Loop Id: 388 | Module: libparcsr_ls.so | Source: ams.c:3536-3538 | Coverage: 0.01% |
---|
Loop Id: 388 | Module: libparcsr_ls.so | Source: ams.c:3536-3538 | Coverage: 0.01% |
---|
0x1e800 VUCOMISD (%RDI,%RAX,1),%XMM3 [1] |
0x1e805 JE 1d200 |
0x1e80b VUCOMISD 0x8(%RDI,%RAX,1),%XMM3 [1] |
0x1e811 JE 1d200 |
0x1e817 ADD $0x10,%RAX |
0x1e81b DEC %RCX |
0x1e81e JNE 1e800 |
/home/eoseret/qaas_runs_CPU_9468/171-147-2675/intel/AMG/build/AMG/AMG/parcsr_ls/ams.c: 3536 - 3538 |
-------------------------------------------------------------------------------- |
3536: for (i = ns; i < ne; i++) |
3537: /* if (fabs(l1_norm[i]) < DBL_EPSILON) */ |
3538: if (fabs(l1_norm[i]) == 0.0) |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.88 |
Bottlenecks | P0, P6, |
Function | hypre_ParCSRComputeL1NormsThreads.extracted |
Source | ams.c:3536-3538 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.50 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 2.50 |
CQA cycles if fully vectorized | 0.31 |
Front-end cycles | 1.33 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 0.00 |
P1 cycles | 0.67 |
P2 cycles | 0.67 |
P3 cycles | 0.00 |
P4 cycles | 0.00 |
P5 cycles | 2.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.58 |
Stall cycles (UFS) | 0.69 |
Nb insns | 7.00 |
Nb uops | 8.00 |
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 | 6.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 16.00 |
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 | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.88 |
Bottlenecks | P0, P6, |
Function | hypre_ParCSRComputeL1NormsThreads.extracted |
Source | ams.c:3536-3538 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.50 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 2.50 |
CQA cycles if fully vectorized | 0.31 |
Front-end cycles | 1.33 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 0.00 |
P1 cycles | 0.67 |
P2 cycles | 0.67 |
P3 cycles | 0.00 |
P4 cycles | 0.00 |
P5 cycles | 2.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.58 |
Stall cycles (UFS) | 0.69 |
Nb insns | 7.00 |
Nb uops | 8.00 |
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 | 6.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 16.00 |
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 | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
Function | hypre_ParCSRComputeL1NormsThreads.extracted |
Source file and lines | ams.c:3536-3538 |
Module | libparcsr_ls.so |
nb instructions | 7 |
nb uops | 8 |
loop length | 32 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.33 cycles |
front end | 1.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 0.00 | 0.67 | 0.67 | 0.00 | 0.00 | 2.50 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
cycles | 2.50 | 0.00 | 0.67 | 0.67 | 0.00 | 0.00 | 2.50 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.58 |
Stall cycles | 0.69 |
RS full (events) | 1.50 |
Front-end | 1.33 |
Dispatch | 2.50 |
Data deps. | 1.00 |
Overall L1 | 2.50 |
all | 0% |
load | 0% |
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 | 0% |
all | 12% |
load | 12% |
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 | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VUCOMISD (%RDI,%RAX,1),%XMM3 | 2 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
JE 1d200 <hypre_ParCSRComputeL1NormsThreads.extracted+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VUCOMISD 0x8(%RDI,%RAX,1),%XMM3 | 2 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
JE 1d200 <hypre_ParCSRComputeL1NormsThreads.extracted+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
ADD $0x10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 1e800 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1800> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_ParCSRComputeL1NormsThreads.extracted |
Source file and lines | ams.c:3536-3538 |
Module | libparcsr_ls.so |
nb instructions | 7 |
nb uops | 8 |
loop length | 32 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.33 cycles |
front end | 1.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 0.00 | 0.67 | 0.67 | 0.00 | 0.00 | 2.50 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
cycles | 2.50 | 0.00 | 0.67 | 0.67 | 0.00 | 0.00 | 2.50 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.58 |
Stall cycles | 0.69 |
RS full (events) | 1.50 |
Front-end | 1.33 |
Dispatch | 2.50 |
Data deps. | 1.00 |
Overall L1 | 2.50 |
all | 0% |
load | 0% |
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 | 0% |
all | 12% |
load | 12% |
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 | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VUCOMISD (%RDI,%RAX,1),%XMM3 | 2 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
JE 1d200 <hypre_ParCSRComputeL1NormsThreads.extracted+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VUCOMISD 0x8(%RDI,%RAX,1),%XMM3 | 2 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
JE 1d200 <hypre_ParCSRComputeL1NormsThreads.extracted+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
ADD $0x10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 1e800 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1800> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |