Loop Id: 308 | Module: exec | Source: OneBodyJastrowRef.h:134-134 [...] | Coverage: 0.03% |
---|
Loop Id: 308 | Module: exec | Source: OneBodyJastrowRef.h:134-134 [...] | Coverage: 0.03% |
---|
0x422e80 KMOVD %K1,%ECX |
0x422e84 MOVZX %CX,%ECX |
0x422e87 POPCNT %ECX,%ECX |
0x422e8b ADD %ECX,%R10D |
0x422e8e ADD $0x10,%R13 |
0x422e92 CMP %R8,%R13 |
0x422e95 JAE 422fc0 |
0x422e9b VMOVUPD (%R15,%R13,8),%YMM7 [1] |
0x422ea1 VMOVUPD 0x20(%R15,%R13,8),%YMM5 [1] |
0x422ea8 VMOVUPD 0x40(%R15,%R13,8),%YMM6 [1] |
0x422eaf VMOVUPD 0x60(%R15,%R13,8),%YMM4 [1] |
0x422eb6 VMOVD %R13D,%XMM8 |
0x422ebb VPADDD %XMM2,%XMM8,%XMM8 |
0x422ebf VPBROADCASTD %XMM8,%YMM8 |
0x422ec4 VPCMPNEQD %YMM9,%YMM8,%K0 |
0x422ecb VPCMPNEQD %YMM10,%YMM8,%K1 |
0x422ed2 KUNPCKBW %K0,%K1,%K0 |
0x422ed6 VCMPPD $0x1,%YMM3,%YMM7,%K1 |
0x422edd VCMPPD $0x1,%YMM3,%YMM5,%K2 |
0x422ee4 KSHIFTLB $0x4,%K2,%K2 |
0x422eea KORB %K2,%K1,%K1 |
0x422eee VCMPPD $0x1,%YMM3,%YMM6,%K2 |
0x422ef5 VCMPPD $0x1,%YMM3,%YMM4,%K3 |
0x422efc KSHIFTLB $0x4,%K3,%K3 |
0x422f02 KORB %K3,%K2,%K2 |
0x422f06 KUNPCKBW %K1,%K2,%K1 |
0x422f0a KANDW %K0,%K1,%K1 |
0x422f0e KORTESTW %K1,%K1 |
0x422f12 JE 422e80 |
0x422f18 MOVSXD %R10D,%RBX |
0x422f1b LEA (%RSI,%RBX,8),%RDX |
0x422f1f VCOMPRESSPD %YMM7,(%RSI,%RBX,8){%K1} [2] |
0x422f26 KSHIFTRW $0x8,%K1,%K2 |
0x422f2c KMOVB %K1,%EBX |
0x422f30 POPCNT %EBX,%EBX |
0x422f34 VCOMPRESSPD %YMM6,(%RDX,%RBX,8){%K2} [5] |
0x422f3b KSHIFTLB $0x4,%K1,%K0 |
0x422f41 KSHIFTRB $0x4,%K0,%K0 |
0x422f47 KMOVB %K0,0x1f(%RSP) [6] |
0x422f4d KSHIFTRB $0x4,%K1,%K3 |
0x422f53 MOVZX 0x1f(%RSP),%ECX [6] |
0x422f58 POPCNT %ECX,%ECX |
0x422f5c VCOMPRESSPD %YMM5,(%RDX,%RCX,8){%K3} [3] |
0x422f63 KSHIFTLB $0x4,%K2,%K0 |
0x422f69 KSHIFTRB $0x4,%K0,%K0 |
0x422f6f KMOVB %K0,0x1e(%RSP) [6] |
0x422f75 LEA (%RDX,%RBX,8),%RCX |
0x422f79 KSHIFTRB $0x4,%K2,%K2 |
0x422f7f MOVZX 0x1e(%RSP),%EDX [6] |
0x422f84 POPCNT %EDX,%EDX |
0x422f88 VCOMPRESSPD %YMM4,(%RCX,%RDX,8){%K2} [4] |
0x422f8f JMP 422e80 |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 134 - 134 |
-------------------------------------------------------------------------------- |
134: for (int k = 0; k < ratios.size(); ++k) |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 236 - 241 |
-------------------------------------------------------------------------------- |
236: for (int jat = 0; jat < iLimit; jat++) |
237: { |
238: real_type r = distArray[jat]; |
239: // pick the distances smaller than the cutoff and avoid the reference atom |
240: if (r < cutoff_radius && iStart + jat != iat) |
241: distArrayCompressed[iCount++] = distArray[jat]; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::WaveFunction::eva[...] | stl_vector.h:806 | exec |
○ | qmcplusplus::NonLocalPP<double[...] | NonLocalPP.hpp:135 | exec |
○ | main.extracted.110 | NewTimer.h:249 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.75 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.81 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.39 |
Bottlenecks | |
Function | miniqmcreference::OneBodyJastrowRef |
Source | OneBodyJastrowRef.h:134-134,BsplineFunctor.h:236-241 |
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 | 17.50 |
CQA cycles if no scalar integer | 10.00 |
CQA cycles if FP arith vectorized | 17.50 |
CQA cycles if fully vectorized | 4.59 |
Front-end cycles | 7.08 |
DIV/SQRT cycles | 5.50 |
P0 cycles | 3.70 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 1.50 |
P4 cycles | 17.50 |
P5 cycles | 2.60 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 2.70 |
P10 cycles | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 17.68 |
Stall cycles (UFS) | 9.71 |
Nb insns | 40.50 |
Nb uops | 42.50 |
Nb loads | 5.00 |
Nb stores | 3.00 |
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 | 11.60 |
Bytes prefetched | 0.00 |
Bytes loaded | 129.00 |
Bytes stored | 65.00 |
Stride 0 | 0.50 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 1.50 |
Stride indirect | 0.50 |
Vectorization ratio all | 78.33 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 50.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 70.83 |
Vector-efficiency ratio all | 38.99 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 15.63 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 37.24 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.79 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.67 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.59 |
Bottlenecks | P5, |
Function | miniqmcreference::OneBodyJastrowRef |
Source | OneBodyJastrowRef.h:134-134,BsplineFunctor.h:236-241 |
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 | 25.00 |
CQA cycles if no scalar integer | 14.00 |
CQA cycles if FP arith vectorized | 25.00 |
CQA cycles if fully vectorized | 6.81 |
Front-end cycles | 9.67 |
DIV/SQRT cycles | 6.00 |
P0 cycles | 5.00 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 3.00 |
P4 cycles | 25.00 |
P5 cycles | 3.00 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 3.00 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 25.19 |
Stall cycles (UFS) | 14.35 |
Nb insns | 52.00 |
Nb uops | 58.00 |
Nb loads | 6.00 |
Nb stores | 6.00 |
Nb stack references | 2.00 |
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 | 10.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 130.00 |
Bytes stored | 130.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 3.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 83.33 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 50.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 75.00 |
Vector-efficiency ratio all | 41.32 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 15.63 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 39.06 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.67 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.21 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.00 |
Bottlenecks | P5, |
Function | miniqmcreference::OneBodyJastrowRef |
Source | OneBodyJastrowRef.h:134-134,BsplineFunctor.h:236-241 |
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 | 10.00 |
CQA cycles if no scalar integer | 6.00 |
CQA cycles if FP arith vectorized | 10.00 |
CQA cycles if fully vectorized | 2.38 |
Front-end cycles | 4.50 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 2.40 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 10.00 |
P5 cycles | 2.20 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 2.40 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 10.17 |
Stall cycles (UFS) | 5.06 |
Nb insns | 29.00 |
Nb uops | 27.00 |
Nb loads | 4.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
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 | 12.80 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 73.33 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 50.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 66.67 |
Vector-efficiency ratio all | 36.67 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 15.63 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 35.42 |
Path / |
Function | miniqmcreference::OneBodyJastrowRef |
Source file and lines | OneBodyJastrowRef.h:134-134 |
Module | exec |
nb instructions | 40.50 |
nb uops | 42.50 |
loop length | 214 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 8 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 7.08 cycles |
front end | 7.08 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.50 | 3.70 | 1.67 | 1.67 | 1.50 | 17.50 | 2.60 | 1.50 | 1.50 | 1.50 | 2.70 | 1.67 |
cycles | 5.50 | 3.70 | 1.67 | 1.67 | 1.50 | 17.50 | 2.60 | 1.50 | 1.50 | 1.50 | 2.70 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 17.68 |
Stall cycles | 9.71 |
RS full (events) | 15.87 |
Front-end | 7.08 |
Dispatch | 17.50 |
Data deps. | 0.00 |
Overall L1 | 17.50 |
all | 46% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 45% |
all | 100% |
load | 100% |
store | 100% |
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 | 100% |
all | 78% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 70% |
all | 22% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 25% |
all | 50% |
load | 50% |
store | 50% |
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 | 50% |
all | 38% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 37% |
Function | miniqmcreference::OneBodyJastrowRef |
Source file and lines | OneBodyJastrowRef.h:134-134 |
Module | exec |
nb instructions | 52 |
nb uops | 58 |
loop length | 276 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 8 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 9.67 cycles |
front end | 9.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 6.00 | 5.00 | 2.00 | 2.00 | 3.00 | 25.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 2.00 |
cycles | 6.00 | 5.00 | 2.00 | 2.00 | 3.00 | 25.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 25.19 |
Stall cycles | 14.35 |
RS full (events) | 22.53 |
Front-end | 9.67 |
Dispatch | 25.00 |
Data deps. | 0.00 |
Overall L1 | 25.00 |
all | 50% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 50% |
all | 100% |
load | 100% |
store | 100% |
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 | 100% |
all | 83% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 75% |
all | 23% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 28% |
all | 50% |
load | 50% |
store | 50% |
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 | 50% |
all | 41% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 39% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
KMOVD %K1,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVZX %CX,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
POPCNT %ECX,%ECX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %ECX,%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD $0x10,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R8,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JAE 422fc0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x340> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VMOVUPD (%R15,%R13,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%R15,%R13,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%R15,%R13,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%R15,%R13,8),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVD %R13D,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %XMM2,%XMM8,%XMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPBROADCASTD %XMM8,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPCMPNEQD %YMM9,%YMM8,%K0 | |||||||||||||||
VPCMPNEQD %YMM10,%YMM8,%K1 | |||||||||||||||
KUNPCKBW %K0,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VCMPPD $0x1,%YMM3,%YMM7,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM3,%YMM5,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
KSHIFTLB $0x4,%K2,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KORB %K2,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VCMPPD $0x1,%YMM3,%YMM6,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM3,%YMM4,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
KSHIFTLB $0x4,%K3,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KORB %K3,%K2,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KUNPCKBW %K1,%K2,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KANDW %K0,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTW %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JE 422e80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOVSXD %R10D,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
LEA (%RSI,%RBX,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VCOMPRESSPD %YMM7,(%RSI,%RBX,8){%K1} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
KSHIFTRW $0x8,%K1,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KMOVB %K1,%EBX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
POPCNT %EBX,%EBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM6,(%RDX,%RBX,8){%K2} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
KSHIFTLB $0x4,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KSHIFTRB $0x4,%K0,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KMOVB %K0,0x1f(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
KSHIFTRB $0x4,%K1,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
MOVZX 0x1f(%RSP),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
POPCNT %ECX,%ECX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM5,(%RDX,%RCX,8){%K3} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
KSHIFTLB $0x4,%K2,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KSHIFTRB $0x4,%K0,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KMOVB %K0,0x1e(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
LEA (%RDX,%RBX,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KSHIFTRB $0x4,%K2,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
MOVZX 0x1e(%RSP),%EDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
POPCNT %EDX,%EDX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM4,(%RCX,%RDX,8){%K2} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
JMP 422e80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x200> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | miniqmcreference::OneBodyJastrowRef |
Source file and lines | OneBodyJastrowRef.h:134-134 |
Module | exec |
nb instructions | 29 |
nb uops | 27 |
loop length | 152 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 8 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 4.50 cycles |
front end | 4.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 2.40 | 1.33 | 1.33 | 0.00 | 10.00 | 2.20 | 0.00 | 0.00 | 0.00 | 2.40 | 1.33 |
cycles | 5.00 | 2.40 | 1.33 | 1.33 | 0.00 | 10.00 | 2.20 | 0.00 | 0.00 | 0.00 | 2.40 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 10.17 |
Stall cycles | 5.06 |
RS full (events) | 9.21 |
Front-end | 4.50 |
Dispatch | 10.00 |
Data deps. | 0.00 |
Overall L1 | 10.00 |
all | 42% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 40% |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 100% |
all | 73% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 66% |
all | 21% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 23% |
all | 50% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 50% |
all | 36% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 35% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
KMOVD %K1,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVZX %CX,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
POPCNT %ECX,%ECX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %ECX,%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD $0x10,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R8,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JAE 422fc0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x340> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VMOVUPD (%R15,%R13,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%R15,%R13,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%R15,%R13,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%R15,%R13,8),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVD %R13D,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %XMM2,%XMM8,%XMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPBROADCASTD %XMM8,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPCMPNEQD %YMM9,%YMM8,%K0 | |||||||||||||||
VPCMPNEQD %YMM10,%YMM8,%K1 | |||||||||||||||
KUNPCKBW %K0,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VCMPPD $0x1,%YMM3,%YMM7,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM3,%YMM5,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
KSHIFTLB $0x4,%K2,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KORB %K2,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VCMPPD $0x1,%YMM3,%YMM6,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM3,%YMM4,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
KSHIFTLB $0x4,%K3,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KORB %K3,%K2,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KUNPCKBW %K1,%K2,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
KANDW %K0,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTW %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JE 422e80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |