base_asm_626b20d4.asm

base_asm_626b20d4.asm

Samples: 301K of event 'cpu-clock', 49999 Hz, Event count (approx.): 6033560000, [percent: local period]
JIT_NewArr1VC_MP_FastPortable(CORINFO_CLASS_STRUCT_*, long)() /home/egorbot/506e473b-af96-4105-b537-a93181aff483/libcoreclr.so
Percent        
               
               
            Disassembly of section .text:
               
            00000000003552d0 <GetCLRRuntimeHost@@V1.0+0x13c660>:
  5.57        push   rbp    
  0.76        mov    rbp,rsp
  3.53        push   r15    
  0.34        push   r14    
  0.00        push   r12    
  0.20        push   rbx    
  0.25        mov    r12,rsi
  5.29        mov    r14,rdi
              cmp    rsi,0xfeff
            ↓ jae    60     
  0.05        cmp    QWORD PTR [rip+0x38175e],0x0
  5.14      ↓ je     29     
            → call   TLS init function for t_runtime_thread_locals@plt
  1.26  29:   movzx  eax,WORD PTR [r14]
  0.04        imul   rax,r12
  0.02        mov    ecx,DWORD PTR [r14+0x4]
  3.55        lea    rbx,[rcx+rax*1]
  0.05        add    rbx,0x7
  0.03        and    rbx,0xfffffffffffffff8
  0.03        data16 lea rdi,[rip+0x38173f]        # 6d6a58 <msync@plt+0x277c8>
  4.06        data16 data16 rex.W call 6ae100 <__tls_get_addr@plt>
  1.86        mov    r15,QWORD PTR [rax]
 23.49        mov    rax,QWORD PTR [rax+0x8]
  0.19        sub    rax,r15
  4.78        cmp    rbx,rax
            ↓ jbe    73     
  0.30  60:   mov    rdi,r14
  0.02        mov    rsi,r12
              pop    rbx    
  0.23        pop    r12    
              pop    r14    
  0.02        pop    r15    
  0.00        pop    rbp    
  0.03      → jmp    JIT_NewArr1(CORINFO_CLASS_STRUCT_*, long)
  5.15  73:   add    rbx,r15
  0.18        data16 lea rdi,[rip+0x38170a]        # 6d6a58 <msync@plt+0x277c8>
  0.01        data16 data16 rex.W call 6ae100 <__tls_get_addr@plt>
  3.43        mov    QWORD PTR [rax],rbx
 12.75        mov    QWORD PTR [r15],r14
  0.03        mov    DWORD PTR [r15+0x8],r12d
  0.22        mov    rax,r15
  1.59        pop    rbx    
  7.88        pop    r12    
  0.69        pop    r14    
  3.71        pop    r15    
  0.08        pop    rbp    
  3.19      ← ret           
Samples: 301K of event 'cpu-clock', 49999 Hz, Event count (approx.): 6033560000, [percent: local period]
__tls_get_addr() /usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2
Percent        
               
               
            Disassembly of section .text:
               
            00000000000181d0 <__tls_get_addr@@GLIBC_2.3>:
  0.62        endbr64       
              mov     rdx,QWORD PTR fs:0x8
  1.73        mov     rax,QWORD PTR [rip+0x22ed4]
  0.15        cmp     QWORD PTR [rdx],rax
            ↓ jne     2f    
  1.82        mov     rax,QWORD PTR [rdi]
  1.84        shl     rax,0x4
 47.28        mov     rax,QWORD PTR [rdx+rax*1]
 20.25        cmp     rax,0xffffffffffffffff
            ↓ je      2f    
 22.42        add     rax,QWORD PTR [rdi+0x8]
  3.89      ← ret           
        2f:   push    rbp   
              mov     rbp,rsp
              and     rsp,0xfffffffffffffff0
            → call    _dl_deallocate_tls@@GLIBC_PRIVATE+0x5e0
              mov     rsp,rbp
              pop     rbp   
            ← ret           
Samples: 301K of event 'cpu-clock', 49999 Hz, Event count (approx.): 6033560000, [percent: local period]
__tls_get_addr@plt() /home/egorbot/506e473b-af96-4105-b537-a93181aff483/libcoreclr.so
Percent        
               
               
            Disassembly of section .plt:
               
            00000000006ae100 <__tls_get_addr@plt>:
100.00      → jmp  QWORD PTR [rip+0x28b2a]        # 6d6c30 <msync@plt+0x279a0>
              push 0x11     
            → jmp  6adfe0 <GetCLRRuntimeHost@@V1.0+0x495370>
Samples: 301K of event 'cpu-clock', 49999 Hz, Event count (approx.): 6033560000, [percent: local period]
void [benchapp] Bench::Work(int32)[OptimizedTier1]() /tmp/jitted-50142-2339.so
Percent        
               
               
            Disassembly of section .text:
               
            0000000000000080 <void [benchapp] Bench::Work(int32)[OptimizedTier1]>:
            void [benchapp] Bench::Work(int32)[OptimizedTier1]():
 68.38        push   rbp    
  0.46        mov    rbp,rsp
              cmp    edi,0x400
            ↓ jge    21     
  0.41        movsxd rsi,edi
  1.63        movabs rdi,0x72e5a2c981b8
  0.28      → call   void [benchapp] Bench::Work(int32)[OptimizedTier1]+0x7e30cd70
  1.31  1e:   nop           
 10.79        pop    rbp    
 16.73      ← ret           
        21:   mov    esi,edi
              movabs rdi,0x72e5a2c981b8
              mov    edx,0x10
            → call   void [benchapp] Bench::Work(int32)[OptimizedTier1]+0x7e2d0870
            ↑ jmp    1e