Loop Id: 396 | Module: exec | Source: TwoBodyJastrowRef.h:107-107 [...] | Coverage: 1.77% |
---|
Loop Id: 396 | Module: exec | Source: TwoBodyJastrowRef.h:107-107 [...] | Coverage: 1.77% |
---|
0x42acc0 KMOVD %K1,%EAX |
0x42acc4 MOVZX %AX,%EAX |
0x42acc7 POPCNT %EAX,%EAX |
0x42accb ADD %EAX,%R14D |
0x42acce ADD $0x10,%RSI |
0x42acd2 CMP %R10,%RSI |
0x42acd5 JAE 42ae00 |
0x42acdb VMOVUPD (%RBX,%RSI,8),%YMM8 [1] |
0x42ace0 VMOVUPD 0x20(%RBX,%RSI,8),%YMM6 [1] |
0x42ace6 VMOVUPD 0x40(%RBX,%RSI,8),%YMM7 [1] |
0x42acec VMOVUPD 0x60(%RBX,%RSI,8),%YMM5 [1] |
0x42acf2 VMOVD %ESI,%XMM9 |
0x42acf6 VPADDD %XMM3,%XMM9,%XMM9 |
0x42acfa VPBROADCASTD %XMM9,%YMM9 |
0x42acff VPADDD %YMM21,%YMM9,%YMM10 |
0x42ad05 VPADDD %YMM22,%YMM9,%YMM9 |
0x42ad0b VPCMPNEQD %YMM1,%YMM9,%K0 |
0x42ad12 VPCMPNEQD %YMM1,%YMM10,%K1 |
0x42ad19 KUNPCKBW %K0,%K1,%K0 |
0x42ad1d VCMPPD $0x1,%YMM4,%YMM8,%K1 |
0x42ad24 VCMPPD $0x1,%YMM4,%YMM6,%K2 |
0x42ad2b KSHIFTLB $0x4,%K2,%K2 |
0x42ad31 KORB %K2,%K1,%K1 |
0x42ad35 VCMPPD $0x1,%YMM4,%YMM7,%K2 |
0x42ad3c VCMPPD $0x1,%YMM4,%YMM5,%K3 |
0x42ad43 KSHIFTLB $0x4,%K3,%K3 |
0x42ad49 KORB %K3,%K2,%K2 |
0x42ad4d KUNPCKBW %K1,%K2,%K1 |
0x42ad51 KANDW %K0,%K1,%K1 |
0x42ad55 KORTESTW %K1,%K1 |
0x42ad59 JE 42acc0 |
0x42ad5f MOVSXD %R14D,%RDI |
0x42ad62 LEA (%RDX,%RDI,8),%RAX |
0x42ad66 VCOMPRESSPD %YMM8,(%RDX,%RDI,8){%K1} [2] |
0x42ad6d KSHIFTRW $0x8,%K1,%K2 |
0x42ad73 KMOVB %K1,%EDI |
0x42ad77 POPCNT %EDI,%EDI |
0x42ad7b VCOMPRESSPD %YMM7,(%RAX,%RDI,8){%K2} [4] |
0x42ad82 KSHIFTLB $0x4,%K1,%K0 |
0x42ad88 KSHIFTRB $0x4,%K0,%K0 |
0x42ad8e KMOVB %K0,0xf(%RSP) [5] |
0x42ad94 KSHIFTRB $0x4,%K1,%K3 |
0x42ad9a MOVZX 0xf(%RSP),%R8D [5] |
0x42ada0 POPCNT %R8D,%R8D |
0x42ada5 VCOMPRESSPD %YMM6,(%RAX,%R8,8){%K3} [6] |
0x42adac KSHIFTLB $0x4,%K2,%K0 |
0x42adb2 KSHIFTRB $0x4,%K0,%K0 |
0x42adb8 KMOVB %K0,0xe(%RSP) [5] |
0x42adbe LEA (%RAX,%RDI,8),%RAX |
0x42adc2 KSHIFTRB $0x4,%K2,%K2 |
0x42adc8 MOVZX 0xe(%RSP),%EDI [5] |
0x42adcd POPCNT %EDI,%EDI |
0x42add1 VCOMPRESSPD %YMM5,(%RAX,%RDI,8){%K2} [3] |
0x42add8 JMP 42acc0 |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 107 - 107 |
-------------------------------------------------------------------------------- |
107: for (int k = 0; k < ratios.size(); ++k) |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/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]; |
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 | 2.33 |
Bottlenecks | |
Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
Source | TwoBodyJastrowRef.h:107-107,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 | 7.42 |
DIV/SQRT cycles | 5.67 |
P0 cycles | 5.33 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 1.50 |
P4 cycles | 17.50 |
P5 cycles | 2.70 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 2.80 |
P10 cycles | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 17.68 |
Stall cycles (UFS) | 9.38 |
Nb insns | 42.50 |
Nb uops | 44.50 |
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 | 1.00 |
Stride indirect | 0.50 |
Vectorization ratio all | 80.74 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 75.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 70.83 |
Vector-efficiency ratio all | 40.21 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 32.81 |
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 | 2.50 |
Bottlenecks | P5, |
Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
Source | TwoBodyJastrowRef.h:107-107,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 | 10.00 |
DIV/SQRT cycles | 6.33 |
P0 cycles | 6.67 |
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) | 14.01 |
Nb insns | 54.00 |
Nb uops | 60.00 |
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 | 2.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 85.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 75.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 75.00 |
Vector-efficiency ratio all | 42.19 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 32.81 |
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 | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
Source | TwoBodyJastrowRef.h:107-107,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 | 4.83 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 4.00 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 10.00 |
P5 cycles | 2.40 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 2.60 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 10.17 |
Stall cycles (UFS) | 4.75 |
Nb insns | 31.00 |
Nb uops | 29.00 |
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 | 76.47 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 75.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 66.67 |
Vector-efficiency ratio all | 38.24 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 32.81 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 35.42 |
Path / |
Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
Source file and lines | TwoBodyJastrowRef.h:107-107 |
Module | exec |
nb instructions | 42.50 |
nb uops | 44.50 |
loop length | 222 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 7.42 cycles |
front end | 7.42 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.67 | 5.33 | 1.67 | 1.67 | 1.50 | 17.50 | 2.70 | 1.50 | 1.50 | 1.50 | 2.80 | 1.67 |
cycles | 5.67 | 5.33 | 1.67 | 1.67 | 1.50 | 17.50 | 2.70 | 1.50 | 1.50 | 1.50 | 2.80 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 17.68 |
Stall cycles | 9.38 |
RS full (events) | 16.35 |
Front-end | 7.42 |
Dispatch | 17.50 |
Data deps. | 0.00 |
Overall L1 | 17.50 |
all | 59% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 75% |
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 | 80% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 75% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 70% |
all | 29% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 32% |
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 | 40% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 32% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 37% |
Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
Source file and lines | TwoBodyJastrowRef.h:107-107 |
Module | exec |
nb instructions | 54 |
nb uops | 60 |
loop length | 285 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 10.00 cycles |
front end | 10.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 6.33 | 6.67 | 2.00 | 2.00 | 3.00 | 25.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 2.00 |
cycles | 6.33 | 6.67 | 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 | 14.01 |
RS full (events) | 23.49 |
Front-end | 10.00 |
Dispatch | 25.00 |
Data deps. | 0.00 |
Overall L1 | 25.00 |
all | 62% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 75% |
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 | 85% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 75% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 75% |
all | 30% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 32% |
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 | 42% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 32% |
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,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVZX %AX,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
POPCNT %EAX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %EAX,%R14D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD $0x10,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R10,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JAE 42ae00 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x380> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VMOVUPD (%RBX,%RSI,8),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%RBX,%RSI,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%RBX,%RSI,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%RBX,%RSI,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVD %ESI,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %XMM3,%XMM9,%XMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPBROADCASTD %XMM9,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %YMM21,%YMM9,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPADDD %YMM22,%YMM9,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPCMPNEQD %YMM1,%YMM9,%K0 | |||||||||||||||
VPCMPNEQD %YMM1,%YMM10,%K1 | |||||||||||||||
KUNPCKBW %K0,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VCMPPD $0x1,%YMM4,%YMM8,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM4,%YMM6,%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,%YMM4,%YMM7,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM4,%YMM5,%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 42acc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x240> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOVSXD %R14D,%RDI | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
LEA (%RDX,%RDI,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VCOMPRESSPD %YMM8,(%RDX,%RDI,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,%EDI | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
POPCNT %EDI,%EDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM7,(%RAX,%RDI,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 %K0,0xf(%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 0xf(%RSP),%R8D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
POPCNT %R8D,%R8D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM6,(%RAX,%R8,8){%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 %K0,0xe(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
LEA (%RAX,%RDI,8),%RAX | 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 0xe(%RSP),%EDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
POPCNT %EDI,%EDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM5,(%RAX,%RDI,8){%K2} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
JMP 42acc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x240> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
Source file and lines | TwoBodyJastrowRef.h:107-107 |
Module | exec |
nb instructions | 31 |
nb uops | 29 |
loop length | 159 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 4.83 cycles |
front end | 4.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 4.00 | 1.33 | 1.33 | 0.00 | 10.00 | 2.40 | 0.00 | 0.00 | 0.00 | 2.60 | 1.33 |
cycles | 5.00 | 4.00 | 1.33 | 1.33 | 0.00 | 10.00 | 2.40 | 0.00 | 0.00 | 0.00 | 2.60 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 10.17 |
Stall cycles | 4.75 |
RS full (events) | 9.21 |
Front-end | 4.83 |
Dispatch | 10.00 |
Data deps. | 0.00 |
Overall L1 | 10.00 |
all | 55% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 75% |
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 | 76% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 75% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 66% |
all | 27% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 32% |
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 | 38% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 32% |
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,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVZX %AX,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
POPCNT %EAX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %EAX,%R14D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD $0x10,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R10,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JAE 42ae00 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x380> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VMOVUPD (%RBX,%RSI,8),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%RBX,%RSI,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%RBX,%RSI,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%RBX,%RSI,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVD %ESI,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %XMM3,%XMM9,%XMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPBROADCASTD %XMM9,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %YMM21,%YMM9,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPADDD %YMM22,%YMM9,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPCMPNEQD %YMM1,%YMM9,%K0 | |||||||||||||||
VPCMPNEQD %YMM1,%YMM10,%K1 | |||||||||||||||
KUNPCKBW %K0,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VCMPPD $0x1,%YMM4,%YMM8,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM4,%YMM6,%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,%YMM4,%YMM7,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM4,%YMM5,%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 42acc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x240> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |