Loop Id: 230 | Module: exec | Source: BsplineFunctor.h:236-241 | Coverage: 0.97% |
---|
Loop Id: 230 | Module: exec | Source: BsplineFunctor.h:236-241 | Coverage: 0.97% |
---|
0x41b8d0 VMOVDQA32 %ZMM10,%ZMM7{%K1} |
0x41b8d6 VEXTRACTI64X4 $0x1,%ZMM7,%YMM8 |
0x41b8dd VPADDD %ZMM8,%ZMM7,%ZMM7 |
0x41b8e3 VEXTRACTI128 $0x1,%YMM7,%XMM8 |
0x41b8e9 VPADDD %ZMM8,%ZMM7,%ZMM7 |
0x41b8ef VPSHUFD $-0x12,%XMM7,%XMM8 |
0x41b8f4 VPADDD %ZMM8,%ZMM7,%ZMM7 |
0x41b8fa VPSHUFD $0x55,%XMM7,%XMM8 |
0x41b8ff VPADDD %ZMM8,%ZMM7,%ZMM8 |
0x41b905 VPBLENDW $0x3,%XMM8,%XMM5,%XMM7 |
0x41b90b ADD $0x10,%RAX |
0x41b90f CMP %RCX,%RAX |
0x41b912 JAE 41b98d |
0x41b914 VMOVUPD (%R15,%RAX,8),%ZMM9 [1] |
0x41b91b VMOVUPD 0x40(%R15,%RAX,8),%ZMM8 [1] |
0x41b923 LEA (%R14,%RAX,1),%EBX |
0x41b927 VPBROADCASTD %EBX,%ZMM10 |
0x41b92d VPADDD %ZMM4,%ZMM10,%ZMM10 |
0x41b933 VCMPPD $0x1,%ZMM3,%ZMM9,%K0 |
0x41b93a VCMPPD $0x1,%ZMM3,%ZMM8,%K1 |
0x41b941 KUNPCKBW %K0,%K1,%K1 |
0x41b945 VPCMPNEQD %ZMM2,%ZMM10,%K1{%K1} |
0x41b94c KORTESTW %K1,%K1 |
0x41b950 VPXOR %XMM10,%XMM10,%XMM10 |
0x41b955 JE 41b8d0 |
0x41b95b VMOVD %XMM7,%EBX |
0x41b95f MOVSXD %EBX,%RBX |
0x41b962 LEA (%R9,%RBX,8),%R12 |
0x41b966 VCOMPRESSPD %ZMM9,(%R9,%RBX,8){%K1} [2] |
0x41b96d KSHIFTRW $0x8,%K1,%K2 |
0x41b973 KMOVB %K1,%EBX |
0x41b977 POPCNT %EBX,%EBX |
0x41b97b VCOMPRESSPD %ZMM8,(%R12,%RBX,8){%K2} [3] |
0x41b982 VPSUBD %ZMM6,%ZMM7,%ZMM10 |
0x41b988 JMP 41b8d0 |
/home/kcamus/qaas_runs/169-451-1869/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 |
---|---|---|---|
►96.55+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:130 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:219 | exec |
○ | main.extracted.104 | stl_vector.h:1126 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | main | miniqmc.cpp:404 | exec |
○ | __libc_init_first | libc.so.6 | |
►3.45+ | miniqmcreference::OneBodyJastr[...] | OneBodyJastrowRef.h:150 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:219 | exec |
○ | main.extracted.104 | stl_vector.h:1126 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | main | miniqmc.cpp:404 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.15 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.53 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.48 |
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 | 11.50 |
CQA cycles if no scalar integer | 10.00 |
CQA cycles if FP arith vectorized | 11.50 |
CQA cycles if fully vectorized | 7.53 |
Front-end cycles | 7.75 |
DIV/SQRT cycles | 7.50 |
P0 cycles | 3.50 |
P1 cycles | 1.17 |
P2 cycles | 1.17 |
P3 cycles | 1.00 |
P4 cycles | 11.50 |
P5 cycles | 3.50 |
P6 cycles | 0.67 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 12.15 |
Stall cycles (UFS) | 3.96 |
Nb insns | 30.00 |
Nb uops | 31.00 |
Nb loads | 2.00 |
Nb stores | 1.00 |
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 | 16.25 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 64.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.50 |
Stride unknown | 0.50 |
Stride indirect | 0.00 |
Vectorization ratio all | 92.68 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 87.12 |
Vector-efficiency ratio all | 71.67 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 100.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 50.90 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.17 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.46 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.47 |
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 | 14.00 |
CQA cycles if no scalar integer | 12.00 |
CQA cycles if FP arith vectorized | 14.00 |
CQA cycles if fully vectorized | 9.56 |
Front-end cycles | 9.50 |
DIV/SQRT cycles | 9.00 |
P0 cycles | 4.50 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 2.00 |
P4 cycles | 14.00 |
P5 cycles | 4.50 |
P6 cycles | 1.33 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 15.17 |
Stall cycles (UFS) | 5.19 |
Nb insns | 35.00 |
Nb uops | 38.00 |
Nb loads | 2.00 |
Nb stores | 2.00 |
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 | 18.29 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 128.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 90.91 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 83.33 |
Vector-efficiency ratio all | 72.16 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 100.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 48.96 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.13 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.64 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.50 |
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 | 8.00 |
CQA cycles if FP arith vectorized | 9.00 |
CQA cycles if fully vectorized | 5.50 |
Front-end cycles | 6.00 |
DIV/SQRT cycles | 6.00 |
P0 cycles | 2.50 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.00 |
P4 cycles | 9.00 |
P5 cycles | 2.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 9.14 |
Stall cycles (UFS) | 2.73 |
Nb insns | 25.00 |
Nb uops | 24.00 |
Nb loads | 2.00 |
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 | 94.44 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 90.91 |
Vector-efficiency ratio all | 71.18 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 100.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 52.84 |
Path / |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:236-241 |
Module | exec |
nb instructions | 30 |
nb uops | 31 |
loop length | 164 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 2 |
used zmm registers | 7.50 |
nb stack references | 0 |
micro-operation queue | 7.75 cycles |
front end | 7.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 7.50 | 3.50 | 1.17 | 1.17 | 1.00 | 11.50 | 3.50 | 0.67 |
cycles | 7.50 | 3.50 | 1.17 | 1.17 | 1.00 | 11.50 | 3.50 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 12.16 |
Stall cycles | 3.96 |
RS full (events) | 8.85 |
Front-end | 7.75 |
Dispatch | 11.50 |
Data deps. | 1.00 |
Overall L1 | 11.50 |
all | 90% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 84% |
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 | 92% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 87% |
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 | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 40% |
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 | 71% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:236-241 |
Module | exec |
nb instructions | 35 |
nb uops | 38 |
loop length | 189 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 2 |
used zmm registers | 8 |
nb stack references | 0 |
micro-operation queue | 9.50 cycles |
front end | 9.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 9.00 | 4.50 | 1.33 | 1.33 | 2.00 | 14.00 | 4.50 | 1.33 |
cycles | 9.00 | 4.50 | 1.33 | 1.33 | 2.00 | 14.00 | 4.50 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 15.17 |
Stall cycles | 5.19 |
RS full (events) | 11.32 |
Front-end | 9.50 |
Dispatch | 14.00 |
Data deps. | 1.00 |
Overall L1 | 14.00 |
all | 87% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 80% |
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 | 90% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 83% |
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 | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 38% |
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 | 72% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 48% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VMOVDQA32 %ZMM10,%ZMM7{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VEXTRACTI64X4 $0x1,%ZMM7,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDD %ZMM8,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VEXTRACTI128 $0x1,%YMM7,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDD %ZMM8,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSHUFD $-0x12,%XMM7,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDD %ZMM8,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSHUFD $0x55,%XMM7,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDD %ZMM8,%ZMM7,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPBLENDW $0x3,%XMM8,%XMM5,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
ADD $0x10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 41b98d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVUPD (%R15,%RAX,8),%ZMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMOVUPD 0x40(%R15,%RAX,8),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
LEA (%R14,%RAX,1),%EBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPBROADCASTD %EBX,%ZMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDD %ZMM4,%ZMM10,%ZMM10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VCMPPD $0x1,%ZMM3,%ZMM9,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%ZMM3,%ZMM8,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
KUNPCKBW %K0,%K1,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 4 | 1 |
VPCMPNEQD %ZMM2,%ZMM10,%K1{%K1} | |||||||||||
KORTESTW %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXOR %XMM10,%XMM10,%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JE 41b8d0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVD %XMM7,%EBX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
MOVSXD %EBX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R9,%RBX,8),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VCOMPRESSPD %ZMM9,(%R9,%RBX,8){%K1} | 3 | 0 | 0 | 0.33 | 0.33 | 1 | 2 | 0 | 0.33 | 3 | 2 |
KSHIFTRW $0x8,%K1,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 4 | 1 |
KMOVB %K1,%EBX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
POPCNT %EBX,%EBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VCOMPRESSPD %ZMM8,(%R12,%RBX,8){%K2} | 3 | 0 | 0 | 0.33 | 0.33 | 1 | 2 | 0 | 0.33 | 3 | 2 |
VPSUBD %ZMM6,%ZMM7,%ZMM10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 41b8d0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:236-241 |
Module | exec |
nb instructions | 25 |
nb uops | 24 |
loop length | 139 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 2 |
used zmm registers | 7 |
nb stack references | 0 |
micro-operation queue | 6.00 cycles |
front end | 6.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 6.00 | 2.50 | 1.00 | 1.00 | 0.00 | 9.00 | 2.50 | 0.00 |
cycles | 6.00 | 2.50 | 1.00 | 1.00 | 0.00 | 9.00 | 2.50 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 9.14 |
Stall cycles | 2.73 |
RS full (events) | 6.37 |
Front-end | 6.00 |
Dispatch | 9.00 |
Data deps. | 1.00 |
Overall L1 | 9.00 |
all | 92% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 88% |
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 | 94% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 90% |
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 | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 42% |
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 | 71% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 52% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VMOVDQA32 %ZMM10,%ZMM7{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VEXTRACTI64X4 $0x1,%ZMM7,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDD %ZMM8,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VEXTRACTI128 $0x1,%YMM7,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDD %ZMM8,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSHUFD $-0x12,%XMM7,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDD %ZMM8,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSHUFD $0x55,%XMM7,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDD %ZMM8,%ZMM7,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPBLENDW $0x3,%XMM8,%XMM5,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
ADD $0x10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 41b98d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVUPD (%R15,%RAX,8),%ZMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMOVUPD 0x40(%R15,%RAX,8),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
LEA (%R14,%RAX,1),%EBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPBROADCASTD %EBX,%ZMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDD %ZMM4,%ZMM10,%ZMM10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VCMPPD $0x1,%ZMM3,%ZMM9,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VCMPPD $0x1,%ZMM3,%ZMM8,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
KUNPCKBW %K0,%K1,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 4 | 1 |
VPCMPNEQD %ZMM2,%ZMM10,%K1{%K1} | |||||||||||
KORTESTW %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXOR %XMM10,%XMM10,%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JE 41b8d0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Metric | run_0 |
---|---|
Coverage (% app. time) | 0.97 |
Time (s) | 0.58 |
Instance Count | 367740 |
Iteration Count - min | 32 |
Iteration Count - avg | 138.67 |
Iteration Count - max | 192 |
Cycles per Iteration - min | 14.94 |
Cycles per Iteration - avg | 23.64 |
Cycles per Iteration - max | 759.24 |
Metric | Value |
---|---|
Bucket Coverage (% loop time) | 99.74 |
Instance Count | 367740 |
ORIG CPI:min | 19.97 |
ORIG CPI:med | 22.39 |
ORIG CPI:max | 38.94 |
DL1 CPI:min | 19.02 |
DL1 CPI:med | 19.58 |
DL1 CPI:max | 24.56 |
ORIG (min) / DL1 (min) | 1.05 |
ORIG (med) / DL1 (med) | 1.12 |
ORIG (max) / DL1 (max) | 1.97 |
Nb Iteration:min | 192 |
Nb Iteration:med | 192.00 |
Nb Iteration:max | 192 |
ORIG: min (cycles) | 668 |
ORIG: med (cycles) | 4154.00 |
ORIG: max (cycles) | 7476 |
DL1:min (cycles) | 638 |
DL1:med (cycles) | 3710.00 |
DL1:max (cycles) | 3798 |
Metric (average per iteration except for Time and Iteration Count) | ORIG | DL1 | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Min (Thread) | Med (Thread) | Avg (Thread) | Max (Thread) | Min (Instances) | Med (Instances) | Max (Instances) | Min (Thread) | Med (Thread) | Avg (Thread) | Max (Thread) | Min (Instances) | Med (Instances) | Max (Instances) | |
Time | 4154.00 | 4154.00 | 4154.00 | 4154.00 | 668.00 | 4154.00 | 7476.00 | 3710.00 | 3710.00 | 3710.00 | 3710.00 | 638.00 | 3710.00 | 3798.00 |
CPI MIN | 19.97 | 19.02 | ||||||||||||
CPI MED | 22.39 | 22.39 | 22.39 | 22.39 | 19.97 | 22.39 | 38.94 | 19.58 | 19.58 | 19.58 | 19.58 | 19.02 | 19.58 | 24.56 |
CPI AVG | 23.31 | 20.02 | ||||||||||||
CPI MAX | 38.94 | 24.56 | ||||||||||||
Iteration Count | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 | 192.00 |
ORIG | DL1 | Original Code |
---|---|---|
0x4f8986 VMOVDQA32 %ZMM10,%ZMM7{%K1} | 0x4f8d79 VMOVDQA32 %ZMM10,%ZMM7{%K1} | 0x41b8d0 VMOVDQA32 %ZMM10,%ZMM7{%K1} |
0x4f898c VEXTRACTI64X4 $0x1,%ZMM7,%YMM8 | 0x4f8d7f VEXTRACTI64X4 $0x1,%ZMM7,%YMM8 | 0x41b8d6 VEXTRACTI64X4 $0x1,%ZMM7,%YMM8 |
0x4f8993 VPADDD %ZMM8,%ZMM7,%ZMM7 | 0x4f8d86 VPADDD %ZMM8,%ZMM7,%ZMM7 | 0x41b8dd VPADDD %ZMM8,%ZMM7,%ZMM7 |
0x4f8999 VEXTRACTI128 $0x1,%YMM7,%XMM8 | 0x4f8d8c VEXTRACTI128 $0x1,%YMM7,%XMM8 | 0x41b8e3 VEXTRACTI128 $0x1,%YMM7,%XMM8 |
0x4f899f VPADDD %ZMM8,%ZMM7,%ZMM7 | 0x4f8d92 VPADDD %ZMM8,%ZMM7,%ZMM7 | 0x41b8e9 VPADDD %ZMM8,%ZMM7,%ZMM7 |
0x4f89a5 VPSHUFD $-0x12,%XMM7,%XMM8 | 0x4f8d98 VPSHUFD $-0x12,%XMM7,%XMM8 | 0x41b8ef VPSHUFD $-0x12,%XMM7,%XMM8 |
0x4f89aa VPADDD %ZMM8,%ZMM7,%ZMM7 | 0x4f8d9d VPADDD %ZMM8,%ZMM7,%ZMM7 | 0x41b8f4 VPADDD %ZMM8,%ZMM7,%ZMM7 |
0x4f89b0 VPSHUFD $0x55,%XMM7,%XMM8 | 0x4f8da3 VPSHUFD $0x55,%XMM7,%XMM8 | 0x41b8fa VPSHUFD $0x55,%XMM7,%XMM8 |
0x4f89b5 VPADDD %ZMM8,%ZMM7,%ZMM8 | 0x4f8da8 VPADDD %ZMM8,%ZMM7,%ZMM8 | 0x41b8ff VPADDD %ZMM8,%ZMM7,%ZMM8 |
0x4f89bb VPBLENDW $0x3,%XMM8,%XMM5,%XMM7 | 0x4f8dae VPBLENDW $0x3,%XMM8,%XMM5,%XMM7 | 0x41b905 VPBLENDW $0x3,%XMM8,%XMM5,%XMM7 |
0x4f89c1 ADD $0x10,%RAX | 0x4f8db4 ADD $0x10,%RAX | 0x41b90b ADD $0x10,%RAX |
0x4f89c5 CMP %RCX,%RAX | 0x4f8db8 CMP %RCX,%RAX | 0x41b90f CMP %RCX,%RAX |
0x4f89c8 JAE 4f8a4f <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0xdd1ef> | 0x4f8dbb JAE 4f8e45 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0xdd5e5> | 0x41b912 JAE 41b98d <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0x12d> |
0x4f89ce ADDQ $0x1,-0xc96(%RIP) 0x4f89d6 VMOVUPD (%R15,%RAX,8),%ZMM9 | 0x4f8dc1 VMOVUPD -0x314b(%RIP),%ZMM9 | 0x41b914 VMOVUPD (%R15,%RAX,8),%ZMM9 |
0x4f89dd VMOVUPD 0x40(%R15,%RAX,8),%ZMM8 | 0x4f8dcb VMOVUPD -0x3155(%RIP),%ZMM8 | 0x41b91b VMOVUPD 0x40(%R15,%RAX,8),%ZMM8 |
0x4f89e5 LEA (%R14,%RAX,1),%EBX | 0x4f8dd5 LEA (%R14,%RAX,1),%EBX | 0x41b923 LEA (%R14,%RAX,1),%EBX |
0x4f89e9 VPBROADCASTD %EBX,%ZMM10 | 0x4f8dd9 VPBROADCASTD %EBX,%ZMM10 | 0x41b927 VPBROADCASTD %EBX,%ZMM10 |
0x4f89ef VPADDD %ZMM4,%ZMM10,%ZMM10 | 0x4f8ddf VPADDD %ZMM4,%ZMM10,%ZMM10 | 0x41b92d VPADDD %ZMM4,%ZMM10,%ZMM10 |
0x4f89f5 VCMPPD $0x1,%ZMM3,%ZMM9,%K0 | 0x4f8de5 VCMPPD $0x1,%ZMM3,%ZMM9,%K0 | 0x41b933 VCMPPD $0x1,%ZMM3,%ZMM9,%K0 |
0x4f89fc VCMPPD $0x1,%ZMM3,%ZMM8,%K1 | 0x4f8dec VCMPPD $0x1,%ZMM3,%ZMM8,%K1 | 0x41b93a VCMPPD $0x1,%ZMM3,%ZMM8,%K1 |
0x4f8a03 KUNPCKBW %K0,%K1,%K1 | 0x4f8df3 KUNPCKBW %K0,%K1,%K1 | 0x41b941 KUNPCKBW %K0,%K1,%K1 |
0x4f8a07 VPCMPNEQD %ZMM2,%ZMM10,%K1{%K1} | 0x4f8df7 VPCMPNEQD %ZMM2,%ZMM10,%K1{%K1} | 0x41b945 VPCMPNEQD %ZMM2,%ZMM10,%K1{%K1} |
0x4f8a0e KORTESTW %K1,%K1 | 0x4f8dfe KORTESTW %K1,%K1 | 0x41b94c KORTESTW %K1,%K1 |
0x4f8a12 VPXOR %XMM10,%XMM10,%XMM10 | 0x4f8e02 VPXOR %XMM10,%XMM10,%XMM10 | 0x41b950 VPXOR %XMM10,%XMM10,%XMM10 |
0x4f8a17 JE 4f8986 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0xdd126> | 0x4f8e07 JE 4f8d79 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0xdd519> | 0x41b955 JE 41b8d0 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0x70> |
0x4f8a1d VMOVD %XMM7,%EBX | 0x4f8e0d VMOVD %XMM7,%EBX | 0x41b95b VMOVD %XMM7,%EBX |
0x4f8a21 MOVSXD %EBX,%RBX | 0x4f8e11 MOVSXD %EBX,%RBX | 0x41b95f MOVSXD %EBX,%RBX |
0x4f8a24 LEA (%R9,%RBX,8),%R12 | 0x4f8e14 LEA (%R9,%RBX,8),%R12 | 0x41b962 LEA (%R9,%RBX,8),%R12 |
0x4f8a28 VCOMPRESSPD %ZMM9,(%R9,%RBX,8){%K1} | 0x4f8e18 VCOMPRESSPD %ZMM9,-0x3222(%RIP) | 0x41b966 VCOMPRESSPD %ZMM9,(%R9,%RBX,8){%K1} |
0x4f8a2f KSHIFTRW $0x8,%K1,%K2 | 0x4f8e22 KSHIFTRW $0x8,%K1,%K2 | 0x41b96d KSHIFTRW $0x8,%K1,%K2 |
0x4f8a35 KMOVB %K1,%EBX | 0x4f8e28 KMOVB %K1,%EBX | 0x41b973 KMOVB %K1,%EBX |
0x4f8a39 POPCNT %EBX,%EBX | 0x4f8e2c POPCNT %EBX,%EBX | 0x41b977 POPCNT %EBX,%EBX |
0x4f8a3d VCOMPRESSPD %ZMM8,(%R12,%RBX,8){%K2} | 0x4f8e30 VCOMPRESSPD %ZMM8,-0x31fa(%RIP) | 0x41b97b VCOMPRESSPD %ZMM8,(%R12,%RBX,8){%K2} |
0x4f8a44 VPSUBD %ZMM6,%ZMM7,%ZMM10 | 0x4f8e3a VPSUBD %ZMM6,%ZMM7,%ZMM10 | 0x41b982 VPSUBD %ZMM6,%ZMM7,%ZMM10 |
0x4f8a4a JMP 4f8986 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0xdd126> | 0x4f8e40 JMP 4f8d79 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0xdd519> | 0x41b988 JMP 41b8d0 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd+0x70> |
Path / |
Metric | ORIG | DL1 | Original |
---|---|---|---|
FP operations per cycle L1 | 0.00, 0.00, | 0.00, 0.00, | 0.00, 0.00, |
cycles L1 CQA | 11.50 | 11.50 | 11.50 |
cycles UFS | 12.17 | 12.14 | 12.15 |
bytes loaded | 136.00 | 128.00 | 128.00 |
bytes stored | 72.00 | 64.00 | 64.00 |
nb loads | 3.00 | 2.00 | 2.00 |
nb stores | 2.00 | 1.00 | 1.00 |
cycles dispatch | 11.50 | 11.50 | 11.50 |
cycles front end | 8.25 | 7.75 | 7.75 |
cycles P0 | 7.50 | 7.50 | 7.50 |
cycles P1 | 4.00 | 3.50 | 3.50 |
cycles P2 | 1.83 | 1.17 | 1.17 |
cycles P3 | 1.67 | 1.17 | 1.17 |
cycles P4 | 2.00 | 1.00 | 1.00 |
cycles P5 | 11.50 | 11.50 | 11.50 |
cycles P6 | 4.00 | 3.50 | 3.50 |
cycles P7 | 1.50 | 0.67 | 0.67 |
stall cycles | 3.46 | 3.91 | 3.96 |
LB full | 0.00 | 0.00 | 0.00 |
LM full | 0.00 | 0.00 | 0.00 |
PRF full | 0.00 | 0.00 | 0.00 |
PRF_FLOAT full | 0.00 | 0.00 | 0.00 |
PRF_INT full | 0.00 | 0.00 | 0.00 |
ROB full | 0.00 | 2.30 | 0.00 |
RS full | 6.79 | 5.50 | 8.85 |
SB full | 0.00 | 0.00 | 0.00 |
nb uops | 33.00 | 31.00 | 31.00 |
uops P0 | 7.50 | 7.50 | 7.50 |
uops P1 | 4.00 | 3.50 | 3.50 |
uops P2 | 1.83 | 1.17 | 1.17 |
uops P3 | 1.67 | 1.17 | 1.17 |
uops P4 | 2.00 | 1.00 | 1.00 |
uops P5 | 11.50 | 11.50 | 11.50 |
uops P6 | 4.00 | 3.50 | 3.50 |
uops P7 | 1.50 | 0.67 | 0.67 |
ID | 231 | 234 | 230 |
Metric | ORIG | DL1 | Original |
---|---|---|---|
FP operations per cycle L1 | 0.00, 0.00, | 0.00, 0.00, | 0.00, 0.00, |
cycles L1 CQA | 14.00 | 14.00 | 14.00 |
cycles UFS | 15.18 | 15.15 | 15.17 |
bytes loaded | 136.00 | 128.00 | 128.00 |
bytes stored | 136.00 | 128.00 | 128.00 |
nb loads | 3.00 | 2.00 | 2.00 |
nb stores | 3.00 | 2.00 | 2.00 |
cycles dispatch | 14.00 | 14.00 | 14.00 |
cycles front end | 10.00 | 9.50 | 9.50 |
cycles P0 | 9.00 | 9.00 | 9.00 |
cycles P1 | 5.00 | 4.50 | 4.50 |
cycles P2 | 2.17 | 1.33 | 1.33 |
cycles P3 | 1.83 | 1.33 | 1.33 |
cycles P4 | 3.00 | 2.00 | 2.00 |
cycles P5 | 14.00 | 14.00 | 14.00 |
cycles P6 | 5.00 | 4.50 | 4.50 |
cycles P7 | 2.00 | 1.33 | 1.33 |
stall cycles | 4.68 | 5.09 | 5.19 |
LB full | 0.00 | 0.00 | 0.00 |
LM full | 0.00 | 0.00 | 0.00 |
PRF full | 0.00 | 0.00 | 0.00 |
PRF_FLOAT full | 0.00 | 0.00 | 0.00 |
PRF_INT full | 0.00 | 0.00 | 0.00 |
ROB full | 0.00 | 4.60 | 0.00 |
RS full | 9.55 | 4.63 | 11.32 |
SB full | 0.00 | 0.00 | 0.00 |
nb uops | 40.00 | 38.00 | 38.00 |
uops P0 | 9.00 | 9.00 | 9.00 |
uops P1 | 5.00 | 4.50 | 4.50 |
uops P2 | 2.17 | 1.33 | 1.33 |
uops P3 | 1.83 | 1.33 | 1.33 |
uops P4 | 3.00 | 2.00 | 2.00 |
uops P5 | 14.00 | 14.00 | 14.00 |
uops P6 | 5.00 | 4.50 | 4.50 |
uops P7 | 2.00 | 1.33 | 1.33 |
ID | 231 | 234 | 230 |
Metric | ORIG | DL1 | Original |
---|---|---|---|
FP operations per cycle L1 | 0.00, 0.00, | 0.00, 0.00, | 0.00, 0.00, |
cycles L1 CQA | 9.00 | 9.00 | 9.00 |
cycles UFS | 9.16 | 9.14 | 9.14 |
bytes loaded | 136.00 | 128.00 | 128.00 |
bytes stored | 8.00 | 0.00 | 0.00 |
nb loads | 3.00 | 2.00 | 2.00 |
nb stores | 1.00 | 0.00 | 0.00 |
cycles dispatch | 9.00 | 9.00 | 9.00 |
cycles front end | 6.50 | 6.00 | 6.00 |
cycles P0 | 6.00 | 6.00 | 6.00 |
cycles P1 | 3.00 | 2.50 | 2.50 |
cycles P2 | 1.50 | 1.00 | 1.00 |
cycles P3 | 1.50 | 1.00 | 1.00 |
cycles P4 | 1.00 | 0.00 | 0.00 |
cycles P5 | 9.00 | 9.00 | 9.00 |
cycles P6 | 3.00 | 2.50 | 2.50 |
cycles P7 | 1.00 | 0.00 | 0.00 |
stall cycles | 2.23 | 2.73 | 2.73 |
LB full | 0.00 | 0.00 | 0.00 |
LM full | 0.00 | 0.00 | 0.00 |
PRF full | 0.00 | 0.00 | 0.00 |
PRF_FLOAT full | 0.00 | 0.00 | 0.00 |
PRF_INT full | 0.00 | 0.00 | 0.00 |
ROB full | 0.00 | 0.00 | 0.00 |
RS full | 4.02 | 6.37 | 6.37 |
SB full | 0.00 | 0.00 | 0.00 |
nb uops | 26.00 | 24.00 | 24.00 |
uops P0 | 6.00 | 6.00 | 6.00 |
uops P1 | 3.00 | 2.50 | 2.50 |
uops P2 | 1.50 | 1.00 | 1.00 |
uops P3 | 1.50 | 1.00 | 1.00 |
uops P4 | 1.00 | 0.00 | 0.00 |
uops P5 | 9.00 | 9.00 | 9.00 |
uops P6 | 3.00 | 2.50 | 2.50 |
uops P7 | 1.00 | 0.00 | 0.00 |
ID | 231 | 234 | 230 |