Loop Id: 594 | Module: exec | Source: TwoBodyJastrowRef.h:340-345 | Coverage: 0.6% |
---|
Loop Id: 594 | Module: exec | Source: TwoBodyJastrowRef.h:340-345 | Coverage: 0.6% |
---|
0x449d8e VMOVSD (%RBX,%RAX,1),%XMM10 [3] |
0x449d93 VMOVSD (%RDX,%RAX,1),%XMM6 [2] |
0x449d98 VMOVSD (%RDI,%RAX,1),%XMM9 [5] |
0x449d9d VMOVSD (%RCX,%RAX,1),%XMM8 [6] |
0x449da2 VFMADD132SD (%RSI,%RAX,1),%XMM6,%XMM10 [7] |
0x449da8 VMOVSD 0x8(%RAX,%RDX,1),%XMM7 [1] |
0x449dae VMOVSD 0x10(%RAX,%RDX,1),%XMM14 [1] |
0x449db4 VMOVSD 0x20(%RAX,%RDX,1),%XMM6 [1] |
0x449dba VFNMADD231SD %XMM9,%XMM8,%XMM10 |
0x449dbf VFMADD132SD %XMM9,%XMM0,%XMM8 |
0x449dc4 VMOVSD 0x18(%RAX,%RDX,1),%XMM9 [1] |
0x449dca VMOVSD %XMM10,(%RDX,%RAX,1) [2] |
0x449dcf VMOVSD 0x8(%RBX,%RAX,1),%XMM11 [3] |
0x449dd5 VMOVSD 0x8(%RCX,%RAX,1),%XMM0 [6] |
0x449ddb VMOVSD 0x8(%RDI,%RAX,1),%XMM2 [5] |
0x449de1 VFMADD132SD 0x8(%RSI,%RAX,1),%XMM7,%XMM11 [7] |
0x449de8 VFMADD231SD %XMM2,%XMM0,%XMM8 |
0x449ded VFNMADD231SD %XMM2,%XMM0,%XMM11 |
0x449df2 VMOVSD %XMM11,0x8(%RAX,%RDX,1) [1] |
0x449df8 VMOVSD 0x10(%RBX,%RAX,1),%XMM3 [3] |
0x449dfe VMOVSD 0x10(%RCX,%RAX,1),%XMM12 [6] |
0x449e04 VMOVSD 0x10(%RDI,%RAX,1),%XMM13 [5] |
0x449e0a VFMADD132SD 0x10(%RSI,%RAX,1),%XMM14,%XMM3 [7] |
0x449e11 VFMADD231SD %XMM13,%XMM12,%XMM8 |
0x449e16 VFNMADD231SD %XMM13,%XMM12,%XMM3 |
0x449e1b VMOVSD %XMM3,0x10(%RAX,%RDX,1) [1] |
0x449e21 VMOVSD 0x18(%RBX,%RAX,1),%XMM4 [3] |
0x449e27 VMOVSD 0x18(%RCX,%RAX,1),%XMM15 [6] |
0x449e2d VMOVSD 0x18(%RDI,%RAX,1),%XMM5 [5] |
0x449e33 VFMADD132SD 0x18(%RSI,%RAX,1),%XMM9,%XMM4 [7] |
0x449e3a VFMADD231SD %XMM5,%XMM15,%XMM8 |
0x449e3f VFNMADD231SD %XMM5,%XMM15,%XMM4 |
0x449e44 VMOVSD %XMM4,0x18(%RAX,%RDX,1) [1] |
0x449e4a VMOVSD 0x20(%RBX,%RAX,1),%XMM2 [3] |
0x449e50 VMOVSD 0x20(%RDI,%RAX,1),%XMM0 [5] |
0x449e56 VMOVSD 0x20(%RCX,%RAX,1),%XMM10 [6] |
0x449e5c VFMADD132SD 0x20(%RSI,%RAX,1),%XMM6,%XMM2 [7] |
0x449e63 VFMADD231SD %XMM0,%XMM10,%XMM8 |
0x449e68 VFNMADD231SD %XMM0,%XMM10,%XMM2 |
0x449e6d VMOVSD %XMM2,0x20(%RAX,%RDX,1) [1] |
0x449e73 VMOVSD 0x28(%RCX,%RAX,1),%XMM11 [6] |
0x449e79 VMOVSD 0x28(%RDI,%RAX,1),%XMM12 [5] |
0x449e7f VMOVSD 0x28(%RBX,%RAX,1),%XMM13 [3] |
0x449e85 VMOVSD 0x28(%RAX,%RDX,1),%XMM7 [1] |
0x449e8b VMOVSD 0x30(%RAX,%RDX,1),%XMM15 [1] |
0x449e91 VMOVSD 0x38(%RAX,%RDX,1),%XMM9 [1] |
0x449e97 VFMADD231SD %XMM12,%XMM11,%XMM8 |
0x449e9c VFMADD132SD 0x28(%RSI,%RAX,1),%XMM7,%XMM13 [7] |
0x449ea3 VFNMADD231SD %XMM12,%XMM11,%XMM13 |
0x449ea8 VMOVSD %XMM13,0x28(%RAX,%RDX,1) [1] |
0x449eae VMOVSD 0x30(%RBX,%RAX,1),%XMM3 [3] |
0x449eb4 VMOVSD 0x30(%RCX,%RAX,1),%XMM0 [6] |
0x449eba VMOVSD 0x30(%RDI,%RAX,1),%XMM14 [5] |
0x449ec0 VFMADD132SD 0x30(%RSI,%RAX,1),%XMM15,%XMM3 [7] |
0x449ec7 VFNMADD231SD %XMM14,%XMM0,%XMM3 |
0x449ecc VFMADD132SD %XMM14,%XMM8,%XMM0 |
0x449ed1 VMOVSD %XMM3,0x30(%RAX,%RDX,1) [1] |
0x449ed7 VMOVSD 0x38(%RBX,%RAX,1),%XMM4 [3] |
0x449edd VMOVSD 0x38(%RCX,%RAX,1),%XMM8 [6] |
0x449ee3 VMOVSD 0x38(%RDI,%RAX,1),%XMM5 [5] |
0x449ee9 VFMADD132SD 0x38(%RSI,%RAX,1),%XMM9,%XMM4 [7] |
0x449ef0 ADD $0x40,%RAX |
0x449ef4 VFMADD231SD %XMM5,%XMM8,%XMM0 |
0x449ef9 VFNMADD231SD %XMM5,%XMM8,%XMM4 |
0x449efe VMOVSD %XMM4,-0x8(%RAX,%RDX,1) [4] |
0x449f04 CMP %RAX,%R11 |
0x449f07 JNE 449d8e |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 340 - 345 |
-------------------------------------------------------------------------------- |
340: for (int jat = 0; jat < N; jat++) |
341: { |
342: const valT newg = cur_du_pt[jat] * new_dX[jat]; |
343: const valT dg = newg - old_du_pt[jat] * old_dX[jat]; |
344: save_g[jat] -= dg; |
345: cur_g += newg; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | 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 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.43 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.60 |
Bottlenecks | |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | TwoBodyJastrowRef.h:340-345 |
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 | 32.00 |
CQA cycles if no scalar integer | 32.00 |
CQA cycles if FP arith vectorized | 22.39 |
CQA cycles if fully vectorized | 4.00 |
Front-end cycles | 18.50 |
DIV/SQRT cycles | 12.00 |
P0 cycles | 12.00 |
P1 cycles | 20.00 |
P2 cycles | 20.00 |
P3 cycles | 8.00 |
P4 cycles | 1.00 |
P5 cycles | 1.00 |
P6 cycles | 8.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 32 |
FE+BE cycles (UFS) | 32.11 |
Stall cycles (UFS) | 13.29 |
Nb insns | 67.00 |
Nb uops | 66.00 |
Nb loads | 40.00 |
Nb stores | 8.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.50 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 24.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 12.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 320.00 |
Bytes stored | 64.00 |
Stride 0 | 0.00 |
Stride 1 | 4.00 |
Stride n | 2.00 |
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 | NA |
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 | NA |
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 | 1.43 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.60 |
Bottlenecks | |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | TwoBodyJastrowRef.h:340-345 |
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 | 32.00 |
CQA cycles if no scalar integer | 32.00 |
CQA cycles if FP arith vectorized | 22.39 |
CQA cycles if fully vectorized | 4.00 |
Front-end cycles | 18.50 |
DIV/SQRT cycles | 12.00 |
P0 cycles | 12.00 |
P1 cycles | 20.00 |
P2 cycles | 20.00 |
P3 cycles | 8.00 |
P4 cycles | 1.00 |
P5 cycles | 1.00 |
P6 cycles | 8.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 32 |
FE+BE cycles (UFS) | 32.11 |
Stall cycles (UFS) | 13.29 |
Nb insns | 67.00 |
Nb uops | 66.00 |
Nb loads | 40.00 |
Nb stores | 8.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.50 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 24.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 12.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 320.00 |
Bytes stored | 64.00 |
Stride 0 | 0.00 |
Stride 1 | 4.00 |
Stride n | 2.00 |
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 | NA |
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 | NA |
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:340-345 |
Module | exec |
nb instructions | 67 |
nb uops | 66 |
loop length | 383 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 15 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 18.50 cycles |
front end | 18.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 12.00 | 12.00 | 20.00 | 20.00 | 8.00 | 1.00 | 1.00 | 8.00 |
cycles | 12.00 | 12.00 | 20.00 | 20.00 | 8.00 | 1.00 | 1.00 | 8.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 32.00 |
FE+BE cycles | 32.11 |
Stall cycles | 13.29 |
LB full (events) | 17.72 |
Front-end | 18.50 |
Dispatch | 20.00 |
Data deps. | 32.00 |
Overall L1 | 32.00 |
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 | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
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 (%RBX,%RAX,1),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RDX,%RAX,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RDI,%RAX,1),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RAX,1),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD (%RSI,%RAX,1),%XMM6,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD 0x8(%RAX,%RDX,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x10(%RAX,%RDX,1),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x20(%RAX,%RDX,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFNMADD231SD %XMM9,%XMM8,%XMM10 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD %XMM9,%XMM0,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD 0x18(%RAX,%RDX,1),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM10,(%RDX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x8(%RBX,%RAX,1),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x8(%RCX,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x8(%RDI,%RAX,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x8(%RSI,%RAX,1),%XMM7,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM2,%XMM0,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM2,%XMM0,%XMM11 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,0x8(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x10(%RBX,%RAX,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x10(%RCX,%RAX,1),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x10(%RDI,%RAX,1),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x10(%RSI,%RAX,1),%XMM14,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM13,%XMM12,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM13,%XMM12,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,0x10(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x18(%RBX,%RAX,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x18(%RCX,%RAX,1),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x18(%RDI,%RAX,1),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x18(%RSI,%RAX,1),%XMM9,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM5,%XMM15,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM5,%XMM15,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM4,0x18(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x20(%RBX,%RAX,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x20(%RDI,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x20(%RCX,%RAX,1),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x20(%RSI,%RAX,1),%XMM6,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM0,%XMM10,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM0,%XMM10,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,0x20(%RAX,%RDX,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 |
VMOVSD 0x28(%RDI,%RAX,1),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x28(%RBX,%RAX,1),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x28(%RAX,%RDX,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x30(%RAX,%RDX,1),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x38(%RAX,%RDX,1),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD231SD %XMM12,%XMM11,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD 0x28(%RSI,%RAX,1),%XMM7,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM12,%XMM11,%XMM13 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM13,0x28(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x30(%RBX,%RAX,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x30(%RCX,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x30(%RDI,%RAX,1),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x30(%RSI,%RAX,1),%XMM15,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM14,%XMM0,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD %XMM14,%XMM8,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,0x30(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x38(%RBX,%RAX,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x38(%RCX,%RAX,1),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x38(%RDI,%RAX,1),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x38(%RSI,%RAX,1),%XMM9,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x40,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VFMADD231SD %XMM5,%XMM8,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM5,%XMM8,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM4,-0x8(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %RAX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 449d8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:340-345 |
Module | exec |
nb instructions | 67 |
nb uops | 66 |
loop length | 383 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 15 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 18.50 cycles |
front end | 18.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 12.00 | 12.00 | 20.00 | 20.00 | 8.00 | 1.00 | 1.00 | 8.00 |
cycles | 12.00 | 12.00 | 20.00 | 20.00 | 8.00 | 1.00 | 1.00 | 8.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 32.00 |
FE+BE cycles | 32.11 |
Stall cycles | 13.29 |
LB full (events) | 17.72 |
Front-end | 18.50 |
Dispatch | 20.00 |
Data deps. | 32.00 |
Overall L1 | 32.00 |
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 | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
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 (%RBX,%RAX,1),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RDX,%RAX,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RDI,%RAX,1),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RAX,1),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD (%RSI,%RAX,1),%XMM6,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD 0x8(%RAX,%RDX,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x10(%RAX,%RDX,1),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x20(%RAX,%RDX,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFNMADD231SD %XMM9,%XMM8,%XMM10 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD %XMM9,%XMM0,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD 0x18(%RAX,%RDX,1),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM10,(%RDX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x8(%RBX,%RAX,1),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x8(%RCX,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x8(%RDI,%RAX,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x8(%RSI,%RAX,1),%XMM7,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM2,%XMM0,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM2,%XMM0,%XMM11 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,0x8(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x10(%RBX,%RAX,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x10(%RCX,%RAX,1),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x10(%RDI,%RAX,1),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x10(%RSI,%RAX,1),%XMM14,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM13,%XMM12,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM13,%XMM12,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,0x10(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x18(%RBX,%RAX,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x18(%RCX,%RAX,1),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x18(%RDI,%RAX,1),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x18(%RSI,%RAX,1),%XMM9,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM5,%XMM15,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM5,%XMM15,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM4,0x18(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x20(%RBX,%RAX,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x20(%RDI,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x20(%RCX,%RAX,1),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x20(%RSI,%RAX,1),%XMM6,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM0,%XMM10,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM0,%XMM10,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,0x20(%RAX,%RDX,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 |
VMOVSD 0x28(%RDI,%RAX,1),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x28(%RBX,%RAX,1),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x28(%RAX,%RDX,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x30(%RAX,%RDX,1),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x38(%RAX,%RDX,1),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD231SD %XMM12,%XMM11,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD 0x28(%RSI,%RAX,1),%XMM7,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM12,%XMM11,%XMM13 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM13,0x28(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x30(%RBX,%RAX,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x30(%RCX,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x30(%RDI,%RAX,1),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x30(%RSI,%RAX,1),%XMM15,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM14,%XMM0,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD %XMM14,%XMM8,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,0x30(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x38(%RBX,%RAX,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x38(%RCX,%RAX,1),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x38(%RDI,%RAX,1),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD132SD 0x38(%RSI,%RAX,1),%XMM9,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x40,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VFMADD231SD %XMM5,%XMM8,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231SD %XMM5,%XMM8,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM4,-0x8(%RAX,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %RAX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 449d8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |