Loop Id: 574 | Module: exec | Source: TwoBodyJastrowRef.h:386-389 | Coverage: 0.04% |
---|
Loop Id: 574 | Module: exec | Source: TwoBodyJastrowRef.h:386-389 | Coverage: 0.04% |
---|
0x446cbf VMOVSD (%RDI,%RAX,1),%XMM4 [3] |
0x446cc4 VADDSD (%R11,%RAX,1),%XMM4,%XMM3 [5] |
0x446cca VMOVSD %XMM3,(%RDI,%RAX,1) [3] |
0x446ccf VMOVSD (%RCX,%RAX,1),%XMM5 [1] |
0x446cd4 VSUBSD (%R14,%RAX,1),%XMM5,%XMM6 [2] |
0x446cda VFNMADD231SD (%RBX,%RAX,1),%XMM12,%XMM6 [4] |
0x446ce0 VMOVSD %XMM6,(%RCX,%RAX,1) [1] |
0x446ce5 VMOVSD 0x8(%RDI,%RAX,1),%XMM7 [3] |
0x446ceb VADDSD 0x8(%R11,%RAX,1),%XMM7,%XMM9 [5] |
0x446cf2 VMOVSD %XMM9,0x8(%RDI,%RAX,1) [3] |
0x446cf8 VMOVSD 0x8(%RCX,%RAX,1),%XMM0 [1] |
0x446cfe VSUBSD 0x8(%R14,%RAX,1),%XMM0,%XMM11 [2] |
0x446d05 VFNMADD231SD 0x8(%RBX,%RAX,1),%XMM12,%XMM11 [4] |
0x446d0c VMOVSD %XMM11,0x8(%RCX,%RAX,1) [1] |
0x446d12 VMOVSD 0x10(%RDI,%RAX,1),%XMM13 [3] |
0x446d18 VADDSD 0x10(%R11,%RAX,1),%XMM13,%XMM15 [5] |
0x446d1f VMOVSD %XMM15,0x10(%RDI,%RAX,1) [3] |
0x446d25 VMOVSD 0x10(%RCX,%RAX,1),%XMM10 [1] |
0x446d2b VSUBSD 0x10(%R14,%RAX,1),%XMM10,%XMM1 [2] |
0x446d32 VFNMADD231SD 0x10(%RBX,%RAX,1),%XMM12,%XMM1 [4] |
0x446d39 VMOVSD %XMM1,0x10(%RCX,%RAX,1) [1] |
0x446d3f VMOVSD 0x18(%RDI,%RAX,1),%XMM8 [3] |
0x446d45 VADDSD 0x18(%R11,%RAX,1),%XMM8,%XMM2 [5] |
0x446d4c VMOVSD %XMM2,0x18(%RDI,%RAX,1) [3] |
0x446d52 VMOVSD 0x18(%RCX,%RAX,1),%XMM14 [1] |
0x446d58 VSUBSD 0x18(%R14,%RAX,1),%XMM14,%XMM4 [2] |
0x446d5f VFNMADD231SD 0x18(%RBX,%RAX,1),%XMM12,%XMM4 [4] |
0x446d66 VMOVSD %XMM4,0x18(%RCX,%RAX,1) [1] |
0x446d6c VMOVSD 0x20(%RDI,%RAX,1),%XMM3 [3] |
0x446d72 VADDSD 0x20(%R11,%RAX,1),%XMM3,%XMM5 [5] |
0x446d79 VMOVSD %XMM5,0x20(%RDI,%RAX,1) [3] |
0x446d7f VMOVSD 0x20(%RCX,%RAX,1),%XMM6 [1] |
0x446d85 VSUBSD 0x20(%R14,%RAX,1),%XMM6,%XMM7 [2] |
0x446d8c VFNMADD231SD 0x20(%RBX,%RAX,1),%XMM12,%XMM7 [4] |
0x446d93 VMOVSD %XMM7,0x20(%RCX,%RAX,1) [1] |
0x446d99 VMOVSD 0x28(%RDI,%RAX,1),%XMM9 [3] |
0x446d9f VADDSD 0x28(%R11,%RAX,1),%XMM9,%XMM0 [5] |
0x446da6 VMOVSD %XMM0,0x28(%RDI,%RAX,1) [3] |
0x446dac VMOVSD 0x28(%RCX,%RAX,1),%XMM11 [1] |
0x446db2 VSUBSD 0x28(%R14,%RAX,1),%XMM11,%XMM13 [2] |
0x446db9 VFNMADD231SD 0x28(%RBX,%RAX,1),%XMM12,%XMM13 [4] |
0x446dc0 VMOVSD %XMM13,0x28(%RCX,%RAX,1) [1] |
0x446dc6 VMOVSD 0x30(%RDI,%RAX,1),%XMM15 [3] |
0x446dcc VADDSD 0x30(%R11,%RAX,1),%XMM15,%XMM10 [5] |
0x446dd3 VMOVSD %XMM10,0x30(%RDI,%RAX,1) [3] |
0x446dd9 VMOVSD 0x30(%RCX,%RAX,1),%XMM1 [1] |
0x446ddf VSUBSD 0x30(%R14,%RAX,1),%XMM1,%XMM8 [2] |
0x446de6 VFNMADD231SD 0x30(%RBX,%RAX,1),%XMM12,%XMM8 [4] |
0x446ded VMOVSD %XMM8,0x30(%RCX,%RAX,1) [1] |
0x446df3 VMOVSD 0x38(%RDI,%RAX,1),%XMM2 [3] |
0x446df9 VADDSD 0x38(%R11,%RAX,1),%XMM2,%XMM14 [5] |
0x446e00 VMOVSD %XMM14,0x38(%RDI,%RAX,1) [3] |
0x446e06 VMOVSD 0x38(%RCX,%RAX,1),%XMM4 [1] |
0x446e0c VSUBSD 0x38(%R14,%RAX,1),%XMM4,%XMM3 [2] |
0x446e13 VFNMADD231SD 0x38(%RBX,%RAX,1),%XMM12,%XMM3 [4] |
0x446e1a VMOVSD %XMM3,0x38(%RCX,%RAX,1) [1] |
0x446e20 ADD $0x40,%RAX |
0x446e24 CMP %RAX,%R8 |
0x446e27 JNE 446cbf |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 386 - 389 |
-------------------------------------------------------------------------------- |
386: for (int jat = 0; jat < iat; jat++) |
387: { |
388: Uat[jat] += u[jat]; |
389: d2Uat[jat] -= d2u[jat] + lapfac * du[jat]; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:421 | 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 | 1.00 |
CQA speedup if FP arith vectorized | 1.02 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.02 |
Bottlenecks | micro-operation queue, |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | TwoBodyJastrowRef.h:386-389 |
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 | 20.50 |
CQA cycles if no scalar integer | 20.50 |
CQA cycles if FP arith vectorized | 20.00 |
CQA cycles if fully vectorized | 2.56 |
Front-end cycles | 20.50 |
DIV/SQRT cycles | 12.00 |
P0 cycles | 12.00 |
P1 cycles | 20.00 |
P2 cycles | 20.00 |
P3 cycles | 16.00 |
P4 cycles | 1.00 |
P5 cycles | 1.00 |
P6 cycles | 16.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 20.71 |
Stall cycles (UFS) | 0.00 |
Nb insns | 59.00 |
Nb uops | 58.00 |
Nb loads | 40.00 |
Nb stores | 16.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.56 |
Nb FLOP add-sub | 16.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 8.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 21.85 |
Bytes prefetched | 0.00 |
Bytes loaded | 320.00 |
Bytes stored | 128.00 |
Stride 0 | 0.00 |
Stride 1 | 5.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
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 | NA |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.02 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.02 |
Bottlenecks | micro-operation queue, |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | TwoBodyJastrowRef.h:386-389 |
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 | 20.50 |
CQA cycles if no scalar integer | 20.50 |
CQA cycles if FP arith vectorized | 20.00 |
CQA cycles if fully vectorized | 2.56 |
Front-end cycles | 20.50 |
DIV/SQRT cycles | 12.00 |
P0 cycles | 12.00 |
P1 cycles | 20.00 |
P2 cycles | 20.00 |
P3 cycles | 16.00 |
P4 cycles | 1.00 |
P5 cycles | 1.00 |
P6 cycles | 16.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 20.71 |
Stall cycles (UFS) | 0.00 |
Nb insns | 59.00 |
Nb uops | 58.00 |
Nb loads | 40.00 |
Nb stores | 16.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.56 |
Nb FLOP add-sub | 16.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 8.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 21.85 |
Bytes prefetched | 0.00 |
Bytes loaded | 320.00 |
Bytes stored | 128.00 |
Stride 0 | 0.00 |
Stride 1 | 5.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
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 | NA |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:386-389 |
Module | exec |
nb instructions | 59 |
nb uops | 58 |
loop length | 366 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 16 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 20.50 cycles |
front end | 20.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 12.00 | 12.00 | 20.00 | 20.00 | 16.00 | 1.00 | 1.00 | 16.00 |
cycles | 12.00 | 12.00 | 20.00 | 20.00 | 16.00 | 1.00 | 1.00 | 16.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 20.71 |
Stall cycles | 0.00 |
Front-end | 20.50 |
Dispatch | 20.00 |
Data deps. | 1.00 |
Overall L1 | 20.50 |
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 | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%RDI,%RAX,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD (%R11,%RAX,1),%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD (%RCX,%RAX,1),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD (%R14,%RAX,1),%XMM5,%XMM6 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD (%RBX,%RAX,1),%XMM12,%XMM6 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM6,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x8(%RDI,%RAX,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x8(%R11,%RAX,1),%XMM7,%XMM9 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,0x8(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x8(%RCX,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x8(%R14,%RAX,1),%XMM0,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x8(%RBX,%RAX,1),%XMM12,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,0x8(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x10(%RDI,%RAX,1),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x10(%R11,%RAX,1),%XMM13,%XMM15 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM15,0x10(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x10(%RCX,%RAX,1),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x10(%R14,%RAX,1),%XMM10,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x10(%RBX,%RAX,1),%XMM12,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM1,0x10(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x18(%RDI,%RAX,1),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x18(%R11,%RAX,1),%XMM8,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,0x18(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x18(%RCX,%RAX,1),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x18(%R14,%RAX,1),%XMM14,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x18(%RBX,%RAX,1),%XMM12,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM4,0x18(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x20(%RDI,%RAX,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x20(%R11,%RAX,1),%XMM3,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM5,0x20(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x20(%RCX,%RAX,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x20(%R14,%RAX,1),%XMM6,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x20(%RBX,%RAX,1),%XMM12,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM7,0x20(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x28(%RDI,%RAX,1),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x28(%R11,%RAX,1),%XMM9,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,0x28(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x28(%RCX,%RAX,1),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x28(%R14,%RAX,1),%XMM11,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x28(%RBX,%RAX,1),%XMM12,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM13,0x28(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x30(%RDI,%RAX,1),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x30(%R11,%RAX,1),%XMM15,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM10,0x30(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x30(%RCX,%RAX,1),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x30(%R14,%RAX,1),%XMM1,%XMM8 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x30(%RBX,%RAX,1),%XMM12,%XMM8 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM8,0x30(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x38(%RDI,%RAX,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x38(%R11,%RAX,1),%XMM2,%XMM14 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM14,0x38(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x38(%RCX,%RAX,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x38(%R14,%RAX,1),%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x38(%RBX,%RAX,1),%XMM12,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,0x38(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x40,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 446cbf | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:386-389 |
Module | exec |
nb instructions | 59 |
nb uops | 58 |
loop length | 366 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 16 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 20.50 cycles |
front end | 20.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 12.00 | 12.00 | 20.00 | 20.00 | 16.00 | 1.00 | 1.00 | 16.00 |
cycles | 12.00 | 12.00 | 20.00 | 20.00 | 16.00 | 1.00 | 1.00 | 16.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 20.71 |
Stall cycles | 0.00 |
Front-end | 20.50 |
Dispatch | 20.00 |
Data deps. | 1.00 |
Overall L1 | 20.50 |
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 | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%RDI,%RAX,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD (%R11,%RAX,1),%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD (%RCX,%RAX,1),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD (%R14,%RAX,1),%XMM5,%XMM6 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD (%RBX,%RAX,1),%XMM12,%XMM6 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM6,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x8(%RDI,%RAX,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x8(%R11,%RAX,1),%XMM7,%XMM9 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,0x8(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x8(%RCX,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x8(%R14,%RAX,1),%XMM0,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x8(%RBX,%RAX,1),%XMM12,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,0x8(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x10(%RDI,%RAX,1),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x10(%R11,%RAX,1),%XMM13,%XMM15 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM15,0x10(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x10(%RCX,%RAX,1),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x10(%R14,%RAX,1),%XMM10,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x10(%RBX,%RAX,1),%XMM12,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM1,0x10(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x18(%RDI,%RAX,1),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x18(%R11,%RAX,1),%XMM8,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,0x18(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x18(%RCX,%RAX,1),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x18(%R14,%RAX,1),%XMM14,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x18(%RBX,%RAX,1),%XMM12,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM4,0x18(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x20(%RDI,%RAX,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x20(%R11,%RAX,1),%XMM3,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM5,0x20(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x20(%RCX,%RAX,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x20(%R14,%RAX,1),%XMM6,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x20(%RBX,%RAX,1),%XMM12,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM7,0x20(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x28(%RDI,%RAX,1),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x28(%R11,%RAX,1),%XMM9,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,0x28(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x28(%RCX,%RAX,1),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x28(%R14,%RAX,1),%XMM11,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x28(%RBX,%RAX,1),%XMM12,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM13,0x28(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x30(%RDI,%RAX,1),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x30(%R11,%RAX,1),%XMM15,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM10,0x30(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x30(%RCX,%RAX,1),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x30(%R14,%RAX,1),%XMM1,%XMM8 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x30(%RBX,%RAX,1),%XMM12,%XMM8 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM8,0x30(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x38(%RDI,%RAX,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x38(%R11,%RAX,1),%XMM2,%XMM14 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM14,0x38(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x38(%RCX,%RAX,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x38(%R14,%RAX,1),%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD 0x38(%RBX,%RAX,1),%XMM12,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,0x38(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x40,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 446cbf | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |