Loop Id: 2 | Module: exec | Source: Step10_orig.c:19-31 | Coverage: 87.83% |
---|
Loop Id: 2 | Module: exec | Source: Step10_orig.c:19-31 | Coverage: 87.83% |
---|
0x401720 VMOVUPS (%RDI,%R11,1),%YMM8 [4] |
0x401726 VMOVUPS (%RSI,%R11,1),%YMM0 [2] |
0x40172c VMOVUPS (%RDX,%R11,1),%YMM5 [3] |
0x401732 VSUBPS %YMM26,%YMM8,%YMM9 |
0x401738 VSUBPS %YMM25,%YMM0,%YMM8 |
0x40173e VSUBPS %YMM24,%YMM5,%YMM30 |
0x401744 VMULPS %YMM8,%YMM8,%YMM28 |
0x40174a VFMADD231PS %YMM9,%YMM9,%YMM28 |
0x401750 VFMADD231PS %YMM30,%YMM30,%YMM28 |
0x401756 VMOVAPS %YMM28,%YMM6 |
0x40175c VCMPPS $0x1,%YMM15,%YMM28,%K1 |
0x401763 VADDPS %YMM23,%YMM28,%YMM5 |
0x401769 VCMPPS $0x1,%YMM15,%YMM6,%YMM0 |
0x40176f VCMPPS $0xe,%YMM16,%YMM28,%K2 |
0x401776 VMOVUPS (%R8,%R11,1),%YMM13{%K1} [1] |
0x40177d VCVTPS2PD %XMM5,%YMM6 |
0x401781 VSQRTPD %YMM6,%YMM29 |
0x401787 ADD $0x20,%R11 |
0x40178b VANDPS %YMM13,%YMM0,%YMM27 |
0x401791 VEXTRACTF128 $0x1,%YMM5,%XMM0 |
0x401797 VCVTPS2PD %XMM0,%YMM5 |
0x40179b VSQRTPD %YMM5,%YMM31 |
0x4017a1 VMOVAPS %YMM28,%YMM0 |
0x4017a7 VFMADD132PS %YMM22,%YMM21,%YMM0 |
0x4017ad VMULPD %YMM29,%YMM6,%YMM6 |
0x4017b3 VMULPD %YMM31,%YMM5,%YMM5 |
0x4017b9 VFMADD132PS %YMM28,%YMM20,%YMM0 |
0x4017bf VDIVPD %YMM6,%YMM14,%YMM6 |
0x4017c3 VFMADD132PS %YMM28,%YMM19,%YMM0 |
0x4017c9 VFMADD132PS %YMM28,%YMM18,%YMM0 |
0x4017cf VFMADD132PS %YMM28,%YMM17,%YMM0 |
0x4017d5 VCVTPS2PD %XMM0,%YMM28 |
0x4017db VEXTRACTF128 $0x1,%YMM0,%XMM0 |
0x4017e1 VDIVPD %YMM5,%YMM14,%YMM5 |
0x4017e5 VCVTPS2PD %XMM0,%YMM0 |
0x4017e9 VADDPD %YMM28,%YMM6,%YMM6 |
0x4017ef VCVTPD2PS %YMM6,%XMM6 |
0x4017f3 VADDPD %YMM0,%YMM5,%YMM5 |
0x4017f7 VCVTPD2PS %YMM5,%XMM0 |
0x4017fb VINSERTF128 $0x1,%XMM0,%YMM6,%YMM5 |
0x401801 VMULPS %YMM27,%YMM5,%YMM6 |
0x401807 VMULPS %YMM6,%YMM9,%YMM0{%K2}{z} |
0x40180d VMULPS %YMM6,%YMM8,%YMM9{%K2}{z} |
0x401813 VMULPS %YMM6,%YMM30,%YMM8{%K2}{z} |
0x401819 VADDPS %YMM0,%YMM10,%YMM10 |
0x40181d VADDPS %YMM9,%YMM11,%YMM11 |
0x401822 VADDPS %YMM8,%YMM12,%YMM12 |
0x401827 CMP %R11,%RBX |
0x40182a JNE 401720 |
/scratch_na/users/xoserete/qaas_runs/171-415-1813/intel/HACCmk/build/HACCmk/src/Step10_orig.c: 19 - 31 |
-------------------------------------------------------------------------------- |
19: for ( j = 0; j < count1; j++ ) |
20: { |
21: dxc = xx1[j] - xxi; |
22: dyc = yy1[j] - yyi; |
23: dzc = zz1[j] - zzi; |
24: |
25: r2 = dxc * dxc + dyc * dyc + dzc * dzc; |
26: |
27: m = ( r2 < fsrrmax2 ) ? mass1[j] : 0.0f; |
28: |
29: f = pow( r2 + mp_rsm2, -1.5 ) - ( ma0 + r2*(ma1 + r2*(ma2 + r2*(ma3 + r2*(ma4 + r2*ma5))))); |
30: |
31: f = ( r2 > 0.0f ) ? m * f : 0.0f; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►46.63+ | main._omp_fn.1 | main.c:144 | exec |
○ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
►46.46+ | main._omp_fn.1 | main.c:144 | exec |
○ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
►5.17+ | main._omp_fn.1 | main.c:144 | exec |
○ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.22 |
Bottlenecks | P0, |
Function | Step10_orig |
Source | Step10_orig.c:19-31 |
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 | 34.00 |
CQA cycles if no scalar integer | 34.00 |
CQA cycles if FP arith vectorized | 34.00 |
CQA cycles if fully vectorized | 34.00 |
Front-end cycles | 9.00 |
DIV/SQRT cycles | 15.33 |
P0 cycles | 15.33 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 15.33 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 1.33 |
P11 cycles | 34.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 35.22 - 34.90 |
Stall cycles (UFS) | 25.60 - 25.28 |
Nb insns | 49.00 |
Nb uops | 54.00 |
Nb loads | 4.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 7.06 |
Nb FLOP add-sub | 64.00 |
Nb FLOP mul | 48.00 |
Nb FLOP fma | 56.00 |
Nb FLOP div | 8.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 8.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 3.76 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 4.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | 100.00 |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 46.20 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 50.00 |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | 50.00 |
Vector-efficiency ratio div_sqrt | 50.00 |
Vector-efficiency ratio other | 38.33 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.22 |
Bottlenecks | P0, |
Function | Step10_orig |
Source | Step10_orig.c:19-31 |
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 | 34.00 |
CQA cycles if no scalar integer | 34.00 |
CQA cycles if FP arith vectorized | 34.00 |
CQA cycles if fully vectorized | 34.00 |
Front-end cycles | 9.00 |
DIV/SQRT cycles | 15.33 |
P0 cycles | 15.33 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 15.33 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 1.33 |
P11 cycles | 34.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 35.22 - 34.90 |
Stall cycles (UFS) | 25.60 - 25.28 |
Nb insns | 49.00 |
Nb uops | 54.00 |
Nb loads | 4.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 7.06 |
Nb FLOP add-sub | 64.00 |
Nb FLOP mul | 48.00 |
Nb FLOP fma | 56.00 |
Nb FLOP div | 8.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 8.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 3.76 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 4.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | 100.00 |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 46.20 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 50.00 |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | 50.00 |
Vector-efficiency ratio div_sqrt | 50.00 |
Vector-efficiency ratio other | 38.33 |
Path / |
Function | Step10_orig |
Source file and lines | Step10_orig.c:19-31 |
Module | exec |
nb instructions | 49 |
nb uops | 54 |
loop length | 272 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 27 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.29 |
micro-operation queue | 9.00 cycles |
front end | 9.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 15.33 | 15.33 | 1.33 | 1.33 | 0.00 | 15.33 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
cycles | 15.33 | 15.33 | 1.33 | 1.33 | 0.00 | 15.33 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
Cycles executing div or sqrt instructions | 34.00 |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 35.22-34.90 |
Stall cycles | 25.60-25.28 |
RS full (events) | 0.30-0.24 |
PRF_FLOAT full (events) | 27.44-27.17 |
Front-end | 9.00 |
Dispatch | 15.33 |
DIV/SQRT | 34.00 |
Data deps. | 3.00 |
Overall L1 | 34.00 |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 46% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | 50% |
div/sqrt | 50% |
other | 38% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPS (%RDI,%R11,1),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPS (%RSI,%R11,1),%YMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPS (%RDX,%R11,1),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VSUBPS %YMM26,%YMM8,%YMM9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSUBPS %YMM25,%YMM0,%YMM8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSUBPS %YMM24,%YMM5,%YMM30 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMULPS %YMM8,%YMM8,%YMM28 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PS %YMM9,%YMM9,%YMM28 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PS %YMM30,%YMM30,%YMM28 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPS %YMM28,%YMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VCMPPS $0x1,%YMM15,%YMM28,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPS %YMM23,%YMM28,%YMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VCMPPS $0x1,%YMM15,%YMM6,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VCMPPS $0xe,%YMM16,%YMM28,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVUPS (%R8,%R11,1),%YMM13{%K1} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VCVTPS2PD %XMM5,%YMM6 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VSQRTPD %YMM6,%YMM29 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-19 | 9 |
ADD $0x20,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VANDPS %YMM13,%YMM0,%YMM27 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VEXTRACTF128 $0x1,%YMM5,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCVTPS2PD %XMM0,%YMM5 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VSQRTPD %YMM5,%YMM31 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-19 | 9 |
VMOVAPS %YMM28,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VFMADD132PS %YMM22,%YMM21,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %YMM29,%YMM6,%YMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %YMM31,%YMM5,%YMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PS %YMM28,%YMM20,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VDIVPD %YMM6,%YMM14,%YMM6 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
VFMADD132PS %YMM28,%YMM19,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PS %YMM28,%YMM18,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PS %YMM28,%YMM17,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VCVTPS2PD %XMM0,%YMM28 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VEXTRACTF128 $0x1,%YMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VDIVPD %YMM5,%YMM14,%YMM5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
VCVTPS2PD %XMM0,%YMM0 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VADDPD %YMM28,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VCVTPD2PS %YMM6,%XMM6 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VADDPD %YMM0,%YMM5,%YMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VCVTPD2PS %YMM5,%XMM0 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VINSERTF128 $0x1,%XMM0,%YMM6,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMULPS %YMM27,%YMM5,%YMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPS %YMM6,%YMM9,%YMM0{%K2}{z} | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPS %YMM6,%YMM8,%YMM9{%K2}{z} | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPS %YMM6,%YMM30,%YMM8{%K2}{z} | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPS %YMM0,%YMM10,%YMM10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDPS %YMM9,%YMM11,%YMM11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDPS %YMM8,%YMM12,%YMM12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
CMP %R11,%RBX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 401720 <Step10_orig+0xb0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | Step10_orig |
Source file and lines | Step10_orig.c:19-31 |
Module | exec |
nb instructions | 49 |
nb uops | 54 |
loop length | 272 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 27 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.29 |
micro-operation queue | 9.00 cycles |
front end | 9.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 15.33 | 15.33 | 1.33 | 1.33 | 0.00 | 15.33 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
cycles | 15.33 | 15.33 | 1.33 | 1.33 | 0.00 | 15.33 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
Cycles executing div or sqrt instructions | 34.00 |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 35.22-34.90 |
Stall cycles | 25.60-25.28 |
RS full (events) | 0.30-0.24 |
PRF_FLOAT full (events) | 27.44-27.17 |
Front-end | 9.00 |
Dispatch | 15.33 |
DIV/SQRT | 34.00 |
Data deps. | 3.00 |
Overall L1 | 34.00 |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 46% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | 50% |
div/sqrt | 50% |
other | 38% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPS (%RDI,%R11,1),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPS (%RSI,%R11,1),%YMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPS (%RDX,%R11,1),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VSUBPS %YMM26,%YMM8,%YMM9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSUBPS %YMM25,%YMM0,%YMM8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSUBPS %YMM24,%YMM5,%YMM30 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMULPS %YMM8,%YMM8,%YMM28 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PS %YMM9,%YMM9,%YMM28 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PS %YMM30,%YMM30,%YMM28 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPS %YMM28,%YMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VCMPPS $0x1,%YMM15,%YMM28,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPS %YMM23,%YMM28,%YMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VCMPPS $0x1,%YMM15,%YMM6,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VCMPPS $0xe,%YMM16,%YMM28,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVUPS (%R8,%R11,1),%YMM13{%K1} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VCVTPS2PD %XMM5,%YMM6 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VSQRTPD %YMM6,%YMM29 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-19 | 9 |
ADD $0x20,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VANDPS %YMM13,%YMM0,%YMM27 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VEXTRACTF128 $0x1,%YMM5,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCVTPS2PD %XMM0,%YMM5 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VSQRTPD %YMM5,%YMM31 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-19 | 9 |
VMOVAPS %YMM28,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VFMADD132PS %YMM22,%YMM21,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %YMM29,%YMM6,%YMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %YMM31,%YMM5,%YMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PS %YMM28,%YMM20,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VDIVPD %YMM6,%YMM14,%YMM6 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
VFMADD132PS %YMM28,%YMM19,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PS %YMM28,%YMM18,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PS %YMM28,%YMM17,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VCVTPS2PD %XMM0,%YMM28 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VEXTRACTF128 $0x1,%YMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VDIVPD %YMM5,%YMM14,%YMM5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
VCVTPS2PD %XMM0,%YMM0 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VADDPD %YMM28,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VCVTPD2PS %YMM6,%XMM6 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VADDPD %YMM0,%YMM5,%YMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VCVTPD2PS %YMM5,%XMM0 | 2 | 0.50 | 0.50 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 1 |
VINSERTF128 $0x1,%XMM0,%YMM6,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMULPS %YMM27,%YMM5,%YMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPS %YMM6,%YMM9,%YMM0{%K2}{z} | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPS %YMM6,%YMM8,%YMM9{%K2}{z} | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPS %YMM6,%YMM30,%YMM8{%K2}{z} | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPS %YMM0,%YMM10,%YMM10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDPS %YMM9,%YMM11,%YMM11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDPS %YMM8,%YMM12,%YMM12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
CMP %R11,%RBX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 401720 <Step10_orig+0xb0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |