Loop Id: 2497 | Module: exec | Source: par_strength.c:1261-1263 | Coverage: 0.03% |
---|
Loop Id: 2497 | Module: exec | Source: par_strength.c:1261-1263 | Coverage: 0.03% |
---|
0x48ee90 VMOVDQU (%R8,%R9,8),%YMM2 [1] |
0x48ee96 VPCMPGTQ %YMM1,%YMM2,%YMM2 |
0x48ee9b VPSUBQ %YMM2,%YMM0,%YMM0 |
0x48ee9f ADD $0x4,%R9 |
0x48eea3 CMP %RSI,%R9 |
0x48eea6 JBE 48ee90 |
/home/eoseret/qaas_runs_CPU_9468/171-112-7443/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 1261 - 1263 |
-------------------------------------------------------------------------------- |
1261: for (i = i_begin; i < i_end; i++) |
1262: { |
1263: if (CF_marker[i] > 0) num_coarse_private++; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.20 |
Bottlenecks | P5, |
Function | hypre_BoomerAMGCreate2ndS.extracted |
Source | par_strength.c:1261-1263 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 1.00 |
CQA cycles if no scalar integer | 1.00 |
CQA cycles if FP arith vectorized | 1.00 |
CQA cycles if fully vectorized | 0.50 |
Front-end cycles | 0.83 |
DIV/SQRT cycles | 0.83 |
P0 cycles | 0.67 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 0.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.10 - 1.12 |
Stall cycles (UFS) | 0.00 |
Nb insns | 6.00 |
Nb uops | 5.00 |
Nb loads | 1.00 |
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 | 32.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
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 | 100.00 |
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 | 100.00 |
Vector-efficiency ratio all | 50.00 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 50.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.20 |
Bottlenecks | P5, |
Function | hypre_BoomerAMGCreate2ndS.extracted |
Source | par_strength.c:1261-1263 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 1.00 |
CQA cycles if no scalar integer | 1.00 |
CQA cycles if FP arith vectorized | 1.00 |
CQA cycles if fully vectorized | 0.50 |
Front-end cycles | 0.83 |
DIV/SQRT cycles | 0.83 |
P0 cycles | 0.67 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 0.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.10 - 1.12 |
Stall cycles (UFS) | 0.00 |
Nb insns | 6.00 |
Nb uops | 5.00 |
Nb loads | 1.00 |
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 | 32.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
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 | 100.00 |
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 | 100.00 |
Vector-efficiency ratio all | 50.00 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 50.00 |
Path / |
Function | hypre_BoomerAMGCreate2ndS.extracted |
Source file and lines | par_strength.c:1261-1263 |
Module | exec |
nb instructions | 6 |
nb uops | 5 |
loop length | 24 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 3 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 0.83 cycles |
front end | 0.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.83 | 0.67 | 0.33 | 0.33 | 0.00 | 1.00 | 0.50 | 0.00 | 0.00 | 0.00 | 0.00 | 0.33 |
cycles | 0.83 | 0.67 | 0.33 | 0.33 | 0.00 | 1.00 | 0.50 | 0.00 | 0.00 | 0.00 | 0.00 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.10-1.12 |
Stall cycles | 0.00 |
Front-end | 0.83 |
Dispatch | 1.00 |
Data deps. | 1.00 |
Overall L1 | 1.00 |
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 | 50% |
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 | 50% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVDQU (%R8,%R9,8),%YMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPCMPGTQ %YMM1,%YMM2,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0-3 | 1 |
VPSUBQ %YMM2,%YMM0,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
ADD $0x4,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 48ee90 <hypre_BoomerAMGCreate2ndS.extracted+0x60> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_BoomerAMGCreate2ndS.extracted |
Source file and lines | par_strength.c:1261-1263 |
Module | exec |
nb instructions | 6 |
nb uops | 5 |
loop length | 24 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 3 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 0.83 cycles |
front end | 0.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.83 | 0.67 | 0.33 | 0.33 | 0.00 | 1.00 | 0.50 | 0.00 | 0.00 | 0.00 | 0.00 | 0.33 |
cycles | 0.83 | 0.67 | 0.33 | 0.33 | 0.00 | 1.00 | 0.50 | 0.00 | 0.00 | 0.00 | 0.00 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.10-1.12 |
Stall cycles | 0.00 |
Front-end | 0.83 |
Dispatch | 1.00 |
Data deps. | 1.00 |
Overall L1 | 1.00 |
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 | 50% |
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 | 50% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVDQU (%R8,%R9,8),%YMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPCMPGTQ %YMM1,%YMM2,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0-3 | 1 |
VPSUBQ %YMM2,%YMM0,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
ADD $0x4,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 48ee90 <hypre_BoomerAMGCreate2ndS.extracted+0x60> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |