x00000235b17eb5b5: nop
0.00% 0x00000235b17eb5b8: vzeroupper
0.22% 0x00000235b17eb5bb: call 235b176c480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.41% 0x00000235b17eb5c0: mov r10,qword ptr [rsp+60h]
0.01% 0x00000235b17eb5c5: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.10% 0x00000235b17eb5cd: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.12% 0x00000235b17eb5d1: test dword ptr [235a5860000h],eax
; {poll}
0.01% 0x00000235b17eb5d7: test r10d,r10d
0x00000235b17eb5da: jne 235b17eb52fh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0x00000235b17eb5e0: mov r10,qword ptr [rsp+70h]
0.10% 0x00000235b17eb5e5: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.15% 0x00000235b17eb5e9: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x00000235b17eb76d
0.37% 0x00000235b17eb5ee: test edx,edx
0x00000235b17eb5f0: jbe 235b17eb5a9h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.12% 0x00000235b17eb5f2: mov r11d,edx
0x00000235b17eb5f5: dec r11d
0.12% 0x00000235b17eb5f8: cmp r11d,edx
0.00% 0x00000235b17eb5fb: jnb 235b17eb712h
0.13% 0x00000235b17eb601: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000235b17eb605: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x00000235b17eb712
0.01% 0x00000235b17eb60a: test r9d,r9d
0x00000235b17eb60d: jbe 235b17eb712h
0.10% 0x00000235b17eb613: cmp r11d,r9d
0x00000235b17eb616: jnb 235b17eb712h
0.13% 0x00000235b17eb61c: mov r11,qword ptr [rsp+70h]
0x00000235b17eb621: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x00000235b17eb627: lea r11,[r12+rbx*8]
0.11% 0x00000235b17eb62b: shl r10,3h
0.12% 0x00000235b17eb62f: mov r8d,r11d
0x00000235b17eb632: shr r8d,3h
0x00000235b17eb636: and r8d,3h
0.09% 0x00000235b17eb63a: mov ecx,1h
0.11% 0x00000235b17eb63f: sub ecx,r8d
0x00000235b17eb642: and ecx,3h
0x00000235b17eb645: inc ecx
0.10% 0x00000235b17eb647: cmp ecx,edx
0.11% 0x00000235b17eb649: cmovnle ecx,edx
0.00% 0x00000235b17eb64c: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000235b17eb64f: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.11% 0x00000235b17eb656: vmulsd xmm0,xmm0,xmm1
0.13% 0x00000235b17eb65a: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.14% 0x00000235b17eb661: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.16% 0x00000235b17eb668: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x00000235b17eb66b: cmp r8d,ecx
0x00000235b17eb66e: jl 235b17eb64fh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000235b17eb670: mov ecx,edx
0x00000235b17eb672: add ecx,0fffffff1h
0.18% 0x00000235b17eb675: cmp r8d,ecx
0x00000235b17eb678: jnl 235b17eb582h
0.03% 0x00000235b17eb67e: vpshufd xmm2,xmm1,44h
0.00% 0x00000235b17eb683: vinsertf128 ymm2,ymm2,xmm2,1h
0x00000235b17eb689: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
6.55% 0x00000235b17eb690: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.44% 0x00000235b17eb697: vmulpd ymm0,ymm0,ymm2
6.79% 0x00000235b17eb69b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
6.69% 0x00000235b17eb6a2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
0.53% 0x00000235b17eb6a9: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
7.21% 0x00000235b17eb6b0: vmulpd ymm0,ymm0,ymm2
0.43% 0x00000235b17eb6b4: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
10.06% 0x00000235b17eb6bb: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
11.30% 0x00000235b17eb6c2: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
0.09% 0x00000235b17eb6c9: vmulpd ymm0,ymm0,ymm2
2.19% 0x00000235b17eb6cd: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
11.69% 0x00000235b17eb6d4: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
0.44% 0x00000235b17eb6db: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
2.45% 0x00000235b17eb6e2: vmulpd ymm0,ymm0,ymm2
0.51% 0x00000235b17eb6e6: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
14.45% 0x00000235b17eb6ed: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
6.89% 0x00000235b17eb6f4: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.20% 0x00000235b17eb6f8: cmp r8d,ecx
0.01% 0x00000235b17eb6fb: jl 235b17eb690h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.15% 0x00000235b17eb6fd: mov r9d,edx
0.01% 0x00000235b17eb700: add r9d,0fffffffdh
0.10% 0x00000235b17eb704: cmp r8d,r9d
0x00000235b17eb707: jl 235b17eb560h
0x00000235b17eb70d: jmp 235b17eb582h
0x00000235b17eb712: mov edx,0ffffff86h
0x00000235b17eb717: nop
0x00000235b17eb718: vzeroupper
0x00000235b17eb71b: call 235b176de80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
98.44% <total for region 1>
....[Hottest Regions]...............................................................................
98.44% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159 (420 bytes)
1.12% c2 org.openjdk.jmh.infra.Blackhole::consume, version 157 (72 bytes)
0.41% <unknown> (0 bytes)
0.01% runtime stub StubRoutines::atomic_cmpxchg_long (36 bytes)
0.00% jvm.dll 0x0000000070c74821 (8 bytes)
0.00% jvm.dll 0x0000000070994f78 (0 bytes)
0.00% jvm.dll 0x000000007099e247 (0 bytes)
0.00% jvm.dll 0x0000000070d5a7b7 (0 bytes)
0.00% jvm.dll 0x000000007090cc27 (0 bytes)
0.00% jvm.dll 0x0000000070a0b4d2 (0 bytes)
0.00% jvm.dll 0x0000000070a681b4 (0 bytes)
0.00% jvm.dll 0x0000000070c51797 (0 bytes)
0.00% jvm.dll 0x0000000070c5ef38 (0 bytes)
0.00% jvm.dll 0x0000000070c69b30 (0 bytes)
0.00% jvm.dll 0x0000000070c737cf (0 bytes)
0.00% jvm.dll 0x0000000070c747ec (0 bytes)
0.00% jvm.dll 0x0000000070c9e65e (0 bytes)
0.00% jvm.dll 0x0000000070cfb2ca (0 bytes)
0.00% jvm.dll 0x0000000070d3837d (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% <...other 4 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
98.44% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159
1.12% c2 org.openjdk.jmh.infra.Blackhole::consume, version 157
0.41% <unknown>
0.01% runtime stub StubRoutines::atomic_cmpxchg_long
0.00% jvm.dll 0x0000000070c74821
0.00% jvm.dll 0x0000000070994f78
0.00% jvm.dll 0x000000007099e247
0.00% jvm.dll 0x0000000070d5a7b7
0.00% jvm.dll 0x0000000070c51797
0.00% jvm.dll 0x0000000070d3837d
0.00% interpreter invokevirtual 182 invokevirtual
0.00% interpreter astore_1 76 astore_1
0.00% jvm.dll 0x0000000070c69b30
0.00% jvm.dll 0x0000000070cfb2ca
0.00% jvm.dll 0x0000000070c5ef38
0.00% interpreter fast_agetfield 203 fast_agetfield
0.00% jvm.dll 0x0000000070c9e65e
0.00% jvm.dll 0x0000000070c747ec
0.00% interpreter method entry point (kind = zerolocals)
0.00% interpreter fast_aaccess_0 222 fast_aaccess_0
0.00% <...other 4 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.56% c2
0.41%
0.02% jvm.dll
0.01% runtime stub
0.01% interpreter
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 18, size = 1000)
# Run progress: 60.00% complete, ETA 00:12:21
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 5.893 ops/us
# Warmup Iteration 2: 6.881 ops/us
# Warmup Iteration 3: 6.349 ops/us
# Warmup Iteration 4: 6.933 ops/us
# Warmup Iteration 5: 6.914 ops/us
# Warmup Iteration 6: 6.664 ops/us
# Warmup Iteration 7: 6.858 ops/us
# Warmup Iteration 8: 7.167 ops/us
# Warmup Iteration 9: 6.953 ops/us
# Warmup Iteration 10: 6.663 ops/us
Iteration 1: 6.797 ops/us
Iteration 2: 7.025 ops/us
Iteration 3: 6.993 ops/us
Iteration 4: 6.986 ops/us
Iteration 5: 6.850 ops/us
Iteration 6: 6.802 ops/us
Iteration 7: 6.986 ops/us
Iteration 8: 6.932 ops/us
Iteration 9: 6.651 ops/us
Iteration 10: 6.619 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
6.864 ±(99.9%) 0.220 ops/us [Average]
(min, avg, max) = (6.619, 6.864, 7.025), stdev = 0.146
CI (99.9%): [6.644, 7.084] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48612 total address lines.
Perf output processed (skipped 14.578 seconds):
Column 1: SampledProfile (99224 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (347 bytes)
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023278c425a1: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023278c425a4: cmp r8d,edx
0x0000023278c425a7: jl 23278c42588h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.24% 0x0000023278c425a9: mov r8,rbx
0x0000023278c425ac: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023278c425b0: mov rdx,qword ptr [rsp+30h]
0.00% 0x0000023278c425b5: nop
0.22% 0x0000023278c425b8: vzeroupper
0.21% 0x0000023278c425bb: call 23278bbc480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.75% 0x0000023278c425c0: mov r10,qword ptr [rsp+60h]
0.05% 0x0000023278c425c5: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.00% 0x0000023278c425cd: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.17% 0x0000023278c425d1: test dword ptr [232771c0000h],eax
; {poll}
0.04% 0x0000023278c425d7: test r10d,r10d
0x0000023278c425da: jne 23278c4252fh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0x0000023278c425e0: mov r10,qword ptr [rsp+70h]
0.00% 0x0000023278c425e5: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.21% 0x0000023278c425e9: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x0000023278c4276d
0.06% 0x0000023278c425ee: test edx,edx
0x0000023278c425f0: jbe 23278c425a9h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000023278c425f2: mov r11d,edx
0.00% 0x0000023278c425f5: dec r11d
0.18% 0x0000023278c425f8: cmp r11d,edx
0x0000023278c425fb: jnb 23278c42712h
0.05% 0x0000023278c42601: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023278c42605: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x0000023278c42712
0.01% 0x0000023278c4260a: test r9d,r9d
0x0000023278c4260d: jbe 23278c42712h
0.17% 0x0000023278c42613: cmp r11d,r9d
0x0000023278c42616: jnb 23278c42712h
0.05% 0x0000023278c4261c: mov r11,qword ptr [rsp+70h]
0.00% 0x0000023278c42621: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023278c42627: lea r11,[r12+rbx*8]
0.18% 0x0000023278c4262b: shl r10,3h
0.04% 0x0000023278c4262f: mov r8d,r11d
0x0000023278c42632: shr r8d,3h
0x0000023278c42636: and r8d,3h
0.18% 0x0000023278c4263a: mov ecx,1h
0.05% 0x0000023278c4263f: sub ecx,r8d
0x0000023278c42642: and ecx,3h
0x0000023278c42645: inc ecx
0.19% 0x0000023278c42647: cmp ecx,edx
0.06% 0x0000023278c42649: cmovnle ecx,edx
0x0000023278c4264c: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.23% 0x0000023278c4264f: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.19% 0x0000023278c42656: vmulsd xmm0,xmm0,xmm1
0.29% 0x0000023278c4265a: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.54% 0x0000023278c42661: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.23% 0x0000023278c42668: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.19% 0x0000023278c4266b: cmp r8d,ecx
0x0000023278c4266e: jl 23278c4264fh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023278c42670: mov ecx,edx
0.24% 0x0000023278c42672: add ecx,0fffffff1h
0.00% 0x0000023278c42675: cmp r8d,ecx
0x0000023278c42678: jnl 23278c42582h
0.00% 0x0000023278c4267e: vpshufd xmm2,xmm1,44h
0x0000023278c42683: vinsertf128 ymm2,ymm2,xmm2,1h
0.22% 0x0000023278c42689: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.19% 0x0000023278c42690: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
10.04% 0x0000023278c42697: vmulpd ymm0,ymm0,ymm2
0.33% 0x0000023278c4269b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
7.15% 0x0000023278c426a2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
11.26% 0x0000023278c426a9: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
0.05% 0x0000023278c426b0: vmulpd ymm0,ymm0,ymm2
3.25% 0x0000023278c426b4: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
11.12% 0x0000023278c426bb: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
0.25% 0x0000023278c426c2: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
3.02% 0x0000023278c426c9: vmulpd ymm0,ymm0,ymm2
0.12% 0x0000023278c426cd: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
13.64% 0x0000023278c426d4: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
10.20% 0x0000023278c426db: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
0.04% 0x0000023278c426e2: vmulpd ymm0,ymm0,ymm2
4.07% 0x0000023278c426e6: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
10.43% 0x0000023278c426ed: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.18% 0x0000023278c426f4: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
3.91% 0x0000023278c426f8: cmp r8d,ecx
0x0000023278c426fb: jl 23278c42690h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000023278c426fd: mov r9d,edx
0.22% 0x0000023278c42700: add r9d,0fffffffdh
0.01% 0x0000023278c42704: cmp r8d,r9d
0x0000023278c42707: jl 23278c42560h
0x0000023278c4270d: jmp 23278c42582h
0x0000023278c42712: mov edx,0ffffff86h
0x0000023278c42717: nop
0x0000023278c42718: vzeroupper
0x0000023278c4271b: call 23278bbde80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
94.73% <total for region 1>
....[Hottest Regions]...............................................................................
94.73% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (347 bytes)
3.92% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (32 bytes)
1.01% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159 (72 bytes)
0.30% <unknown> (0 bytes)
0.01% runtime stub StubRoutines::atomic_cmpxchg_long (30 bytes)
0.00% jvm.dll 0x0000000070cfb2b0 (41 bytes)
0.00% interpreter method entry point (kind = zerolocals) (4 bytes)
0.00% KernelBase.dll WaitForSingleObjectEx (0 bytes)
0.00% jvm.dll 0x0000000070c517d5 (0 bytes)
0.00% jvm.dll 0x0000000070c7481f (10 bytes)
0.00% jvm.dll 0x0000000070c9e640 (30 bytes)
0.00% jvm.dll 0x0000000070798b90 (0 bytes)
0.00% jvm.dll 0x00000000708a77ac (0 bytes)
0.00% jvm.dll 0x000000007090cc27 (0 bytes)
0.00% jvm.dll 0x000000007099e247 (0 bytes)
0.00% jvm.dll 0x00000000709aa950 (0 bytes)
0.00% jvm.dll 0x0000000070c52101 (0 bytes)
0.00% jvm.dll 0x0000000070c5ef38 (0 bytes)
0.00% jvm.dll 0x0000000070c74730 (0 bytes)
0.00% jvm.dll 0x0000000070d28eb1 (0 bytes)
0.01% <...other 10 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
98.65% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161
1.01% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159
0.30% <unknown>
0.01% runtime stub StubRoutines::atomic_cmpxchg_long
0.01% interpreter method entry point (kind = zerolocals)
0.00% jvm.dll 0x0000000070cfb2b0
0.00% KernelBase.dll WaitForSingleObjectEx
0.00% jvm.dll 0x0000000070c517d5
0.00% jvm.dll 0x0000000070c9e640
0.00% jvm.dll 0x0000000070c7481f
0.00% jvm.dll 0x0000000070d383d7
0.00% interpreter method entry point (kind = native)
0.00% kernel32.dll GetThreadTimesStub
0.00% jvm.dll 0x0000000070d28eb1
0.00% jvm.dll 0x0000000070c74730
0.00% jvm.dll 0x000000007090cc27
0.00% kernel32.dll QueryPerformanceCounterStub
0.00% jvm.dll 0x0000000070c52101
0.00% jvm.dll 0x0000000070798b90
0.00% jvm.dll 0x00000000709aa950
0.01% <...other 6 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.66% c2
0.30%
0.02% jvm.dll
0.01% runtime stub
0.01% interpreter
0.00% KernelBase.dll
0.00% kernel32.dll
0.00% msvcr120.dll
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 18, size = 1024)
# Run progress: 70.00% complete, ETA 00:09:12
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 6.948 ops/us
# Warmup Iteration 2: 7.073 ops/us
# Warmup Iteration 3: 7.131 ops/us
# Warmup Iteration 4: 7.253 ops/us
# Warmup Iteration 5: 7.077 ops/us
# Warmup Iteration 6: 7.083 ops/us
# Warmup Iteration 7: 7.205 ops/us
# Warmup Iteration 8: 7.015 ops/us
# Warmup Iteration 9: 7.235 ops/us
# Warmup Iteration 10: 6.980 ops/us
Iteration 1: 6.839 ops/us
Iteration 2: 6.482 ops/us
Iteration 3: 5.821 ops/us
Iteration 4: 5.847 ops/us
Iteration 5: 5.319 ops/us
Iteration 6: 5.280 ops/us
Iteration 7: 5.974 ops/us
Iteration 8: 5.850 ops/us
Iteration 9: 6.001 ops/us
Iteration 10: 6.461 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
5.987 ±(99.9%) 0.749 ops/us [Average]
(min, avg, max) = (5.280, 5.987, 6.839), stdev = 0.495
CI (99.9%): [5.239, 6.736] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48371 total address lines.
Perf output processed (skipped 14.009 seconds):
Column 1: SampledProfile (98301 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159 (420 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023d79b584d0: vzeroupper
0x0000023d79b584d3: add rsp,50h
0x0000023d79b584d7: pop rbp
0x0000023d79b584d8: test dword ptr [23d780d0000h],eax
; {poll_return}
0x0000023d79b584de: ret
0x0000023d79b584df: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x0000023d79b584e0: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.84% 0x0000023d79b584e7: vmulpd ymm0,ymm0,ymm2
1.97% 0x0000023d79b584eb: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
1.67% 0x0000023d79b584f2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.62% 0x0000023d79b584f9: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000023d79b584fd: cmp r8d,r9d
0.00% 0x0000023d79b58500: jl 23d79b584e0h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023d79b58502: cmp r8d,edx
0x0000023d79b58505: jnl 23d79b58529h
0.22% 0x0000023d79b58507: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000023d79b58508: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000023d79b5850f: vmulsd xmm0,xmm0,xmm1
0x0000023d79b58513: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.23% 0x0000023d79b5851a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000023d79b58521: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023d79b58524: cmp r8d,edx
0.00% 0x0000023d79b58527: jl 23d79b58508h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.22% 0x0000023d79b58529: mov r8,rbx
0x0000023d79b5852c: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x0000023d79b58530: mov rdx,qword ptr [rsp+30h]
0.02% 0x0000023d79b58535: nop
0.21% 0x0000023d79b58538: vzeroupper
0.21% 0x0000023d79b5853b: call 23d79adc480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.15% 0x0000023d79b58540: mov r10,qword ptr [rsp+60h]
0.09% 0x0000023d79b58545: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.03% 0x0000023d79b5854d: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.10% 0x0000023d79b58551: test dword ptr [23d780d0000h],eax
; {poll}
0.13% 0x0000023d79b58557: test r10d,r10d
0x0000023d79b5855a: jne 23d79b584afh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0.01% 0x0000023d79b58560: mov r10,qword ptr [rsp+70h]
0.00% 0x0000023d79b58565: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.10% 0x0000023d79b58569: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x0000023d79b586ed
0.81% 0x0000023d79b5856e: test edx,edx
0x0000023d79b58570: jbe 23d79b58529h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.34% 0x0000023d79b58572: mov r11d,edx
0x0000023d79b58575: dec r11d
0.01% 0x0000023d79b58578: cmp r11d,edx
0.01% 0x0000023d79b5857b: jnb 23d79b58692h
0.22% 0x0000023d79b58581: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.07% 0x0000023d79b58585: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x0000023d79b58692
0.01% 0x0000023d79b5858a: test r9d,r9d
0x0000023d79b5858d: jbe 23d79b58692h
0.01% 0x0000023d79b58593: cmp r11d,r9d
0x0000023d79b58596: jnb 23d79b58692h
0.16% 0x0000023d79b5859c: mov r11,qword ptr [rsp+70h]
0.05% 0x0000023d79b585a1: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x0000023d79b585a7: lea r11,[r12+rbx*8]
0.01% 0x0000023d79b585ab: shl r10,3h
0.14% 0x0000023d79b585af: mov r8d,r11d
0.06% 0x0000023d79b585b2: shr r8d,3h
0x0000023d79b585b6: and r8d,3h
0.00% 0x0000023d79b585ba: mov ecx,1h
0.15% 0x0000023d79b585bf: sub ecx,r8d
0.06% 0x0000023d79b585c2: and ecx,3h
0.00% 0x0000023d79b585c5: inc ecx
0.00% 0x0000023d79b585c7: cmp ecx,edx
0.11% 0x0000023d79b585c9: cmovnle ecx,edx
0.06% 0x0000023d79b585cc: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.12% 0x0000023d79b585cf: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.07% 0x0000023d79b585d6: vmulsd xmm0,xmm0,xmm1
0.21% 0x0000023d79b585da: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.64% 0x0000023d79b585e1: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.16% 0x0000023d79b585e8: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.16% 0x0000023d79b585eb: cmp r8d,ecx
0x0000023d79b585ee: jl 23d79b585cfh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.05% 0x0000023d79b585f0: mov ecx,edx
0.09% 0x0000023d79b585f2: add ecx,0fffffff1h
0.07% 0x0000023d79b585f5: cmp r8d,ecx
0x0000023d79b585f8: jnl 23d79b58502h
0.01% 0x0000023d79b585fe: vpshufd xmm2,xmm1,44h
0.07% 0x0000023d79b58603: vinsertf128 ymm2,ymm2,xmm2,1h
0.08% 0x0000023d79b58609: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
5.40% 0x0000023d79b58610: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.07% 0x0000023d79b58617: vmulpd ymm0,ymm0,ymm2
7.52% 0x0000023d79b5861b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
5.85% 0x0000023d79b58622: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
0.28% 0x0000023d79b58629: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
7.81% 0x0000023d79b58630: vmulpd ymm0,ymm0,ymm2
0.73% 0x0000023d79b58634: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
9.87% 0x0000023d79b5863b: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
10.73% 0x0000023d79b58642: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
0.07% 0x0000023d79b58649: vmulpd ymm0,ymm0,ymm2
2.48% 0x0000023d79b5864d: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
10.74% 0x0000023d79b58654: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
0.14% 0x0000023d79b5865b: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
2.86% 0x0000023d79b58662: vmulpd ymm0,ymm0,ymm2
0.64% 0x0000023d79b58666: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
14.22% 0x0000023d79b5866d: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
7.70% 0x0000023d79b58674: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x0000023d79b58678: cmp r8d,ecx
0.00% 0x0000023d79b5867b: jl 23d79b58610h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.04% 0x0000023d79b5867d: mov r9d,edx
0.03% 0x0000023d79b58680: add r9d,0fffffffdh
0.20% 0x0000023d79b58684: cmp r8d,r9d
0x0000023d79b58687: jl 23d79b584e0h
0x0000023d79b5868d: jmp 23d79b58502h
0x0000023d79b58692: mov edx,0ffffff86h
0x0000023d79b58697: nop
0x0000023d79b58698: vzeroupper
0x0000023d79b5869b: call 23d79adde80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
98.34% <total for region 1>
....[Hottest Regions]...............................................................................
98.34% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159 (420 bytes)
0.95% c2 org.openjdk.jmh.infra.Blackhole::consume, version 157 (72 bytes)
0.66% <unknown> (0 bytes)
0.01% runtime stub StubRoutines::atomic_cmpxchg_long (36 bytes)
0.00% KernelBase.dll WaitForSingleObjectEx (0 bytes)
0.00% jvm.dll 0x00000000707a4618 (3 bytes)
0.00% jvm.dll 0x00000000709a39ca (0 bytes)
0.00% jvm.dll 0x0000000070c517d5 (0 bytes)
0.00% jvm.dll 0x0000000070c7481f (10 bytes)
0.00% jvm.dll 0x0000000070cfb2b0 (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (8 bytes)
0.00% kernel32.dll QueryPerformanceCounterStub (0 bytes)
0.00% jvm.dll 0x00000000709ab586 (0 bytes)
0.00% jvm.dll 0x00000000709ac6e1 (0 bytes)
0.00% jvm.dll 0x00000000709c97eb (0 bytes)
0.00% jvm.dll 0x00000000709c9902 (0 bytes)
0.00% jvm.dll 0x0000000070a17831 (0 bytes)
0.00% jvm.dll 0x0000000070ab63b0 (0 bytes)
0.00% jvm.dll 0x0000000070c51d89 (0 bytes)
0.00% jvm.dll 0x0000000070c73790 (0 bytes)
0.01% <...other 8 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
98.34% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 159
0.95% c2 org.openjdk.jmh.infra.Blackhole::consume, version 157
0.66% <unknown>
0.01% runtime stub StubRoutines::atomic_cmpxchg_long
0.00% KernelBase.dll WaitForSingleObjectEx
0.00% jvm.dll 0x0000000070c517d5
0.00% interpreter method entry point (kind = zerolocals)
0.00% kernel32.dll QueryPerformanceCounterStub
0.00% jvm.dll 0x00000000709a39ca
0.00% jvm.dll 0x00000000707a4618
0.00% jvm.dll 0x0000000070cfb2b0
0.00% jvm.dll 0x0000000070c7481f
0.00% jvm.dll 0x0000000070c73790
0.00% jvm.dll 0x0000000070c51d89
0.00% jvm.dll 0x00000000709c9902
0.00% interpreter invokespecial 183 invokespecial
0.00% kernel32.dll WaitForSingleObject
0.00% jvm.dll 0x0000000070c74730
0.00% jvm.dll 0x00000000709c97eb
0.00% jvm.dll 0x00000000709ac6e1
0.01% <...other 8 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.30% c2
0.66%
0.02% jvm.dll
0.01% runtime stub
0.00% interpreter
0.00% KernelBase.dll
0.00% kernel32.dll
0.00% ntdll.dll
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 24, size = 1000)
# Run progress: 80.00% complete, ETA 00:06:21
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 6.661 ops/us
# Warmup Iteration 2: 6.888 ops/us
# Warmup Iteration 3: 6.588 ops/us
# Warmup Iteration 4: 6.234 ops/us
# Warmup Iteration 5: 6.679 ops/us
# Warmup Iteration 6: 6.425 ops/us
# Warmup Iteration 7: 6.272 ops/us
# Warmup Iteration 8: 6.484 ops/us
# Warmup Iteration 9: 6.424 ops/us
# Warmup Iteration 10: 6.526 ops/us
Iteration 1: 6.975 ops/us
Iteration 2: 6.940 ops/us
Iteration 3: 6.809 ops/us
Iteration 4: 6.457 ops/us
Iteration 5: 6.393 ops/us
Iteration 6: 6.414 ops/us
Iteration 7: 6.443 ops/us
Iteration 8: 6.766 ops/us
Iteration 9: 6.454 ops/us
Iteration 10: 6.725 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
6.638 ±(99.9%) 0.347 ops/us [Average]
(min, avg, max) = (6.393, 6.638, 6.975), stdev = 0.229
CI (99.9%): [6.291, 6.984] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48621 total address lines.
Perf output processed (skipped 14.365 seconds):
Column 1: SampledProfile (99045 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (423 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001ace759cc50: vzeroupper
0x000001ace759cc53: add rsp,50h
0x000001ace759cc57: pop rbp
0x000001ace759cc58: test dword ptr [1acdce00000h],eax
; {poll_return}
0x000001ace759cc5e: ret
0x000001ace759cc5f: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000001ace759cc60: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.54% 0x000001ace759cc67: vmulpd ymm0,ymm0,ymm2
1.30% 0x000001ace759cc6b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
0.91% 0x000001ace759cc72: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.26% 0x000001ace759cc79: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001ace759cc7d: cmp r8d,r9d
0.00% 0x000001ace759cc80: jl 1ace759cc60h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001ace759cc82: cmp r8d,edx
0x000001ace759cc85: jnl 1ace759cca9h
0.22% 0x000001ace759cc87: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.19% 0x000001ace759cc88: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.23% 0x000001ace759cc8f: vmulsd xmm0,xmm0,xmm1
0.04% 0x000001ace759cc93: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.53% 0x000001ace759cc9a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.28% 0x000001ace759cca1: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x000001ace759cca4: cmp r8d,edx
0x000001ace759cca7: jl 1ace759cc88h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001ace759cca9: mov r8,rbx
0x000001ace759ccac: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.22% 0x000001ace759ccb0: mov rdx,qword ptr [rsp+30h]
0.01% 0x000001ace759ccb5: nop
0.00% 0x000001ace759ccb8: vzeroupper
0.24% 0x000001ace759ccbb: call 1ace751c480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.28% 0x000001ace759ccc0: mov r10,qword ptr [rsp+60h]
0.08% 0x000001ace759ccc5: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.03% 0x000001ace759cccd: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.12% 0x000001ace759ccd1: test dword ptr [1acdce00000h],eax
; {poll}
0.00% 0x000001ace759ccd7: test r10d,r10d
0.00% 0x000001ace759ccda: jne 1ace759cc2fh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0.09% 0x000001ace759cce0: mov r10,qword ptr [rsp+70h]
0.04% 0x000001ace759cce5: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.12% 0x000001ace759cce9: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000001ace759ce6d
0.14% 0x000001ace759ccee: test edx,edx
0x000001ace759ccf0: jbe 1ace759cca9h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.22% 0x000001ace759ccf2: mov r11d,edx
0x000001ace759ccf5: dec r11d
0.01% 0x000001ace759ccf8: cmp r11d,edx
0x000001ace759ccfb: jnb 1ace759ce12h
0.40% 0x000001ace759cd01: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.02% 0x000001ace759cd05: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x000001ace759ce12
0.01% 0x000001ace759cd0a: test r9d,r9d
0x000001ace759cd0d: jbe 1ace759ce12h
0.05% 0x000001ace759cd13: cmp r11d,r9d
0x000001ace759cd16: jnb 1ace759ce12h
0.15% 0x000001ace759cd1c: mov r11,qword ptr [rsp+70h]
0.01% 0x000001ace759cd21: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001ace759cd27: lea r11,[r12+rbx*8]
0.06% 0x000001ace759cd2b: shl r10,3h
0.14% 0x000001ace759cd2f: mov r8d,r11d
0.01% 0x000001ace759cd32: shr r8d,3h
0x000001ace759cd36: and r8d,3h
0.04% 0x000001ace759cd3a: mov ecx,1h
0.17% 0x000001ace759cd3f: sub ecx,r8d
0.01% 0x000001ace759cd42: and ecx,3h
0x000001ace759cd45: inc ecx
0.04% 0x000001ace759cd47: cmp ecx,edx
0.15% 0x000001ace759cd49: cmovnle ecx,edx
0.01% 0x000001ace759cd4c: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x000001ace759cd4f: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.04% 0x000001ace759cd56: vmulsd xmm0,xmm0,xmm1
0.18% 0x000001ace759cd5a: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.84% 0x000001ace759cd61: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.21% 0x000001ace759cd68: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001ace759cd6b: cmp r8d,ecx
0x000001ace759cd6e: jl 1ace759cd4fh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x000001ace759cd70: mov ecx,edx
0x000001ace759cd72: add ecx,0fffffff1h
0.24% 0x000001ace759cd75: cmp r8d,ecx
0x000001ace759cd78: jnl 1ace759cc82h
0x000001ace759cd7e: vpshufd xmm2,xmm1,44h
0.00% 0x000001ace759cd83: vinsertf128 ymm2,ymm2,xmm2,1h
0x000001ace759cd89: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
7.61% 0x000001ace759cd90: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
0.07% 0x000001ace759cd97: vmulpd ymm0,ymm0,ymm2
6.84% 0x000001ace759cd9b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
7.52% 0x000001ace759cda2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
0.12% 0x000001ace759cda9: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
7.16% 0x000001ace759cdb0: vmulpd ymm0,ymm0,ymm2
0.12% 0x000001ace759cdb4: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
9.28% 0x000001ace759cdbb: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
13.30% 0x000001ace759cdc2: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
0.03% 0x000001ace759cdc9: vmulpd ymm0,ymm0,ymm2
0.89% 0x000001ace759cdcd: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
13.55% 0x000001ace759cdd4: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
0.16% 0x000001ace759cddb: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
1.07% 0x000001ace759cde2: vmulpd ymm0,ymm0,ymm2
0.18% 0x000001ace759cde6: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
14.21% 0x000001ace759cded: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
6.95% 0x000001ace759cdf4: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.03% 0x000001ace759cdf8: cmp r8d,ecx
0.01% 0x000001ace759cdfb: jl 1ace759cd90h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.08% 0x000001ace759cdfd: mov r9d,edx
0.01% 0x000001ace759ce00: add r9d,0fffffffdh
0.14% 0x000001ace759ce04: cmp r8d,r9d
0.00% 0x000001ace759ce07: jl 1ace759cc60h
0x000001ace759ce0d: jmp 1ace759cc82h
0x000001ace759ce12: mov edx,0ffffff86h
0x000001ace759ce17: nop
0x000001ace759ce18: vzeroupper
0x000001ace759ce1b: call 1ace751de80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
0x000001ace759ce20: int3 ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
....................................................................................................
98.25% <total for region 1>
....[Hottest Regions]...............................................................................
98.25% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (423 bytes)
1.33% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159 (72 bytes)
0.40% <unknown> (0 bytes)
0.01% runtime stub StubRoutines::atomic_cmpxchg_long (8 bytes)
0.00% jvm.dll 0x0000000070c51d89 (0 bytes)
0.00% jvm.dll 0x0000000070d5a7ce (2 bytes)
0.00% KernelBase.dll WaitForSingleObjectEx (0 bytes)
0.00% ntdll.dll ZwWaitForSingleObject (20 bytes)
0.00% jvm.dll 0x00000000707d874f (0 bytes)
0.00% jvm.dll 0x00000000709c9966 (0 bytes)
0.00% jvm.dll 0x0000000070c520b0 (0 bytes)
0.00% jvm.dll 0x0000000070c9e640 (0 bytes)
0.00% jvm.dll 0x0000000070d3837d (0 bytes)
0.00% jvm.dll 0x0000000070d5b068 (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% interpreter method entry point (kind = zerolocals) (0 bytes)
0.00% interpreter invokespecial 183 invokespecial (0 bytes)
0.00% interpreter fast_lgetfield 209 fast_lgetfield (0 bytes)
0.00% interpreter invokehandle 233 invokehandle (0 bytes)
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
98.25% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161
1.33% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159
0.40% <unknown>
0.01% runtime stub StubRoutines::atomic_cmpxchg_long
0.00% jvm.dll 0x0000000070d5a7ce
0.00% jvm.dll 0x0000000070c51d89
0.00% ntdll.dll ZwWaitForSingleObject
0.00% interpreter method entry point (kind = zerolocals)
0.00% KernelBase.dll WaitForSingleObjectEx
0.00% jvm.dll 0x00000000709c9966
0.00% jvm.dll 0x0000000070d3837d
0.00% jvm.dll 0x0000000070c9e640
0.00% jvm.dll 0x0000000070d5b068
0.00% interpreter invokespecial 183 invokespecial
0.00% jvm.dll 0x0000000070c520b0
0.00% interpreter fast_lgetfield 209 fast_lgetfield
0.00% jvm.dll 0x00000000707d874f
0.00% interpreter invokehandle 233 invokehandle
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.57% c2
0.40%
0.01% jvm.dll
0.01% runtime stub
0.01% interpreter
0.00% KernelBase.dll
0.00% ntdll.dll
....................................................................................................
100.00% <totals>
# JMH version: 1.19
# VM version: JDK 9.0.1, VM 9.0.1+11
# VM invoker: C:\Program Files\Java\jdk-9.0.1\bin\java.exe
# VM options: -server -XX:-TieredCompilation -javaagent:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\lib\idea_rt.jar=58772:C:\Program Files\JetBrains\IntelliJ IDEA 2017.2.5\bin -Dfile.encoding=UTF-8
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Throughput, ops/time
# Benchmark: com.openkappa.simd.saxpy.DAXPYAlignment.daxpy
# Parameters: (offset = 24, size = 1024)
# Run progress: 90.00% complete, ETA 00:03:09
# Fork: 1 of 1
# Preparing profilers: WinPerfAsmProfiler
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console
# Warmup Iteration 1: 6.687 ops/us
# Warmup Iteration 2: 6.754 ops/us
# Warmup Iteration 3: 6.905 ops/us
# Warmup Iteration 4: 6.855 ops/us
# Warmup Iteration 5: 6.970 ops/us
# Warmup Iteration 6: 6.798 ops/us
# Warmup Iteration 7: 6.756 ops/us
# Warmup Iteration 8: 6.789 ops/us
# Warmup Iteration 9: 6.889 ops/us
# Warmup Iteration 10: 6.845 ops/us
Iteration 1: 6.995 ops/us
Iteration 2: 6.746 ops/us
Iteration 3: 6.864 ops/us
Iteration 4: 6.807 ops/us
Iteration 5: 6.825 ops/us
Iteration 6: 6.717 ops/us
Iteration 7: 6.542 ops/us
Iteration 8: 6.688 ops/us
Iteration 9: 6.947 ops/us
Iteration 10: 6.942 ops/us
# Processing profiler results: WinPerfAsmProfiler
Result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy":
6.807 ±(99.9%) 0.209 ops/us [Average]
(min, avg, max) = (6.542, 6.807, 6.995), stdev = 0.138
CI (99.9%): [6.598, 7.017] (assumes normal distribution)
Secondary result "com.openkappa.simd.saxpy.DAXPYAlignment.daxpy:·asm":
PrintAssembly processed: 48628 total address lines.
Perf output processed (skipped 14.321 seconds):
Column 1: SampledProfile (99408 events)
Hottest code regions (>10.00% "SampledProfile" events):
....[Hottest Region 1]..............................................................................
c2, com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (420 bytes)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000129a91cb450: vzeroupper
0x00000129a91cb453: add rsp,50h
0x00000129a91cb457: pop rbp
0x00000129a91cb458: test dword ptr [1299d300000h],eax
; {poll_return}
0x00000129a91cb45e: ret
0x00000129a91cb45f: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.15% 0x00000129a91cb460: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
1.01% 0x00000129a91cb467: vmulpd ymm0,ymm0,ymm2
1.31% 0x00000129a91cb46b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
1.48% 0x00000129a91cb472: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.65% 0x00000129a91cb479: add r8d,4h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000129a91cb47d: cmp r8d,r9d
0x00000129a91cb480: jl 129a91cb460h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000129a91cb482: cmp r8d,edx
0x00000129a91cb485: jnl 129a91cb4a9h
0.22% 0x00000129a91cb487: nop ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.21% 0x00000129a91cb488: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.23% 0x00000129a91cb48f: vmulsd xmm0,xmm0,xmm1
0.00% 0x00000129a91cb493: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.46% 0x00000129a91cb49a: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.24% 0x00000129a91cb4a1: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000129a91cb4a4: cmp r8d,edx
0x00000129a91cb4a7: jl 129a91cb488h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000129a91cb4a9: mov r8,rbx
0x00000129a91cb4ac: shl r8,3h ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.25% 0x00000129a91cb4b0: mov rdx,qword ptr [rsp+30h]
0.00% 0x00000129a91cb4b5: nop
0x00000129a91cb4b8: vzeroupper
0.22% 0x00000129a91cb4bb: call 129a914c480h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@42 (line 39)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {optimized virtual_call}
0.15% 0x00000129a91cb4c0: mov r10,qword ptr [rsp+60h]
0.06% 0x00000129a91cb4c5: movzx r10d,byte ptr [r10+94h] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@27 (line 121)
0.09% 0x00000129a91cb4cd: add rbp,1h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*ifeq {reexecute=1 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@30 (line 121)
0.06% 0x00000129a91cb4d1: test dword ptr [1299d300000h],eax
; {poll}
0.00% 0x00000129a91cb4d7: test r10d,r10d
0x00000129a91cb4da: jne 129a91cb42fh ;*aload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@13 (line 119)
0.06% 0x00000129a91cb4e0: mov r10,qword ptr [rsp+70h]
0.10% 0x00000129a91cb4e5: mov ebx,dword ptr [r10+1ch] ;*getfield a {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@4 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.10% 0x00000129a91cb4e9: mov edx,dword ptr [r12+rbx*8+0ch]
;*arraylength {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@7 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x00000129a91cb66d
1.09% 0x00000129a91cb4ee: test edx,edx
0x00000129a91cb4f0: jbe 129a91cb4a9h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.24% 0x00000129a91cb4f2: mov r11d,edx
0x00000129a91cb4f5: dec r11d
0.00% 0x00000129a91cb4f8: cmp r11d,edx
0x00000129a91cb4fb: jnb 129a91cb612h
0.24% 0x00000129a91cb501: mov r10d,dword ptr [r10+20h]
;*getfield b {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@23 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000129a91cb505: mov r9d,dword ptr [r12+r10*8+0ch]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; implicit exception: dispatches to 0x00000129a91cb612
0.00% 0x00000129a91cb50a: test r9d,r9d
0x00000129a91cb50d: jbe 129a91cb612h
0.00% 0x00000129a91cb513: cmp r11d,r9d
0x00000129a91cb516: jnb 129a91cb612h
0.24% 0x00000129a91cb51c: mov r11,qword ptr [rsp+70h]
0x00000129a91cb521: vmovsd xmm1,qword ptr [r11+10h]
;*getfield s {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@19 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000129a91cb527: lea r11,[r12+rbx*8]
0.00% 0x00000129a91cb52b: shl r10,3h
0.24% 0x00000129a91cb52f: mov r8d,r11d
0x00000129a91cb532: shr r8d,3h
0x00000129a91cb536: and r8d,3h
0x00000129a91cb53a: mov ecx,1h
0.23% 0x00000129a91cb53f: sub ecx,r8d
0.00% 0x00000129a91cb542: and ecx,3h
0x00000129a91cb545: inc ecx
0x00000129a91cb547: cmp ecx,edx
0.24% 0x00000129a91cb549: cmovnle ecx,edx
0x00000129a91cb54c: xor r8d,r8d ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0x00000129a91cb54f: vmovsd xmm0,qword ptr [r10+r8*8+10h]
;*daload {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@27 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000129a91cb556: vmulsd xmm0,xmm0,xmm1
0.22% 0x00000129a91cb55a: vaddsd xmm0,xmm0,mmword ptr [r11+r8*8+10h]
0.08% 0x00000129a91cb561: vmovsd qword ptr [r11+r8*8+10h],xmm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.07% 0x00000129a91cb568: inc r8d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.18% 0x00000129a91cb56b: cmp r8d,ecx
0x00000129a91cb56e: jl 129a91cb54fh ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.00% 0x00000129a91cb570: mov ecx,edx
0.00% 0x00000129a91cb572: add ecx,0fffffff1h
0.06% 0x00000129a91cb575: cmp r8d,ecx
0x00000129a91cb578: jnl 129a91cb482h
0.17% 0x00000129a91cb57e: vpshufd xmm2,xmm1,44h
0x00000129a91cb583: vinsertf128 ymm2,ymm2,xmm2,1h
0x00000129a91cb589: nop dword ptr [rax+0h] ;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.18% 0x00000129a91cb590: vmovdqu ymm0,ymmword ptr [r10+r8*8+10h]
9.60% 0x00000129a91cb597: vmulpd ymm0,ymm0,ymm2
0.18% 0x00000129a91cb59b: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+10h]
6.61% 0x00000129a91cb5a2: vmovdqu ymmword ptr [r11+r8*8+10h],ymm0
10.20% 0x00000129a91cb5a9: vmovdqu ymm0,ymmword ptr [r10+r8*8+30h]
0.03% 0x00000129a91cb5b0: vmulpd ymm0,ymm0,ymm2
4.16% 0x00000129a91cb5b4: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+30h]
10.23% 0x00000129a91cb5bb: vmovdqu ymmword ptr [r11+r8*8+30h],ymm0
0.08% 0x00000129a91cb5c2: vmovdqu ymm0,ymmword ptr [r10+r8*8+50h]
4.12% 0x00000129a91cb5c9: vmulpd ymm0,ymm0,ymm2
0.10% 0x00000129a91cb5cd: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+50h]
13.81% 0x00000129a91cb5d4: vmovdqu ymmword ptr [r11+r8*8+50h],ymm0
9.31% 0x00000129a91cb5db: vmovdqu ymm0,ymmword ptr [r10+r8*8+70h]
0.03% 0x00000129a91cb5e2: vmulpd ymm0,ymm0,ymm2
4.89% 0x00000129a91cb5e6: vaddpd ymm0,ymm0,ymmword ptr [r11+r8*8+70h]
9.49% 0x00000129a91cb5ed: vmovdqu ymmword ptr [r11+r8*8+70h],ymm0
;*dastore {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@30 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.05% 0x00000129a91cb5f4: add r8d,10h ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@31 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
4.91% 0x00000129a91cb5f8: cmp r8d,ecx
0x00000129a91cb5fb: jl 129a91cb590h ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@8 (line 36)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
0.01% 0x00000129a91cb5fd: mov r9d,edx
0.06% 0x00000129a91cb600: add r9d,0fffffffdh
0.01% 0x00000129a91cb604: cmp r8d,r9d
0x00000129a91cb607: jl 129a91cb460h
0x00000129a91cb60d: jmp 129a91cb482h
0x00000129a91cb612: mov edx,0ffffff86h
0x00000129a91cb617: nop
0x00000129a91cb618: vzeroupper
0x00000129a91cb61b: call 129a914de80h ; ImmutableOopMap{[96]=Oop [104]=Oop [112]=Oop [48]=Oop }
;*aload_0 {reexecute=0 rethrow=0 return_oop=0}
; - com.openkappa.simd.saxpy.DAXPYAlignment::daxpy@11 (line 37)
; - com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub@17 (line 119)
; {runtime_call UncommonTrapBlob}
....................................................................................................
98.45% <total for region 1>
....[Hottest Regions]...............................................................................
98.45% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161 (420 bytes)
1.29% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159 (72 bytes)
0.23% <unknown> (0 bytes)
0.00% jvm.dll 0x00000000709aa950 (0 bytes)
0.00% jvm.dll 0x0000000070c9e640 (0 bytes)
0.00% jvm.dll 0x0000000070d5b068 (0 bytes)
0.00% runtime stub StubRoutines::orderaccess_fence (0 bytes)
0.00% KernelBase.dll WaitForSingleObjectEx (0 bytes)
0.00% jvm.dll 0x0000000070992295 (0 bytes)
0.00% jvm.dll 0x0000000070994f78 (0 bytes)
0.00% jvm.dll 0x00000000709ab570 (0 bytes)
0.00% jvm.dll 0x00000000709ff9d0 (0 bytes)
0.00% jvm.dll 0x0000000070c517d5 (0 bytes)
0.00% jvm.dll 0x0000000070c51d79 (0 bytes)
0.00% jvm.dll 0x0000000070c71690 (0 bytes)
0.00% jvm.dll 0x0000000070c7481f (0 bytes)
0.00% jvm.dll 0x0000000070cfb2b0 (0 bytes)
0.00% jvm.dll 0x0000000070cfb2d9 (0 bytes)
0.00% jvm.dll 0x0000000070d5a7b7 (0 bytes)
0.00% runtime stub StubRoutines::atomic_cmpxchg_long (0 bytes)
0.01% <...other 9 warm regions...>
....................................................................................................
100.00% <totals>
....[Hottest Methods (after inlining)]..............................................................
98.45% c2 com.openkappa.simd.saxpy.generated.DAXPYAlignment_daxpy_jmhTest::daxpy_thrpt_jmhStub, version 161
1.29% c2 org.openjdk.jmh.infra.Blackhole::consume, version 159
0.23% <unknown>
0.00% KernelBase.dll WaitForSingleObjectEx
0.00% jvm.dll 0x0000000070d5b068
0.00% runtime stub StubRoutines::orderaccess_fence
0.00% interpreter method entry point (kind = zerolocals)
0.00% jvm.dll 0x0000000070c9e640
0.00% jvm.dll 0x00000000709aa950
0.00% jvm.dll 0x0000000070992295
0.00% jvm.dll 0x0000000070cfb2d9
0.00% interpreter method entry point (kind = native)
0.00% KernelBase.dll WaitForSingleObject
0.00% jvm.dll 0x0000000070c71690
0.00% jvm.dll 0x0000000070994f78
0.00% jvm.dll 0x0000000070c517d5
0.00% jvm.dll 0x0000000070c51d79
0.00% jvm.dll 0x00000000709ab570
0.00% kernel32.dll QueryPerformanceCounterStub
0.00% interpreter aload_1 43 aload_1
0.01% <...other 7 warm methods...>
....................................................................................................
100.00% <totals>
....[Distribution by Source]........................................................................
99.74% c2
0.23%
0.02% jvm.dll
0.01% interpreter
0.00% KernelBase.dll
0.00% runtime stub
0.00% ntdll.dll
0.00% kernel32.dll
....................................................................................................
100.00% <totals>
# Run complete. Total time: 00:31:20
Benchmark (offset) (size) Mode Cnt Score Error Units
DAXPYAlignment.daxpy 0 1000 thrpt 10 2.662 ± 0.033 ops/us
DAXPYAlignment.daxpy:·asm 0 1000 thrpt NaN ---
DAXPYAlignment.daxpy 0 1024 thrpt 10 6.891 ± 0.403 ops/us
DAXPYAlignment.daxpy:·asm 0 1024 thrpt NaN ---
DAXPYAlignment.daxpy 6 1000 thrpt 10 2.563 ± 0.104 ops/us
DAXPYAlignment.daxpy:·asm 6 1000 thrpt NaN ---
DAXPYAlignment.daxpy 6 1024 thrpt 10 6.974 ± 0.167 ops/us
DAXPYAlignment.daxpy:·asm 6 1024 thrpt NaN ---
DAXPYAlignment.daxpy 12 1000 thrpt 10 3.841 ± 0.113 ops/us
DAXPYAlignment.daxpy:·asm 12 1000 thrpt NaN ---
DAXPYAlignment.daxpy 12 1024 thrpt 10 6.556 ± 0.472 ops/us
DAXPYAlignment.daxpy:·asm 12 1024 thrpt NaN ---
DAXPYAlignment.daxpy 18 1000 thrpt 10 6.864 ± 0.220 ops/us
DAXPYAlignment.daxpy:·asm 18 1000 thrpt NaN ---
DAXPYAlignment.daxpy 18 1024 thrpt 10 5.987 ± 0.749 ops/us
DAXPYAlignment.daxpy:·asm 18 1024 thrpt NaN ---
DAXPYAlignment.daxpy 24 1000 thrpt 10 6.638 ± 0.347 ops/us
DAXPYAlignment.daxpy:·asm 24 1000 thrpt NaN ---
DAXPYAlignment.daxpy 24 1024 thrpt 10 6.807 ± 0.209 ops/us
DAXPYAlignment.daxpy:·asm 24 1024 thrpt NaN ---
Benchmark result is saved to jmh-result.csv
Process finished with exit code 0
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment