Loop Id: 4338 | Module: exec | Source: csr_matvec.c:577-579 | Coverage: 0.12% |
---|
Loop Id: 4338 | Module: exec | Source: csr_matvec.c:577-579 | Coverage: 0.12% |
---|
0x4dfd20 VPBROADCASTQ %R11,%YMM5 |
0x4dfd26 VPADDQ %YMM1,%YMM5,%YMM5 |
0x4dfd2a VPMULLQ %YMM5,%YMM0,%YMM5 |
0x4dfd30 VPADDQ %YMM5,%YMM4,%YMM5 |
0x4dfd34 VXORPD %XMM6,%XMM6,%XMM6 |
0x4dfd38 KXNORW %K0,%K0,%K1 |
0x4dfd3c VGATHERQPD (%RBX,%YMM5,8),%YMM6{%K1} [1] |
0x4dfd43 VADDPD %YMM6,%YMM3,%YMM3 |
0x4dfd47 ADD $0x4,%R11 |
0x4dfd4b CMP %RSI,%R11 |
0x4dfd4e JLE 4dfd20 |
/home/eoseret/qaas_runs_CPU_9468/171-112-7443/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 577 - 579 |
-------------------------------------------------------------------------------- |
577: for (j = 0; j < num_threads; j++) |
578: { |
579: y_data[i] += y_data_expand[j*y_size + i]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.15 |
CQA speedup if FP arith vectorized | 1.12 |
CQA speedup if fully vectorized | 2.36 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | P1, |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source | csr_matvec.c:577-579 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 3.83 |
CQA cycles if no scalar integer | 3.33 |
CQA cycles if FP arith vectorized | 3.42 |
CQA cycles if fully vectorized | 1.63 |
Front-end cycles | 3.00 |
DIV/SQRT cycles | 3.50 |
P0 cycles | 3.83 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 3.67 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 4.46 - 87.63 |
Stall cycles (UFS) | 1.55 - 84.53 |
Nb insns | 11.00 |
Nb uops | 18.00 |
Nb loads | 1.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.04 |
Nb FLOP add-sub | 4.00 |
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 | 8.35 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 85.71 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 66.67 |
Vector-efficiency ratio all | 41.07 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 50.00 |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 29.17 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.15 |
CQA speedup if FP arith vectorized | 1.12 |
CQA speedup if fully vectorized | 2.36 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | P1, |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source | csr_matvec.c:577-579 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 3.83 |
CQA cycles if no scalar integer | 3.33 |
CQA cycles if FP arith vectorized | 3.42 |
CQA cycles if fully vectorized | 1.63 |
Front-end cycles | 3.00 |
DIV/SQRT cycles | 3.50 |
P0 cycles | 3.83 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 3.67 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 4.46 - 87.63 |
Stall cycles (UFS) | 1.55 - 84.53 |
Nb insns | 11.00 |
Nb uops | 18.00 |
Nb loads | 1.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.04 |
Nb FLOP add-sub | 4.00 |
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 | 8.35 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 85.71 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 66.67 |
Vector-efficiency ratio all | 41.07 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 50.00 |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 29.17 |
Path / |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source file and lines | csr_matvec.c:577-579 |
Module | exec |
nb instructions | 11 |
nb uops | 18 |
loop length | 48 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 6 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.00 cycles |
front end | 3.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.50 | 3.83 | 1.33 | 1.33 | 0.00 | 3.67 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
cycles | 3.50 | 3.83 | 1.33 | 1.33 | 0.00 | 3.67 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 4.46-87.63 |
Stall cycles | 1.55-84.52 |
RS full (events) | 3.72-0.32 |
Front-end | 3.00 |
Dispatch | 3.83 |
Data deps. | 3.00 |
Overall L1 | 3.83 |
all | 75% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 100% |
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 | 100% |
all | 85% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 66% |
all | 40% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 41% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 37% |
all | 41% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 29% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VPBROADCASTQ %R11,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDQ %YMM1,%YMM5,%YMM5 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPMULLQ %YMM5,%YMM0,%YMM5 | 5 | 1.50 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
VPADDQ %YMM5,%YMM4,%YMM5 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VXORPD %XMM6,%XMM6,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD (%RBX,%YMM5,8),%YMM6{%K1} | 5 | 1 | 1 | 1.33 | 1.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 1.33 | 0-29 | 2 |
VADDPD %YMM6,%YMM3,%YMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD $0x4,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 4dfd20 <hypre_CSRMatrixMatvecT.extracted.49+0x3d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source file and lines | csr_matvec.c:577-579 |
Module | exec |
nb instructions | 11 |
nb uops | 18 |
loop length | 48 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 6 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.00 cycles |
front end | 3.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.50 | 3.83 | 1.33 | 1.33 | 0.00 | 3.67 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
cycles | 3.50 | 3.83 | 1.33 | 1.33 | 0.00 | 3.67 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 4.46-87.63 |
Stall cycles | 1.55-84.52 |
RS full (events) | 3.72-0.32 |
Front-end | 3.00 |
Dispatch | 3.83 |
Data deps. | 3.00 |
Overall L1 | 3.83 |
all | 75% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 100% |
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 | 100% |
all | 85% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 66% |
all | 40% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 41% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 37% |
all | 41% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 29% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VPBROADCASTQ %R11,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDQ %YMM1,%YMM5,%YMM5 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPMULLQ %YMM5,%YMM0,%YMM5 | 5 | 1.50 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
VPADDQ %YMM5,%YMM4,%YMM5 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VXORPD %XMM6,%XMM6,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD (%RBX,%YMM5,8),%YMM6{%K1} | 5 | 1 | 1 | 1.33 | 1.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 1.33 | 0-29 | 2 |
VADDPD %YMM6,%YMM3,%YMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD $0x4,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 4dfd20 <hypre_CSRMatrixMatvecT.extracted.49+0x3d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |