| Loop Id: 4 | Module: exec | Source: main.c:140-147 | Coverage: 0.05% |
|---|
| Loop Id: 4 | Module: exec | Source: main.c:140-147 | Coverage: 0.05% |
|---|
0x401870 VMOVSS 0x6091b0(%R12,%RBX,4),%XMM0 [3] |
0x40187a VMOVSS 0x66ac30(%R12,%RBX,4),%XMM1 [3] |
0x401884 VMOVSS 0x6cc6b0(%R12,%RBX,4),%XMM2 [3] |
0x40188e MOV $0x6091b0,%ESI |
0x401893 MOV $0x66ac30,%EDX |
0x401898 MOV $0x6cc6b0,%ECX |
0x40189d MOV $0x72e130,%R8D |
0x4018a3 MOV %R14D,%EDI |
0x4018a6 VMOVSS 0x41f6(%RIP),%XMM3 [1] |
0x4018ae VMOVSS 0x41f2(%RIP),%XMM4 [1] |
0x4018b6 MOV %R15,%R9 |
0x4018b9 LEA -0x48(%RBP),%RAX |
0x4018bd PUSH %RAX |
0x4018be LEA -0x44(%RBP),%RAX |
0x4018c2 PUSH %RAX |
0x4018c3 CALL 4019c0 <Step10_orig> |
0x4018c8 ADD $0x10,%RSP |
0x4018cc VMOVSS -0x40(%RBP),%XMM0 [2] |
0x4018d1 VMOVSS 0x41d3(%RIP),%XMM1 [1] |
0x4018d9 VFMADD213SS 0x78fbb0(%R12,%RBX,4),%XMM1,%XMM0 [3] |
0x4018e3 VMOVSS %XMM0,0x78fbb0(%R12,%RBX,4) [3] |
0x4018ed VMOVSS -0x44(%RBP),%XMM0 [2] |
0x4018f2 VFMADD213SS 0x7f1630(%R12,%RBX,4),%XMM1,%XMM0 [3] |
0x4018fc VMOVSS %XMM0,0x7f1630(%R12,%RBX,4) [3] |
0x401906 VMOVSS -0x48(%RBP),%XMM0 [2] |
0x40190b VFMADD213SS 0x8530b0(%R12,%RBX,4),%XMM1,%XMM0 [3] |
0x401915 VMOVSS %XMM0,0x8530b0(%R12,%RBX,4) [3] |
0x40191f INC %RBX |
0x401922 CMP %RBX,%R13 |
0x401925 JNE 401870 |
/scratch_na/users/xoserete/qaas_runs/171-415-1813/intel/HACCmk/build/HACCmk/src/main.c: 140 - 147 |
-------------------------------------------------------------------------------- |
140: for ( i = 0; i < count; ++i) |
141: { |
142: Step10_orig( n, xx[i], yy[i], zz[i], fsrrmax2, mp_rsm2, xx, yy, zz, mass, &dx1, &dy1, &dz1 ); |
143: |
144: vx1[i] = vx1[i] + dx1 * fcoeff; |
145: vy1[i] = vy1[i] + dy1 * fcoeff; |
146: vz1[i] = vz1[i] + dz1 * fcoeff; |
147: } |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.38 |
| CQA speedup if FP arith vectorized | 1.38 |
| CQA speedup if fully vectorized | 15.48 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.38 |
| Bottlenecks | micro-operation queue, |
| Function | main.extracted.8 |
| Source | main.c:140-147 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.50 |
| CQA cycles if no scalar integer | 4.00 |
| CQA cycles if FP arith vectorized | 4.00 |
| CQA cycles if fully vectorized | 0.36 |
| Front-end cycles | 5.50 |
| DIV/SQRT cycles | 1.70 |
| P0 cycles | 1.50 |
| P1 cycles | 4.00 |
| P2 cycles | 4.00 |
| P3 cycles | 3.00 |
| P4 cycles | 1.60 |
| P5 cycles | 1.60 |
| P6 cycles | 3.00 |
| P7 cycles | 3.00 |
| P8 cycles | 3.00 |
| P9 cycles | 1.60 |
| P10 cycles | 4.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 5.50 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 30.00 |
| Nb uops | 30.00 |
| Nb loads | 12.00 |
| Nb stores | 3.00 |
| Nb stack references | 3.00 |
| FLOP/cycle | 1.09 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 3.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 10.91 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 48.00 |
| Bytes stored | 12.00 |
| Stride 0 | 2.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 1.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 6.82 |
| Vector-efficiency ratio load | 6.25 |
| Vector-efficiency ratio store | 6.25 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | 6.25 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 7.29 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.38 |
| CQA speedup if FP arith vectorized | 1.38 |
| CQA speedup if fully vectorized | 15.48 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.38 |
| Bottlenecks | micro-operation queue, |
| Function | main.extracted.8 |
| Source | main.c:140-147 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.50 |
| CQA cycles if no scalar integer | 4.00 |
| CQA cycles if FP arith vectorized | 4.00 |
| CQA cycles if fully vectorized | 0.36 |
| Front-end cycles | 5.50 |
| DIV/SQRT cycles | 1.70 |
| P0 cycles | 1.50 |
| P1 cycles | 4.00 |
| P2 cycles | 4.00 |
| P3 cycles | 3.00 |
| P4 cycles | 1.60 |
| P5 cycles | 1.60 |
| P6 cycles | 3.00 |
| P7 cycles | 3.00 |
| P8 cycles | 3.00 |
| P9 cycles | 1.60 |
| P10 cycles | 4.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 5.50 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 30.00 |
| Nb uops | 30.00 |
| Nb loads | 12.00 |
| Nb stores | 3.00 |
| Nb stack references | 3.00 |
| FLOP/cycle | 1.09 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 3.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 10.91 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 48.00 |
| Bytes stored | 12.00 |
| Stride 0 | 2.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 1.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 6.82 |
| Vector-efficiency ratio load | 6.25 |
| Vector-efficiency ratio store | 6.25 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | 6.25 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 7.29 |
| Path / |
| Function | main.extracted.8 |
| Source file and lines | main.c:140-147 |
| Module | exec |
| nb instructions | 30 |
| nb uops | 30 |
| loop length | 187 |
| used x86 registers | 14 |
| used mmx registers | 0 |
| used xmm registers | 5 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 5.50 cycles |
| front end | 5.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.70 | 1.50 | 4.00 | 4.00 | 3.00 | 1.60 | 1.60 | 3.00 | 3.00 | 3.00 | 1.60 | 4.00 |
| cycles | 1.70 | 1.50 | 4.00 | 4.00 | 3.00 | 1.60 | 1.60 | 3.00 | 3.00 | 3.00 | 1.60 | 4.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 5.50 |
| Stall cycles | 0.00 |
| Front-end | 5.50 |
| Dispatch | 4.00 |
| Data deps. | 1.00 |
| Overall L1 | 5.50 |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 8% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 7% |
| all | 6% |
| load | 6% |
| store | 6% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 6% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 6% |
| load | 6% |
| store | 6% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | 6% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 7% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVSS 0x6091b0(%R12,%RBX,4),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMOVSS 0x66ac30(%R12,%RBX,4),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMOVSS 0x6cc6b0(%R12,%RBX,4),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV $0x6091b0,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV $0x66ac30,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV $0x6cc6b0,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV $0x72e130,%R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %R14D,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VMOVSS 0x41f6(%RIP),%XMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMOVSS 0x41f2(%RIP),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %R15,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| LEA -0x48(%RBP),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| PUSH %RAX | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 5-12 | 0.50 |
| LEA -0x44(%RBP),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| PUSH %RAX | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 5-12 | 0.50 |
| CALL 4019c0 <Step10_orig> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
| ADD $0x10,%RSP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VMOVSS -0x40(%RBP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMOVSS 0x41d3(%RIP),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VFMADD213SS 0x78fbb0(%R12,%RBX,4),%XMM1,%XMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVSS %XMM0,0x78fbb0(%R12,%RBX,4) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| VMOVSS -0x44(%RBP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VFMADD213SS 0x7f1630(%R12,%RBX,4),%XMM1,%XMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVSS %XMM0,0x7f1630(%R12,%RBX,4) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| VMOVSS -0x48(%RBP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VFMADD213SS 0x8530b0(%R12,%RBX,4),%XMM1,%XMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVSS %XMM0,0x8530b0(%R12,%RBX,4) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| INC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RBX,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JNE 401870 <main.extracted.8+0x90> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | main.extracted.8 |
| Source file and lines | main.c:140-147 |
| Module | exec |
| nb instructions | 30 |
| nb uops | 30 |
| loop length | 187 |
| used x86 registers | 14 |
| used mmx registers | 0 |
| used xmm registers | 5 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 5.50 cycles |
| front end | 5.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.70 | 1.50 | 4.00 | 4.00 | 3.00 | 1.60 | 1.60 | 3.00 | 3.00 | 3.00 | 1.60 | 4.00 |
| cycles | 1.70 | 1.50 | 4.00 | 4.00 | 3.00 | 1.60 | 1.60 | 3.00 | 3.00 | 3.00 | 1.60 | 4.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 5.50 |
| Stall cycles | 0.00 |
| Front-end | 5.50 |
| Dispatch | 4.00 |
| Data deps. | 1.00 |
| Overall L1 | 5.50 |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 8% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 7% |
| all | 6% |
| load | 6% |
| store | 6% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 6% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 6% |
| load | 6% |
| store | 6% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | 6% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 7% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVSS 0x6091b0(%R12,%RBX,4),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMOVSS 0x66ac30(%R12,%RBX,4),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMOVSS 0x6cc6b0(%R12,%RBX,4),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV $0x6091b0,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV $0x66ac30,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV $0x6cc6b0,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV $0x72e130,%R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %R14D,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VMOVSS 0x41f6(%RIP),%XMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMOVSS 0x41f2(%RIP),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %R15,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| LEA -0x48(%RBP),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| PUSH %RAX | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 5-12 | 0.50 |
| LEA -0x44(%RBP),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| PUSH %RAX | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 5-12 | 0.50 |
| CALL 4019c0 <Step10_orig> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
| ADD $0x10,%RSP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VMOVSS -0x40(%RBP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMOVSS 0x41d3(%RIP),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VFMADD213SS 0x78fbb0(%R12,%RBX,4),%XMM1,%XMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVSS %XMM0,0x78fbb0(%R12,%RBX,4) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| VMOVSS -0x44(%RBP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VFMADD213SS 0x7f1630(%R12,%RBX,4),%XMM1,%XMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVSS %XMM0,0x7f1630(%R12,%RBX,4) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| VMOVSS -0x48(%RBP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VFMADD213SS 0x8530b0(%R12,%RBX,4),%XMM1,%XMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVSS %XMM0,0x8530b0(%R12,%RBX,4) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| INC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RBX,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JNE 401870 <main.extracted.8+0x90> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
