Loop Id: 332 | Module: exec | Source: BsplineFunctor.h:291-297 | Coverage: 0.49% |
---|
Loop Id: 332 | Module: exec | Source: BsplineFunctor.h:291-297 | Coverage: 0.49% |
---|
0x425080 KMOVD %K1,%EAX |
0x425084 MOVZX %AX,%EAX |
0x425087 POPCNT %EAX,%EAX |
0x42508b ADD %EAX,%R14D |
0x42508e ADD $0x10,%R13 |
0x425092 CMP %RBX,%R13 |
0x425095 JAE 4251c0 |
0x42509b VMOVUPD (%R12,%R13,8),%YMM7 [4] |
0x4250a1 VMOVUPD 0x20(%R12,%R13,8),%YMM6 [4] |
0x4250a8 VMOVUPD 0x40(%R12,%R13,8),%YMM8 [4] |
0x4250af VMOVUPD 0x60(%R12,%R13,8),%YMM5 [4] |
0x4250b6 LEA (%R15,%R13,1),%R10D |
0x4250ba VPBROADCASTD %R10D,%YMM9 |
0x4250c0 VPADDD %YMM3,%YMM9,%YMM10 |
0x4250c4 VPADDD %YMM4,%YMM9,%YMM9 |
0x4250c8 VPCMPNEQD %YMM0,%YMM9,%K0 |
0x4250cf VPCMPNEQD %YMM0,%YMM10,%K1 |
0x4250d6 KUNPCKBW %K0,%K1,%K0 |
0x4250da VCMPPD $0x1,%YMM2,%YMM7,%K1 |
0x4250e1 VCMPPD $0x1,%YMM2,%YMM6,%K2 |
0x4250e8 KSHIFTLB $0x4,%K2,%K2 |
0x4250ee KORB %K2,%K1,%K1 |
0x4250f2 VCMPPD $0x1,%YMM2,%YMM8,%K2 |
0x4250f9 VCMPPD $0x1,%YMM2,%YMM5,%K3 |
0x425100 KSHIFTLB $0x4,%K3,%K3 |
0x425106 KORB %K3,%K2,%K2 |
0x42510a KUNPCKBW %K1,%K2,%K1 |
0x42510e KANDW %K0,%K1,%K1 |
0x425112 KORTESTW %K1,%K1 |
0x425116 JE 425080 |
0x42511c VPBROADCASTD %R13D,%YMM9 |
0x425122 VPADDD %YMM3,%YMM9,%YMM10 |
0x425126 VPADDD %YMM4,%YMM9,%YMM9 |
0x42512a MOVSXD %R14D,%R10 |
0x42512d MOV %R11,%R9 |
0x425130 LEA (%R11,%R10,4),%RAX |
0x425134 VPCOMPRESSD %YMM9,(%R11,%R10,4){%K1} [3] |
0x42513b KSHIFTRW $0x8,%K1,%K2 |
0x425141 KMOVB %K1,%R9D |
0x425145 POPCNT %R9D,%R9D |
0x42514a VPCOMPRESSD %YMM10,(%RAX,%R9,4){%K2} [7] |
0x425151 LEA (%R8,%R10,8),%RAX |
0x425155 VCOMPRESSPD %YMM8,(%RAX,%R9,8){%K2} [5] |
0x42515c VCOMPRESSPD %YMM7,(%R8,%R10,8){%K1} [2] |
0x425163 KSHIFTLB $0x4,%K1,%K0 |
0x425169 KSHIFTRB $0x4,%K0,%K0 |
0x42516f KMOVB %K0,0xe(%RSP) [8] |
0x425175 KSHIFTRB $0x4,%K1,%K3 |
0x42517b MOVZX 0xe(%RSP),%R10D [8] |
0x425181 POPCNT %R10D,%R10D |
0x425186 VCOMPRESSPD %YMM6,(%RAX,%R10,8){%K3} [6] |
0x42518d KSHIFTLB $0x4,%K2,%K0 |
0x425193 KSHIFTRB $0x4,%K0,%K0 |
0x425199 KMOVB %K0,0xf(%RSP) [8] |
0x42519f LEA (%RAX,%R9,8),%RAX |
0x4251a3 KSHIFTRB $0x4,%K2,%K2 |
0x4251a9 MOVZX 0xf(%RSP),%R9D [8] |
0x4251af POPCNT %R9D,%R9D |
0x4251b4 VCOMPRESSPD %YMM5,(%RAX,%R9,8){%K2} [1] |
0x4251bb JMP 425080 |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 297 |
-------------------------------------------------------------------------------- |
291: for (int jat = 0; jat < iLimit; jat++) |
292: { |
293: real_type r = distArray[jat]; |
294: if (r < cutoff_radius && iStart + jat != iat) |
295: { |
296: distIndices[iCount] = jat; |
297: distArrayCompressed[iCount] = r; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►53.68+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:274 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:201 | exec |
○ | main.extracted.110 | refwrap.h:313 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so | |
►37.31+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:274 | exec |
○ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | exec |
○ | main.extracted.110 | refwrap.h:313 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so | |
►8.22+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:274 | exec |
○ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:411 | exec |
○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:175 | exec |
○ | main.extracted.113 | miniqmc.cpp:397 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.65 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.42 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.28 |
Bottlenecks | |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:291-297 |
Source loop unroll info | unrolled by 16 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 16 |
CQA cycles | 19.00 |
CQA cycles if no scalar integer | 11.50 |
CQA cycles if FP arith vectorized | 19.00 |
CQA cycles if fully vectorized | 5.56 |
Front-end cycles | 8.17 |
DIV/SQRT cycles | 6.00 |
P0 cycles | 5.00 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 2.00 |
P4 cycles | 19.00 |
P5 cycles | 3.20 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 3.30 |
P10 cycles | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 19.17 |
Stall cycles (UFS) | 9.94 |
Nb insns | 45.00 |
Nb uops | 49.00 |
Nb loads | 5.00 |
Nb stores | 4.00 |
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 | 12.70 |
Bytes prefetched | 0.00 |
Bytes loaded | 129.00 |
Bytes stored | 97.00 |
Stride 0 | 0.50 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 1.50 |
Stride indirect | 0.00 |
Vectorization ratio all | 83.48 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 73.33 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 75.00 |
Vector-efficiency ratio all | 42.77 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 38.33 |
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 | 1.61 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.29 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.49 |
Bottlenecks | P5, |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:291-297 |
Source loop unroll info | unrolled by 16 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 16 |
CQA cycles | 29.00 |
CQA cycles if no scalar integer | 18.00 |
CQA cycles if FP arith vectorized | 29.00 |
CQA cycles if fully vectorized | 8.81 |
Front-end cycles | 11.67 |
DIV/SQRT cycles | 7.00 |
P0 cycles | 7.00 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 4.00 |
P4 cycles | 29.00 |
P5 cycles | 3.40 |
P6 cycles | 4.00 |
P7 cycles | 4.00 |
P8 cycles | 4.00 |
P9 cycles | 3.60 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 29.15 |
Stall cycles (UFS) | 15.98 |
Nb insns | 60.00 |
Nb uops | 70.00 |
Nb loads | 6.00 |
Nb stores | 8.00 |
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 | 11.17 |
Bytes prefetched | 0.00 |
Bytes loaded | 130.00 |
Bytes stored | 194.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 2.00 |
Stride unknown | 3.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 86.96 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 80.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 75.00 |
Vector-efficiency ratio all | 44.29 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 41.25 |
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 | 1.80 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.89 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.80 |
Bottlenecks | P5, |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:291-297 |
Source loop unroll info | unrolled by 16 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 16 |
CQA cycles | 9.00 |
CQA cycles if no scalar integer | 5.00 |
CQA cycles if FP arith vectorized | 9.00 |
CQA cycles if fully vectorized | 2.31 |
Front-end cycles | 4.67 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 3.00 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 9.00 |
P5 cycles | 3.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 3.00 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 9.19 |
Stall cycles (UFS) | 3.89 |
Nb insns | 30.00 |
Nb uops | 28.00 |
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 | 14.22 |
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 | 80.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 66.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 75.00 |
Vector-efficiency ratio all | 41.25 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 35.42 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 39.06 |
Path / |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:291-297 |
Module | exec |
nb instructions | 45 |
nb uops | 49 |
loop length | 238 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 8.17 cycles |
front end | 8.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 6.00 | 5.00 | 1.67 | 1.67 | 2.00 | 19.00 | 3.20 | 2.00 | 2.00 | 2.00 | 3.30 | 1.67 |
cycles | 6.00 | 5.00 | 1.67 | 1.67 | 2.00 | 19.00 | 3.20 | 2.00 | 2.00 | 2.00 | 3.30 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 19.17 |
Stall cycles | 9.94 |
RS full (events) | 17.31 |
Front-end | 8.17 |
Dispatch | 19.00 |
Data deps. | 0.00 |
Overall L1 | 19.00 |
all | 64% |
load | NA (no load vectorizable/vectorized instructions) |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 73% |
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 | 73% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 75% |
all | 34% |
load | NA (no load vectorizable/vectorized instructions) |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 38% |
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 | 38% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 39% |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:291-297 |
Module | exec |
nb instructions | 60 |
nb uops | 70 |
loop length | 320 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 11.67 cycles |
front end | 11.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 7.00 | 7.00 | 2.00 | 2.00 | 4.00 | 29.00 | 3.40 | 4.00 | 4.00 | 4.00 | 3.60 | 2.00 |
cycles | 7.00 | 7.00 | 2.00 | 2.00 | 4.00 | 29.00 | 3.40 | 4.00 | 4.00 | 4.00 | 3.60 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 29.15 |
Stall cycles | 15.99 |
RS full (events) | 27.41 |
Front-end | 11.67 |
Dispatch | 29.00 |
Data deps. | 0.00 |
Overall L1 | 29.00 |
all | 72% |
load | NA (no load vectorizable/vectorized instructions) |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 80% |
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 | 86% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 80% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 75% |
all | 38% |
load | NA (no load vectorizable/vectorized instructions) |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 41% |
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 | 44% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 41% |
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,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RBX,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JAE 4251c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VMOVUPD (%R12,%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(%R12,%R13,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%R12,%R13,8),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%R12,%R13,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
LEA (%R15,%R13,1),%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
VPBROADCASTD %R10D,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %YMM3,%YMM9,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPADDD %YMM4,%YMM9,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPCMPNEQD %YMM0,%YMM9,%K0 | |||||||||||||||
VPCMPNEQD %YMM0,%YMM10,%K1 | |||||||||||||||
KUNPCKBW %K0,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VCMPPD $0x1,%YMM2,%YMM7,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM2,%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,%YMM2,%YMM8,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM2,%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 425080 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xc0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VPBROADCASTD %R13D,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %YMM3,%YMM9,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPADDD %YMM4,%YMM9,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
MOVSXD %R14D,%R10 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV %R11,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
LEA (%R11,%R10,4),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VPCOMPRESSD %YMM9,(%R11,%R10,4){%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,%R9D | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
POPCNT %R9D,%R9D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPCOMPRESSD %YMM10,(%RAX,%R9,4){%K2} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
LEA (%R8,%R10,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VCOMPRESSPD %YMM8,(%RAX,%R9,8){%K2} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
VCOMPRESSPD %YMM7,(%R8,%R10,8){%K1} | 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 %K0,0xe(%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 0xe(%RSP),%R10D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
POPCNT %R10D,%R10D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM6,(%RAX,%R10,8){%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 %K0,0xf(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
LEA (%RAX,%R9,8),%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 0xf(%RSP),%R9D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
POPCNT %R9D,%R9D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM5,(%RAX,%R9,8){%K2} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
JMP 425080 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xc0> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:291-297 |
Module | exec |
nb instructions | 30 |
nb uops | 28 |
loop length | 156 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 4.67 cycles |
front end | 4.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 3.00 | 1.33 | 1.33 | 0.00 | 9.00 | 3.00 | 0.00 | 0.00 | 0.00 | 3.00 | 1.33 |
cycles | 5.00 | 3.00 | 1.33 | 1.33 | 0.00 | 9.00 | 3.00 | 0.00 | 0.00 | 0.00 | 3.00 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 9.19 |
Stall cycles | 3.89 |
RS full (events) | 7.21 |
Front-end | 4.67 |
Dispatch | 9.00 |
Data deps. | 0.00 |
Overall L1 | 9.00 |
all | 57% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 66% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 50% |
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 | 80% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 66% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 75% |
all | 31% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 35% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 28% |
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 | 41% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 35% |
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,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RBX,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JAE 4251c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VMOVUPD (%R12,%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(%R12,%R13,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%R12,%R13,8),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%R12,%R13,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
LEA (%R15,%R13,1),%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
VPBROADCASTD %R10D,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %YMM3,%YMM9,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPADDD %YMM4,%YMM9,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPCMPNEQD %YMM0,%YMM9,%K0 | |||||||||||||||
VPCMPNEQD %YMM0,%YMM10,%K1 | |||||||||||||||
KUNPCKBW %K0,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VCMPPD $0x1,%YMM2,%YMM7,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM2,%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,%YMM2,%YMM8,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM2,%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 425080 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xc0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |