Last active
December 27, 2015 06:39
-
-
Save mtklein/7283313 to your computer and use it in GitHub Desktop.
memset 32 with loop vs. store_first --- store_first seems to be much slower
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
00096d14 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j>: | |
96d14: e92d 0ff0 stmdb sp!, {r4, r5, r6, r7, r8, r9, sl, fp} | |
96d18: 2a03 cmp r2, #3 | |
96d1a: b08c sub sp, #48 ; 0x30 | |
96d1c: 4607 mov r7, r0 | |
96d1e: 9103 str r1, [sp, #12] | |
96d20: 9201 str r2, [sp, #4] | |
96d22: f240 80c6 bls.w 96eb2 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x19e> | |
96d26: 0702 lsls r2, r0, #28 | |
96d28: 4603 mov r3, r0 | |
96d2a: bf18 it ne | |
96d2c: 9a01 ldrne r2, [sp, #4] | |
96d2e: d007 beq.n 96d40 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x2c> | |
96d30: f843 1b04 str.w r1, [r3], #4 | |
96d34: 0718 lsls r0, r3, #28 | |
96d36: f102 32ff add.w r2, r2, #4294967295 ; 0xffffffff | |
96d3a: 461f mov r7, r3 | |
96d3c: d1f8 bne.n 96d30 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1c> | |
96d3e: 9201 str r2, [sp, #4] | |
96d40: 9a01 ldr r2, [sp, #4] | |
96d42: ab03 add r3, sp, #12 | |
96d44: 2a3f cmp r2, #63 ; 0x3f | |
96d46: f9e3 0caf vld1.32 {d16[]-d17[]}, [r3] | |
96d4a: edcd 0b04 vstr d16, [sp, #16] | |
96d4e: edcd 1b06 vstr d17, [sp, #24] | |
96d52: f240 80b8 bls.w 96ec6 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1b2> | |
96d56: ad08 add r5, sp, #32 | |
96d58: ac04 add r4, sp, #16 | |
96d5a: 463e mov r6, r7 | |
96d5c: 4694 mov ip, r2 | |
96d5e: 9702 str r7, [sp, #8] | |
96d60: e894 000f ldmia.w r4, {r0, r1, r2, r3} | |
96d64: f106 0b20 add.w fp, r6, #32 | |
96d68: f106 0a30 add.w sl, r6, #48 ; 0x30 | |
96d6c: f106 0940 add.w r9, r6, #64 ; 0x40 | |
96d70: f106 0850 add.w r8, r6, #80 ; 0x50 | |
96d74: 4637 mov r7, r6 | |
96d76: f1ac 0c40 sub.w ip, ip, #64 ; 0x40 | |
96d7a: e885 000f stmia.w r5, {r0, r1, r2, r3} | |
96d7e: eddd 0b08 vldr d16, [sp, #32] | |
96d82: eddd 1b0a vldr d17, [sp, #40] ; 0x28 | |
96d86: f1bc 0f3f cmp.w ip, #63 ; 0x3f | |
96d8a: f947 0add vst1.64 {d16-d17}, [r7 :64]! | |
96d8e: f947 0adf vst1.64 {d16-d17}, [r7 :64] | |
96d92: f106 0760 add.w r7, r6, #96 ; 0x60 | |
96d96: f94b 0adf vst1.64 {d16-d17}, [fp :64] | |
96d9a: f106 0b70 add.w fp, r6, #112 ; 0x70 | |
96d9e: f94a 0adf vst1.64 {d16-d17}, [sl :64] | |
96da2: f106 0a80 add.w sl, r6, #128 ; 0x80 | |
96da6: f949 0adf vst1.64 {d16-d17}, [r9 :64] | |
96daa: f106 0990 add.w r9, r6, #144 ; 0x90 | |
96dae: f948 0adf vst1.64 {d16-d17}, [r8 :64] | |
96db2: f106 08a0 add.w r8, r6, #160 ; 0xa0 | |
96db6: f947 0adf vst1.64 {d16-d17}, [r7 :64] | |
96dba: f106 07b0 add.w r7, r6, #176 ; 0xb0 | |
96dbe: f94b 0adf vst1.64 {d16-d17}, [fp :64] | |
96dc2: f106 0bc0 add.w fp, r6, #192 ; 0xc0 | |
96dc6: f94a 0adf vst1.64 {d16-d17}, [sl :64] | |
96dca: f106 0ad0 add.w sl, r6, #208 ; 0xd0 | |
96dce: f949 0adf vst1.64 {d16-d17}, [r9 :64] | |
96dd2: f106 09e0 add.w r9, r6, #224 ; 0xe0 | |
96dd6: f948 0adf vst1.64 {d16-d17}, [r8 :64] | |
96dda: f106 08f0 add.w r8, r6, #240 ; 0xf0 | |
96dde: f506 7680 add.w r6, r6, #256 ; 0x100 | |
96de2: f947 0adf vst1.64 {d16-d17}, [r7 :64] | |
96de6: f94b 0adf vst1.64 {d16-d17}, [fp :64] | |
96dea: f94a 0adf vst1.64 {d16-d17}, [sl :64] | |
96dee: f949 0adf vst1.64 {d16-d17}, [r9 :64] | |
96df2: f948 0adf vst1.64 {d16-d17}, [r8 :64] | |
96df6: d8b3 bhi.n 96d60 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x4c> | |
96df8: 9a01 ldr r2, [sp, #4] | |
96dfa: 9f02 ldr r7, [sp, #8] | |
96dfc: f1a2 0340 sub.w r3, r2, #64 ; 0x40 | |
96e00: f002 0a3f and.w sl, r2, #63 ; 0x3f | |
96e04: 099b lsrs r3, r3, #6 | |
96e06: 3301 adds r3, #1 | |
96e08: eb07 2703 add.w r7, r7, r3, lsl #8 | |
96e0c: f1ba 0f0f cmp.w sl, #15 | |
96e10: d927 bls.n 96e62 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x14e> | |
96e12: ad08 add r5, sp, #32 | |
96e14: ac04 add r4, sp, #16 | |
96e16: 463e mov r6, r7 | |
96e18: 46d0 mov r8, sl | |
96e1a: e894 000f ldmia.w r4, {r0, r1, r2, r3} | |
96e1e: f1a8 0810 sub.w r8, r8, #16 | |
96e22: f106 0b20 add.w fp, r6, #32 | |
96e26: f106 0930 add.w r9, r6, #48 ; 0x30 | |
96e2a: f1b8 0f0f cmp.w r8, #15 | |
96e2e: 46b4 mov ip, r6 | |
96e30: f106 0640 add.w r6, r6, #64 ; 0x40 | |
96e34: e885 000f stmia.w r5, {r0, r1, r2, r3} | |
96e38: eddd 0b08 vldr d16, [sp, #32] | |
96e3c: eddd 1b0a vldr d17, [sp, #40] ; 0x28 | |
96e40: f94c 0add vst1.64 {d16-d17}, [ip :64]! | |
96e44: f94c 0adf vst1.64 {d16-d17}, [ip :64] | |
96e48: f94b 0adf vst1.64 {d16-d17}, [fp :64] | |
96e4c: f949 0adf vst1.64 {d16-d17}, [r9 :64] | |
96e50: d8e3 bhi.n 96e1a <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x106> | |
96e52: f1aa 0310 sub.w r3, sl, #16 | |
96e56: f00a 0a0f and.w sl, sl, #15 | |
96e5a: 091b lsrs r3, r3, #4 | |
96e5c: 3301 adds r3, #1 | |
96e5e: eb07 1783 add.w r7, r7, r3, lsl #6 | |
96e62: f1ba 0f03 cmp.w sl, #3 | |
96e66: d931 bls.n 96ecc <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1b8> | |
96e68: ad08 add r5, sp, #32 | |
96e6a: ac04 add r4, sp, #16 | |
96e6c: 46bc mov ip, r7 | |
96e6e: 4656 mov r6, sl | |
96e70: e894 000f ldmia.w r4, {r0, r1, r2, r3} | |
96e74: 3e04 subs r6, #4 | |
96e76: 2e03 cmp r6, #3 | |
96e78: e885 000f stmia.w r5, {r0, r1, r2, r3} | |
96e7c: eddd 0b08 vldr d16, [sp, #32] | |
96e80: eddd 1b0a vldr d17, [sp, #40] ; 0x28 | |
96e84: f94c 0adf vst1.64 {d16-d17}, [ip :64] | |
96e88: f10c 0c10 add.w ip, ip, #16 | |
96e8c: d8f0 bhi.n 96e70 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x15c> | |
96e8e: f1aa 0204 sub.w r2, sl, #4 | |
96e92: f00a 0303 and.w r3, sl, #3 | |
96e96: 0892 lsrs r2, r2, #2 | |
96e98: 3201 adds r2, #1 | |
96e9a: eb07 1702 add.w r7, r7, r2, lsl #4 | |
96e9e: b123 cbz r3, 96eaa <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x196> | |
96ea0: 9a03 ldr r2, [sp, #12] | |
96ea2: 3b01 subs r3, #1 | |
96ea4: f847 2b04 str.w r2, [r7], #4 | |
96ea8: d1fb bne.n 96ea2 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x18e> | |
96eaa: b00c add sp, #48 ; 0x30 | |
96eac: e8bd 0ff0 ldmia.w sp!, {r4, r5, r6, r7, r8, r9, sl, fp} | |
96eb0: 4770 bx lr | |
96eb2: 9a01 ldr r2, [sp, #4] | |
96eb4: 2a00 cmp r2, #0 | |
96eb6: d0f8 beq.n 96eaa <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x196> | |
96eb8: eb00 0382 add.w r3, r0, r2, lsl #2 | |
96ebc: f847 1b04 str.w r1, [r7], #4 | |
96ec0: 429f cmp r7, r3 | |
96ec2: d1fb bne.n 96ebc <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1a8> | |
96ec4: e7f1 b.n 96eaa <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x196> | |
96ec6: f8dd a004 ldr.w sl, [sp, #4] | |
96eca: e79f b.n 96e0c <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0xf8> | |
96ecc: 4653 mov r3, sl | |
96ece: e7e6 b.n 96e9e <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x18a> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
00096f74 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j>: | |
96f74: e92d 4ff0 stmdb sp!, {r4, r5, r6, r7, r8, r9, sl, fp, lr} | |
96f78: 2a03 cmp r2, #3 | |
96f7a: b0a1 sub sp, #132 ; 0x84 | |
96f7c: 4607 mov r7, r0 | |
96f7e: 9103 str r1, [sp, #12] | |
96f80: 9201 str r2, [sp, #4] | |
96f82: f240 80e4 bls.w 9714e <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1da> | |
96f86: 0704 lsls r4, r0, #28 | |
96f88: 4603 mov r3, r0 | |
96f8a: bf18 it ne | |
96f8c: 9a01 ldrne r2, [sp, #4] | |
96f8e: d007 beq.n 96fa0 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x2c> | |
96f90: f843 1b04 str.w r1, [r3], #4 | |
96f94: 0718 lsls r0, r3, #28 | |
96f96: f102 32ff add.w r2, r2, #4294967295 ; 0xffffffff | |
96f9a: 461f mov r7, r3 | |
96f9c: d1f8 bne.n 96f90 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1c> | |
96f9e: 9201 str r2, [sp, #4] | |
96fa0: 9a01 ldr r2, [sp, #4] | |
96fa2: ab03 add r3, sp, #12 | |
96fa4: 2a3f cmp r2, #63 ; 0x3f | |
96fa6: f9e3 0caf vld1.32 {d16[]-d17[]}, [r3] | |
96faa: edcd 0b04 vstr d16, [sp, #16] | |
96fae: edcd 1b06 vstr d17, [sp, #24] | |
96fb2: f240 80e2 bls.w 9717a <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x206> | |
96fb6: ad08 add r5, sp, #32 | |
96fb8: ac04 add r4, sp, #16 | |
96fba: 463e mov r6, r7 | |
96fbc: 4694 mov ip, r2 | |
96fbe: 9702 str r7, [sp, #8] | |
96fc0: e894 000f ldmia.w r4, {r0, r1, r2, r3} | |
96fc4: f106 0b20 add.w fp, r6, #32 | |
96fc8: f106 0a30 add.w sl, r6, #48 ; 0x30 | |
96fcc: f106 0940 add.w r9, r6, #64 ; 0x40 | |
96fd0: f106 0850 add.w r8, r6, #80 ; 0x50 | |
96fd4: 4637 mov r7, r6 | |
96fd6: f1ac 0c40 sub.w ip, ip, #64 ; 0x40 | |
96fda: e885 000f stmia.w r5, {r0, r1, r2, r3} | |
96fde: eddd 0b08 vldr d16, [sp, #32] | |
96fe2: eddd 1b0a vldr d17, [sp, #40] ; 0x28 | |
96fe6: f1bc 0f3f cmp.w ip, #63 ; 0x3f | |
96fea: f947 0add vst1.64 {d16-d17}, [r7 :64]! | |
96fee: f947 0adf vst1.64 {d16-d17}, [r7 :64] | |
96ff2: f106 0760 add.w r7, r6, #96 ; 0x60 | |
96ff6: f94b 0adf vst1.64 {d16-d17}, [fp :64] | |
96ffa: f106 0b70 add.w fp, r6, #112 ; 0x70 | |
96ffe: f94a 0adf vst1.64 {d16-d17}, [sl :64] | |
97002: f106 0a80 add.w sl, r6, #128 ; 0x80 | |
97006: f949 0adf vst1.64 {d16-d17}, [r9 :64] | |
9700a: f106 0990 add.w r9, r6, #144 ; 0x90 | |
9700e: f948 0adf vst1.64 {d16-d17}, [r8 :64] | |
97012: f106 08a0 add.w r8, r6, #160 ; 0xa0 | |
97016: f947 0adf vst1.64 {d16-d17}, [r7 :64] | |
9701a: f106 07b0 add.w r7, r6, #176 ; 0xb0 | |
9701e: f94b 0adf vst1.64 {d16-d17}, [fp :64] | |
97022: f106 0bc0 add.w fp, r6, #192 ; 0xc0 | |
97026: f94a 0adf vst1.64 {d16-d17}, [sl :64] | |
9702a: f106 0ad0 add.w sl, r6, #208 ; 0xd0 | |
9702e: f949 0adf vst1.64 {d16-d17}, [r9 :64] | |
97032: f106 09e0 add.w r9, r6, #224 ; 0xe0 | |
97036: f948 0adf vst1.64 {d16-d17}, [r8 :64] | |
9703a: f106 08f0 add.w r8, r6, #240 ; 0xf0 | |
9703e: f506 7680 add.w r6, r6, #256 ; 0x100 | |
97042: f947 0adf vst1.64 {d16-d17}, [r7 :64] | |
97046: f94b 0adf vst1.64 {d16-d17}, [fp :64] | |
9704a: f94a 0adf vst1.64 {d16-d17}, [sl :64] | |
9704e: f949 0adf vst1.64 {d16-d17}, [r9 :64] | |
97052: f948 0adf vst1.64 {d16-d17}, [r8 :64] | |
97056: d8b3 bhi.n 96fc0 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x4c> | |
97058: 9a01 ldr r2, [sp, #4] | |
9705a: 9f02 ldr r7, [sp, #8] | |
9705c: f1a2 0340 sub.w r3, r2, #64 ; 0x40 | |
97060: f002 0a3f and.w sl, r2, #63 ; 0x3f | |
97064: 099b lsrs r3, r3, #6 | |
97066: 3301 adds r3, #1 | |
97068: eb07 2703 add.w r7, r7, r3, lsl #8 | |
9706c: f1ba 0f0f cmp.w sl, #15 | |
97070: d926 bls.n 970c0 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x14c> | |
97072: ad08 add r5, sp, #32 | |
97074: 463e mov r6, r7 | |
97076: 46d0 mov r8, sl | |
97078: e894 000f ldmia.w r4, {r0, r1, r2, r3} | |
9707c: f1a8 0810 sub.w r8, r8, #16 | |
97080: f106 0b20 add.w fp, r6, #32 | |
97084: f106 0930 add.w r9, r6, #48 ; 0x30 | |
97088: f1b8 0f0f cmp.w r8, #15 | |
9708c: 46b4 mov ip, r6 | |
9708e: f106 0640 add.w r6, r6, #64 ; 0x40 | |
97092: e885 000f stmia.w r5, {r0, r1, r2, r3} | |
97096: eddd 0b08 vldr d16, [sp, #32] | |
9709a: eddd 1b0a vldr d17, [sp, #40] ; 0x28 | |
9709e: f94c 0add vst1.64 {d16-d17}, [ip :64]! | |
970a2: f94c 0adf vst1.64 {d16-d17}, [ip :64] | |
970a6: f94b 0adf vst1.64 {d16-d17}, [fp :64] | |
970aa: f949 0adf vst1.64 {d16-d17}, [r9 :64] | |
970ae: d8e3 bhi.n 97078 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x104> | |
970b0: f1aa 0310 sub.w r3, sl, #16 | |
970b4: f00a 0a0f and.w sl, sl, #15 | |
970b8: 091b lsrs r3, r3, #4 | |
970ba: 3301 adds r3, #1 | |
970bc: eb07 1783 add.w r7, r7, r3, lsl #6 | |
970c0: f1ba 0f03 cmp.w sl, #3 | |
970c4: d919 bls.n 970fa <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x186> | |
970c6: ad08 add r5, sp, #32 | |
970c8: 46bc mov ip, r7 | |
970ca: 4656 mov r6, sl | |
970cc: e894 000f ldmia.w r4, {r0, r1, r2, r3} | |
970d0: 3e04 subs r6, #4 | |
970d2: 2e03 cmp r6, #3 | |
970d4: e885 000f stmia.w r5, {r0, r1, r2, r3} | |
970d8: eddd 0b08 vldr d16, [sp, #32] | |
970dc: eddd 1b0a vldr d17, [sp, #40] ; 0x28 | |
970e0: f94c 0adf vst1.64 {d16-d17}, [ip :64] | |
970e4: f10c 0c10 add.w ip, ip, #16 | |
970e8: d8f0 bhi.n 970cc <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x158> | |
970ea: f1aa 0304 sub.w r3, sl, #4 | |
970ee: f00a 0a03 and.w sl, sl, #3 | |
970f2: 089b lsrs r3, r3, #2 | |
970f4: 3301 adds r3, #1 | |
970f6: eb07 1703 add.w r7, r7, r3, lsl #4 | |
970fa: e894 000f ldmia.w r4, {r0, r1, r2, r3} | |
970fe: f1ba 0f01 cmp.w sl, #1 | |
97102: ac0c add r4, sp, #48 ; 0x30 | |
97104: e884 000f stmia.w r4, {r0, r1, r2, r3} | |
97108: d91b bls.n 97142 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1ce> | |
9710a: f10d 0e60 add.w lr, sp, #96 ; 0x60 | |
9710e: ad14 add r5, sp, #80 ; 0x50 | |
97110: f10d 0870 add.w r8, sp, #112 ; 0x70 | |
97114: ae10 add r6, sp, #64 ; 0x40 | |
97116: e885 000f stmia.w r5, {r0, r1, r2, r3} | |
9711a: eddd 0b14 vldr d16, [sp, #80] ; 0x50 | |
9711e: eddd 1b16 vldr d17, [sp, #88] ; 0x58 | |
97122: e886 000f stmia.w r6, {r0, r1, r2, r3} | |
97126: e88e 000f stmia.w lr, {r0, r1, r2, r3} | |
9712a: 4671 mov r1, lr | |
9712c: 4640 mov r0, r8 | |
9712e: f947 07dd vst1.64 {d16}, [r7 :64]! | |
97132: f000 f95b bl 973ec <_ZN6simdpp9arch_neon6move_lILj8EEENS0_13basic_int8x16ES2_> | |
97136: e898 000f ldmia.w r8, {r0, r1, r2, r3} | |
9713a: e885 000f stmia.w r5, {r0, r1, r2, r3} | |
9713e: e884 000f stmia.w r4, {r0, r1, r2, r3} | |
97142: f01a 0f01 tst.w sl, #1 | |
97146: d10c bne.n 97162 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1ee> | |
97148: b021 add sp, #132 ; 0x84 | |
9714a: e8bd 8ff0 ldmia.w sp!, {r4, r5, r6, r7, r8, r9, sl, fp, pc} | |
9714e: 9a01 ldr r2, [sp, #4] | |
97150: 2a00 cmp r2, #0 | |
97152: d0f9 beq.n 97148 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1d4> | |
97154: eb00 0382 add.w r3, r0, r2, lsl #2 | |
97158: f847 1b04 str.w r1, [r7], #4 | |
9715c: 429f cmp r7, r3 | |
9715e: d1fb bne.n 97158 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1e4> | |
97160: e7f2 b.n 97148 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1d4> | |
97162: e894 000f ldmia.w r4, {r0, r1, r2, r3} | |
97166: ac14 add r4, sp, #80 ; 0x50 | |
97168: e884 000f stmia.w r4, {r0, r1, r2, r3} | |
9716c: eddd 0b14 vldr d16, [sp, #80] ; 0x50 | |
97170: eddd 1b16 vldr d17, [sp, #88] ; 0x58 | |
97174: f9c7 080f vst1.32 {d16[0]}, [r7] | |
97178: e7e6 b.n 97148 <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0x1d4> | |
9717a: ac04 add r4, sp, #16 | |
9717c: f8dd a004 ldr.w sl, [sp, #4] | |
97180: e774 b.n 9706c <_ZN9arch_neonL8memset_TIN6simdpp9arch_neon8uint32x4EjEEvPT0_S4_j+0xf8> | |
97182: bf00 nop |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment