Samples: 25K of event 'cpu-clock', 4999 Hz, Event count (approx.): 5026605120, [percent: local period] instance int32 [benchapp] SumBench::SumInt()[OptimizedTier1]() /tmp/jitted-40832-27200.so 0.08 push rbp push r15 push r14 push r13 push rbx lea rbp,[rsp+0x20] mov rbx,QWORD PTR [rdi+0x8] test rbx,rbx 0.10 ↓ je 1e3 mov r15d,0x1 movabs rdi,0x746fa275ba78 cmp QWORD PTR [rbx],rdi ↓ jne 1f5 lea rax,[rbx+0x10] mov ecx,DWORD PTR [rbx+0x8] 3a: test r15d,r15d ↓ je 26c cmp ecx,0x20 ↓ jl 24d mov ecx,ecx 0.09 vxorps ymm0,ymm0,ymm0 vbroadcastss ymm1,DWORD PTR [rip+0x2d9] # 3b4 xor edx,edx lea rdi,[rcx-0x20] 0.19 61: vmovups ymm2,YMMWORD PTR [rax+rdx*4] vpaddd ymm3,ymm2,ymm0 1.33 vpxor ymm2,ymm2,ymm3 vpternlogd ymm0,ymm2,ymm3,0x48 8.13 vmovups ymm2,YMMWORD PTR [rax+rdx*4+0x20] 0.10 vpaddd ymm4,ymm2,ymm3 vpxor ymm2,ymm2,ymm4 vpternlogd ymm3,ymm2,ymm4,0x48 0.26 vpor ymm0,ymm3,ymm0 vmovups ymm2,YMMWORD PTR [rax+rdx*4+0x40] 1.26 vpaddd ymm3,ymm2,ymm4 vpxor ymm2,ymm2,ymm3 12.05 vpternlogd ymm4,ymm2,ymm3,0x48 0.15 vpor ymm0,ymm4,ymm0 vmovups ymm2,YMMWORD PTR [rax+rdx*4+0x60] vpaddd ymm4,ymm2,ymm3 0.86 vpxor ymm2,ymm2,ymm4 vpternlogd ymm3,ymm2,ymm4,0x48 5.99 vpternlogd ymm0,ymm3,ymm1,0xa8 0.62 vptest ymm0,ymm0 43.34 ↓ jne 240 24.01 add rdx,0x20 0.09 cmp rdx,rdi vmovaps ymm0,ymm4 ↑ jb 61 0.00 lea rdi,[rcx-0x8] cmp rdx,rdi 0.01 ↓ jae 118 vxorps ymm2,ymm2,ymm2 e8: vmovups ymm3,YMMWORD PTR [rax+rdx*4] 0.20 vpaddd ymm4,ymm0,ymm3 vpxor ymm3,ymm4,ymm3 vpternlogd ymm0,ymm3,ymm4,0x48 vpor ymm2,ymm0,ymm2 0.02 vmovaps ymm0,ymm4 add rdx,0x8 0.09 cmp rdx,rdi ↑ jb e8 vptest ymm1,ymm2 0.25 ↓ jne 240 0.07 118: vmovd edi,xmm0 vmovaps ymm1,ymm0 vpextrd esi,xmm1,0x1 0.00 add edi,esi ↓ jo 325 vmovaps ymm1,ymm0 0.04 vpextrd esi,xmm1,0x2 0.04 add esi,edi ↓ jo 325 mov edi,esi vmovaps ymm1,ymm0 0.01 vpextrd esi,xmm1,0x3 add esi,edi 0.05 ↓ jo 325 mov edi,esi 0.05 vextracti128 xmm1,ymm0,0x1 vmovd esi,xmm1 add esi,edi ↓ jo 325 mov edi,esi vextracti128 xmm1,ymm0,0x1 vpextrd esi,xmm1,0x1 0.05 add esi,edi 0.04 ↓ jo 325 mov edi,esi vextracti128 xmm1,ymm0,0x1 vpextrd esi,xmm1,0x2 add esi,edi ↓ jo 325 mov edi,esi 0.04 vextracti128 xmm0,ymm0,0x1 vpextrd esi,xmm0,0x3 0.04 add esi,edi ↓ jo 325 mov edi,esi cmp rdx,rcx ↓ jae 1d1 nop nop 0.04 1c0: add edi,DWORD PTR [rax+rdx*4] 0.06 ↓ jo 325 inc rdx 0.14 cmp rdx,rcx 0.01 ↑ jb 1c0 1d1: mov r15d,edi 0.06 1d4: mov eax,r15d vzeroupper pop rbx pop r13 0.00 pop r14 pop r15 0.04 pop rbp ← ret 1e3: mov edi,0x11 movabs rax,0x746fa29263e8 → call QWORD PTR [rax] int3 1f5: movabs rdi,0x746fa2a9dcf0 cmp QWORD PTR [rbx],rdi ↓ jne 234 mov esi,DWORD PTR [rbx+0x10] mov rdi,QWORD PTR [rbx+0x8] cmp DWORD PTR [rdi+0x8],esi ↓ jae 21d movabs rax,0x746fa2927228 → call QWORD PTR [rax] int3 21d: add rdi,0x10 movabs rax,0x746fa2c77270 → call QWORD PTR [rax] mov ecx,edx ↑ jmp 3a 234: xor eax,eax xor ecx,ecx xor r15d,r15d ↑ jmp 3a 240: movabs rax,0x746fa328cd98 → call QWORD PTR [rax] int3 24d: xor edi,edi xor edx,edx cmp edx,ecx ↓ jge 264 255: add edi,DWORD PTR [rax+rdx*4] ↓ jo 325 inc edx cmp edx,ecx ↑ jl 255 264: mov r15d,edi ↑ jmp 1d4 26c: xor r15d,r15d mov r14d,DWORD PTR [rbx+0x8] test r14d,r14d ↓ je 2aa movabs rdi,0x746fa32da940 → call instance int32 [benchapp] SumBench::SumInt()[OptimizedTier1]+0x7db00090 mov r13,rax mov rdi,r13 mov esi,r14d movabs rax,0x746fa2c74e28 → call QWORD PTR [rax] lea rdi,[r13+0x10] mov rsi,rbx → call instance int32 [benchapp] SumBench::SumInt()[OptimizedTier1]+0xfffffffffe583720 ↓ jmp 2cd 2aa: movabs rdi,0x746fa32da940 movabs rax,0x746fa2725728 → call QWORD PTR [rax] movabs rax,0x745fe8802e10 mov r13,QWORD PTR [rax] 2cd: mov eax,DWORD PTR [r13+0x8] inc eax cmp eax,DWORD PTR [r13+0xc] ↓ jae 301 ↓ jmp 2fb 2db: mov eax,DWORD PTR [r13+0x8] cmp eax,DWORD PTR [r13+0xc] ↓ jae 30f mov rax,QWORD PTR [r13+0x10] mov edi,DWORD PTR [r13+0x8] cmp edi,DWORD PTR [rax+0x8] ↓ jae 32b add r15d,DWORD PTR [rax+rdi*4+0x10] ↓ jo 325 ↑ jmp 2cd 2fb: mov DWORD PTR [r13+0x8],eax ↑ jmp 2db 301: mov eax,DWORD PTR [r13+0xc] mov DWORD PTR [r13+0x8],eax xor eax,eax ↑ jne 2db ↓ jmp 320 30f: mov edi,DWORD PTR [r13+0x8] movabs rax,0x746fa2c7dd10 → call QWORD PTR [rax] int3 320: ↑ jmp 1d4 325: → call instance int32 [benchapp] SumBench::SumInt()[OptimizedTier1]+0xffffffffff684e50 int3 32b: → call instance int32 [benchapp] SumBench::SumInt()[OptimizedTier1]+0xffffffffff684e68 int3