Loop Id: 274 | Module: exec | Source: BsplineFunctor.h:236-241 | Coverage: 1.36% |
---|
Loop Id: 274 | Module: exec | Source: BsplineFunctor.h:236-241 | Coverage: 1.36% |
---|
0x418630 KMOVD %K1,%R11D |
0x418634 MOVZX %R11W,%R11D |
0x418638 POPCNT %R11D,%R11D |
0x41863d ADD %R11D,%ECX |
0x418640 ADD $0x10,%R15 |
0x418644 CMP %R10,%R15 |
0x418647 JAE 41874e |
0x41864d VMOVUPD (%R14,%R15,8),%YMM9 [5] |
0x418653 VMOVUPD 0x20(%R14,%R15,8),%YMM7 [5] |
0x41865a VMOVUPD 0x40(%R14,%R15,8),%YMM8 [5] |
0x418661 VMOVUPD 0x60(%R14,%R15,8),%YMM6 [5] |
0x418668 LEA (%RBX,%R15,1),%R12D |
0x41866c VPBROADCASTD %R12D,%YMM10 |
0x418672 VPADDD %YMM4,%YMM10,%YMM11 |
0x418676 VPADDD %YMM5,%YMM10,%YMM10 |
0x41867a VPCMPNEQD %YMM2,%YMM10,%K0 |
0x418681 VPCMPNEQD %YMM2,%YMM11,%K1 |
0x418688 KUNPCKBW %K0,%K1,%K0 |
0x41868c VCMPPD $0x1,%YMM3,%YMM9,%K1 |
0x418693 VCMPPD $0x1,%YMM3,%YMM7,%K2 |
0x41869a KSHIFTLB $0x4,%K2,%K2 |
0x4186a0 KORB %K2,%K1,%K1 |
0x4186a4 VCMPPD $0x1,%YMM3,%YMM8,%K2 |
0x4186ab VCMPPD $0x1,%YMM3,%YMM6,%K3 |
0x4186b2 KSHIFTLB $0x4,%K3,%K3 |
0x4186b8 KORB %K3,%K2,%K2 |
0x4186bc KUNPCKBW %K1,%K2,%K1 |
0x4186c0 KANDW %K0,%K1,%K1 |
0x4186c4 KORTESTW %K1,%K1 |
0x4186c8 JE 418630 |
0x4186ce MOVSXD %ECX,%R12 |
0x4186d1 LEA (%R9,%R12,8),%R13 |
0x4186d5 VCOMPRESSPD %YMM9,(%R9,%R12,8){%K1} [1] |
0x4186dc KSHIFTRW $0x8,%K1,%K2 |
0x4186e2 KMOVB %K1,%R12D |
0x4186e6 POPCNT %R12D,%R12D |
0x4186eb VCOMPRESSPD %YMM8,(%R13,%R12,8){%K2} [3] |
0x4186f3 KSHIFTLB $0x4,%K1,%K0 |
0x4186f9 KSHIFTRB $0x4,%K0,%K0 |
0x4186ff KMOVB %K0,-0x2a(%RBP) [6] |
0x418704 KSHIFTRB $0x4,%K1,%K3 |
0x41870a MOVZX -0x2a(%RBP),%R11D [6] |
0x41870f POPCNT %R11D,%R11D |
0x418714 VCOMPRESSPD %YMM7,(%R13,%R11,8){%K3} [2] |
0x41871c KSHIFTLB $0x4,%K2,%K0 |
0x418722 KSHIFTRB $0x4,%K0,%K0 |
0x418728 KMOVB %K0,-0x29(%RBP) [6] |
0x41872d LEA (%R13,%R12,8),%R11 |
0x418732 KSHIFTRB $0x4,%K2,%K2 |
0x418738 MOVZX -0x29(%RBP),%R12D [6] |
0x41873d POPCNT %R12D,%R12D |
0x418742 VCOMPRESSPD %YMM6,(%R11,%R12,8){%K2} [4] |
0x418749 JMP 418630 |
/scratch_na/users/xoserete/qaas_runs/171-284-5202/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 | 1.83 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.64 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.22 |
Bottlenecks | |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:236-241 |
Source loop unroll info | unrolled by 16 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 16 |
CQA cycles | 16.50 |
CQA cycles if no scalar integer | 9.00 |
CQA cycles if FP arith vectorized | 16.50 |
CQA cycles if fully vectorized | 4.53 |
Front-end cycles | 7.25 |
DIV/SQRT cycles | 5.50 |
P0 cycles | 4.50 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 1.50 |
P4 cycles | 16.50 |
P5 cycles | 3.20 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 3.30 |
P10 cycles | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 16.70 |
Stall cycles (UFS) | 8.53 |
Nb insns | 41.50 |
Nb uops | 43.50 |
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 | 12.53 |
Bytes prefetched | 0.00 |
Bytes loaded | 129.00 |
Bytes stored | 65.00 |
Stride 0 | 0.50 |
Stride 1 | 1.00 |
Stride n | 0.50 |
Stride unknown | 1.50 |
Stride indirect | 0.00 |
Vectorization ratio all | 84.44 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 66.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 80.36 |
Vector-efficiency ratio all | 43.19 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
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 | 41.41 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.85 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.56 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.44 |
Bottlenecks | P5, |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:236-241 |
Source loop unroll info | unrolled by 16 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 16 |
CQA cycles | 24.00 |
CQA cycles if no scalar integer | 13.00 |
CQA cycles if FP arith vectorized | 24.00 |
CQA cycles if fully vectorized | 6.75 |
Front-end cycles | 9.83 |
DIV/SQRT cycles | 6.00 |
P0 cycles | 6.00 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 3.00 |
P4 cycles | 24.00 |
P5 cycles | 3.40 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 3.60 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 24.20 |
Stall cycles (UFS) | 13.16 |
Nb insns | 53.00 |
Nb uops | 59.00 |
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 | 10.83 |
Bytes prefetched | 0.00 |
Bytes loaded | 130.00 |
Bytes stored | 130.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 3.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 88.89 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 66.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 85.71 |
Vector-efficiency ratio all | 45.14 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
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 | 43.75 |
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:236-241 |
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:236-241 |
Module | exec |
nb instructions | 41.50 |
nb uops | 43.50 |
loop length | 222 |
used x86 registers | 8.50 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 7.25 cycles |
front end | 7.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.50 | 4.50 | 1.67 | 1.67 | 1.50 | 16.50 | 3.20 | 1.50 | 1.50 | 1.50 | 3.30 | 1.67 |
cycles | 5.50 | 4.50 | 1.67 | 1.67 | 1.50 | 16.50 | 3.20 | 1.50 | 1.50 | 1.50 | 3.30 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 16.70 |
Stall cycles | 8.53 |
RS full (events) | 14.82 |
Front-end | 7.25 |
Dispatch | 16.50 |
Data deps. | 0.00 |
Overall L1 | 16.50 |
all | 61% |
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 | 58% |
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 | 84% |
load | 100% |
store | 100% |
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 | 80% |
all | 33% |
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 | 31% |
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 | 43% |
load | 50% |
store | 50% |
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 | 41% |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:236-241 |
Module | exec |
nb instructions | 53 |
nb uops | 59 |
loop length | 286 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 9.83 cycles |
front end | 9.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 6.00 | 6.00 | 2.00 | 2.00 | 3.00 | 24.00 | 3.40 | 3.00 | 3.00 | 3.00 | 3.60 | 2.00 |
cycles | 6.00 | 6.00 | 2.00 | 2.00 | 3.00 | 24.00 | 3.40 | 3.00 | 3.00 | 3.00 | 3.60 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 24.20 |
Stall cycles | 13.17 |
RS full (events) | 22.42 |
Front-end | 9.83 |
Dispatch | 24.00 |
Data deps. | 0.00 |
Overall L1 | 24.00 |
all | 66% |
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 | 66% |
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 | 88% |
load | 100% |
store | 100% |
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 | 85% |
all | 35% |
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 | 35% |
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 | 45% |
load | 50% |
store | 50% |
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 | 43% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
KMOVD %K1,%R11D | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVZX %R11W,%R11D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
POPCNT %R11D,%R11D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %R11D,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD $0x10,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R10,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JAE 41874e <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0x18e> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VMOVUPD (%R14,%R15,8),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%R14,%R15,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%R14,%R15,8),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%R14,%R15,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
LEA (%RBX,%R15,1),%R12D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
VPBROADCASTD %R12D,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %YMM4,%YMM10,%YMM11 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPADDD %YMM5,%YMM10,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPCMPNEQD %YMM2,%YMM10,%K0 | |||||||||||||||
VPCMPNEQD %YMM2,%YMM11,%K1 | |||||||||||||||
KUNPCKBW %K0,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VCMPPD $0x1,%YMM3,%YMM9,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM3,%YMM7,%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,%YMM8,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM3,%YMM6,%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 418630 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0x70> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOVSXD %ECX,%R12 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
LEA (%R9,%R12,8),%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VCOMPRESSPD %YMM9,(%R9,%R12,8){%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,%R12D | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
POPCNT %R12D,%R12D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM8,(%R13,%R12,8){%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,-0x2a(%RBP) | 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 -0x2a(%RBP),%R11D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
POPCNT %R11D,%R11D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM7,(%R13,%R11,8){%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,-0x29(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
LEA (%R13,%R12,8),%R11 | 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 -0x29(%RBP),%R12D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
POPCNT %R12D,%R12D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %YMM6,(%R11,%R12,8){%K2} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 |
JMP 418630 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0x70> | 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:236-241 |
Module | exec |
nb instructions | 30 |
nb uops | 28 |
loop length | 158 |
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,%R11D | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVZX %R11W,%R11D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
POPCNT %R11D,%R11D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %R11D,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD $0x10,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R10,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JAE 41874e <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0x18e> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VMOVUPD (%R14,%R15,8),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%R14,%R15,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%R14,%R15,8),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%R14,%R15,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
LEA (%RBX,%R15,1),%R12D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
VPBROADCASTD %R12D,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDD %YMM4,%YMM10,%YMM11 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPADDD %YMM5,%YMM10,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPCMPNEQD %YMM2,%YMM10,%K0 | |||||||||||||||
VPCMPNEQD %YMM2,%YMM11,%K1 | |||||||||||||||
KUNPCKBW %K0,%K1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VCMPPD $0x1,%YMM3,%YMM9,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM3,%YMM7,%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,%YMM8,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%YMM3,%YMM6,%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 418630 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0x70> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |