Loop Id: 583 | Module: exec | Source: BsplineFunctor.h:291-298 | Coverage: 0.37% |
---|
Loop Id: 583 | Module: exec | Source: BsplineFunctor.h:291-298 | Coverage: 0.37% |
---|
0x44785d VMOVSD (%R8,%RAX,8),%XMM10 [9] |
0x447863 VCOMISD %XMM10,%XMM1 |
0x447868 JBE 447882 |
0x44786a LEA (%RDX,%RAX,1),%R14D |
0x44786e CMP %R14D,%EBX |
0x447871 JE 447882 |
0x447873 MOVSXD %ECX,%R15 |
0x447876 INC %ECX |
0x447878 MOV %EAX,(%R10,%R15,4) [14] |
0x44787c VMOVSD %XMM10,(%RSI,%R15,8) [3] |
0x447882 INC %RAX |
0x447885 VMOVSD (%R8,%RAX,8),%XMM11 [10] |
0x44788b VCOMISD %XMM11,%XMM1 |
0x447890 JBE 4478aa |
0x447892 LEA (%RDX,%RAX,1),%R14D |
0x447896 CMP %R14D,%EBX |
0x447899 JE 4478aa |
0x44789b MOVSXD %ECX,%R15 |
0x44789e INC %ECX |
0x4478a0 MOV %EAX,(%R10,%R15,4) [13] |
0x4478a4 VMOVSD %XMM11,(%RSI,%R15,8) [2] |
0x4478aa LEA 0x1(%RAX),%R14 |
0x4478ae VMOVSD (%R8,%R14,8),%XMM12 [11] |
0x4478b4 VCOMISD %XMM12,%XMM1 |
0x4478b9 JBE 4478d3 |
0x4478bb LEA (%RDX,%R14,1),%R15D |
0x4478bf CMP %R15D,%EBX |
0x4478c2 JE 4478d3 |
0x4478c4 MOVSXD %ECX,%R15 |
0x4478c7 INC %ECX |
0x4478c9 MOV %R14D,(%R10,%R15,4) [12] |
0x4478cd VMOVSD %XMM12,(%RSI,%R15,8) [1] |
0x4478d3 LEA 0x2(%RAX),%R14 |
0x4478d7 VMOVSD (%R8,%R14,8),%XMM13 [11] |
0x4478dd VCOMISD %XMM13,%XMM1 |
0x4478e2 JBE 4478fc |
0x4478e4 LEA (%RDX,%R14,1),%R15D |
0x4478e8 CMP %R15D,%EBX |
0x4478eb JE 4478fc |
0x4478ed MOVSXD %ECX,%R15 |
0x4478f0 INC %ECX |
0x4478f2 MOV %R14D,(%R10,%R15,4) [8] |
0x4478f6 VMOVSD %XMM13,(%RSI,%R15,8) [19] |
0x4478fc LEA 0x3(%RAX),%R14 |
0x447900 VMOVSD (%R8,%R14,8),%XMM14 [11] |
0x447906 VCOMISD %XMM14,%XMM1 |
0x44790b JBE 447925 |
0x44790d LEA (%RDX,%R14,1),%R15D |
0x447911 CMP %R15D,%EBX |
0x447914 JE 447925 |
0x447916 MOVSXD %ECX,%R15 |
0x447919 INC %ECX |
0x44791b MOV %R14D,(%R10,%R15,4) [7] |
0x44791f VMOVSD %XMM14,(%RSI,%R15,8) [18] |
0x447925 LEA 0x4(%RAX),%R14 |
0x447929 VMOVSD (%R8,%R14,8),%XMM15 [11] |
0x44792f VCOMISD %XMM15,%XMM1 |
0x447934 JBE 44794e |
0x447936 LEA (%RDX,%R14,1),%R15D |
0x44793a CMP %R15D,%EBX |
0x44793d JE 44794e |
0x44793f MOVSXD %ECX,%R15 |
0x447942 INC %ECX |
0x447944 MOV %R14D,(%R10,%R15,4) [6] |
0x447948 VMOVSD %XMM15,(%RSI,%R15,8) [17] |
0x44794e LEA 0x5(%RAX),%R14 |
0x447952 VMOVSD (%R8,%R14,8),%XMM4 [11] |
0x447958 VCOMISD %XMM4,%XMM1 |
0x44795c JBE 447976 |
0x44795e LEA (%RDX,%R14,1),%R15D |
0x447962 CMP %R15D,%EBX |
0x447965 JE 447976 |
0x447967 MOVSXD %ECX,%R15 |
0x44796a INC %ECX |
0x44796c MOV %R14D,(%R10,%R15,4) [5] |
0x447970 VMOVSD %XMM4,(%RSI,%R15,8) [16] |
0x447976 LEA 0x6(%RAX),%R14 |
0x44797a VMOVSD (%R8,%R14,8),%XMM2 [11] |
0x447980 VCOMISD %XMM2,%XMM1 |
0x447984 JBE 44799e |
0x447986 LEA (%RDX,%R14,1),%R15D |
0x44798a CMP %R15D,%EBX |
0x44798d JE 44799e |
0x44798f MOVSXD %ECX,%R15 |
0x447992 INC %ECX |
0x447994 MOV %R14D,(%R10,%R15,4) [4] |
0x447998 VMOVSD %XMM2,(%RSI,%R15,8) [15] |
0x44799e MOV 0x4e8(%RSP),%R14 [20] |
0x4479a6 ADD $0x7,%RAX |
0x4479aa CMP %R14,%RAX |
0x4479ad JNE 44785d |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 298 |
-------------------------------------------------------------------------------- |
291: for (int jat = 0; jat < iLimit; jat++) |
292: { |
293: real_type r = distArray[jat]; |
294: if (r < cutoff_radius && iStart + jat != iat) |
295: { |
296: distIndices[iCount] = jat; |
297: distArrayCompressed[iCount] = r; |
298: iCount++; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►26.03+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:266 | exec |
○ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:312 | exec |
○ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | exec |
○ | main._omp_fn.1 | stl_vector.h:1126 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►26.03+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:266 | exec |
○ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:300 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:207 | exec |
○ | main._omp_fn.1 | miniqmc.cpp:438 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►24.66+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:266 | exec |
○ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:300 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:207 | exec |
○ | main._omp_fn.1 | miniqmc.cpp:438 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►13.70+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:266 | exec |
○ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:312 | exec |
○ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | exec |
○ | main._omp_fn.1 | stl_vector.h:1126 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►6.85+ | miniqmcreference::OneBodyJastr[...] | OneBodyJastrowRef.h:222 | exec |
○ | miniqmcreference::OneBodyJastr[...] | stl_vector.h:1123 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:207 | exec |
○ | main._omp_fn.1 | miniqmc.cpp:438 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►2.74+ | miniqmcreference::OneBodyJastr[...] | OneBodyJastrowRef.h:222 | exec |
○ | miniqmcreference::OneBodyJastr[...] | OneBodyJastrowRef.h:116 | exec |
○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:181 | exec |
○ | main._omp_fn.0 | miniqmc.cpp:390 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.55 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.66 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.38 |
Bottlenecks | micro-operation queue, |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:291-298 |
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 | 22.50 |
CQA cycles if no scalar integer | 14.50 |
CQA cycles if FP arith vectorized | 22.50 |
CQA cycles if fully vectorized | 1.78 |
Front-end cycles | 22.50 |
DIV/SQRT cycles | 16.25 |
P0 cycles | 16.25 |
P1 cycles | 8.50 |
P2 cycles | 8.17 |
P3 cycles | 16.00 |
P4 cycles | 16.25 |
P5 cycles | 16.25 |
P6 cycles | 8.33 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 22.64 |
Stall cycles (UFS) | 0.00 |
Nb insns | 91.00 |
Nb uops | 90.00 |
Nb loads | 9.00 |
Nb stores | 16.00 |
Nb stack references | 1.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 7.47 |
Bytes prefetched | 0.00 |
Bytes loaded | 72.00 |
Bytes stored | 96.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
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 | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 9.38 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 9.38 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 6.25 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 9.38 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.55 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.66 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.38 |
Bottlenecks | micro-operation queue, |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:291-298 |
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 | 22.50 |
CQA cycles if no scalar integer | 14.50 |
CQA cycles if FP arith vectorized | 22.50 |
CQA cycles if fully vectorized | 1.78 |
Front-end cycles | 22.50 |
DIV/SQRT cycles | 16.25 |
P0 cycles | 16.25 |
P1 cycles | 8.50 |
P2 cycles | 8.17 |
P3 cycles | 16.00 |
P4 cycles | 16.25 |
P5 cycles | 16.25 |
P6 cycles | 8.33 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 22.64 |
Stall cycles (UFS) | 0.00 |
Nb insns | 91.00 |
Nb uops | 90.00 |
Nb loads | 9.00 |
Nb stores | 16.00 |
Nb stack references | 1.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 7.47 |
Bytes prefetched | 0.00 |
Bytes loaded | 72.00 |
Bytes stored | 96.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
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 | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 9.38 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 9.38 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 6.25 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 9.38 |
Path / |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:291-298 |
Module | exec |
nb instructions | 91 |
nb uops | 90 |
loop length | 342 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 9 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 22.50 cycles |
front end | 22.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.25 | 16.25 | 8.50 | 8.17 | 16.00 | 16.25 | 16.25 | 8.33 |
cycles | 16.25 | 16.25 | 8.50 | 8.17 | 16.00 | 16.25 | 16.25 | 8.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 22.64 |
Stall cycles | 0.00 |
Front-end | 22.50 |
Dispatch | 16.25 |
Overall L1 | 22.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
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 | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 6% |
load | NA (no load vectorizable/vectorized instructions) |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 6% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 9% |
load | 12% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 9% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%R8,%RAX,8),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM10,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 447882 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%RAX,1),%R14D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R14D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 447882 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %EAX,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM10,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%R8,%RAX,8),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM11,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 4478aa | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%RAX,1),%R14D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R14D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4478aa | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %EAX,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM11,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM12,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 4478d3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4478d3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM12,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x2(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM13,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 4478fc | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4478fc | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM13,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x3(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM14,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 447925 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 447925 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM14,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x4(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM15,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 44794e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44794e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM15,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x5(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM4,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 447976 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 447976 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM4,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x6(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM2,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 44799e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44799e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM2,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x4e8(%RSP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x7,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R14,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 44785d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:291-298 |
Module | exec |
nb instructions | 91 |
nb uops | 90 |
loop length | 342 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 9 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 22.50 cycles |
front end | 22.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.25 | 16.25 | 8.50 | 8.17 | 16.00 | 16.25 | 16.25 | 8.33 |
cycles | 16.25 | 16.25 | 8.50 | 8.17 | 16.00 | 16.25 | 16.25 | 8.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 22.64 |
Stall cycles | 0.00 |
Front-end | 22.50 |
Dispatch | 16.25 |
Overall L1 | 22.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
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 | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 6% |
load | NA (no load vectorizable/vectorized instructions) |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 6% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 9% |
load | 12% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 9% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%R8,%RAX,8),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM10,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 447882 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%RAX,1),%R14D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R14D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 447882 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %EAX,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM10,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%R8,%RAX,8),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM11,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 4478aa | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%RAX,1),%R14D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R14D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4478aa | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %EAX,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM11,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM12,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 4478d3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4478d3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM12,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x2(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM13,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 4478fc | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4478fc | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM13,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x3(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM14,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 447925 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 447925 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM14,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x4(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM15,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 44794e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44794e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM15,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x5(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM4,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 447976 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 447976 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM4,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x6(%RAX),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R14,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD %XMM2,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JBE 44799e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RDX,%R14,1),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15D,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44799e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %ECX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,(%R10,%R15,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM2,(%RSI,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x4e8(%RSP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x7,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R14,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 44785d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |