Loop Id: 383 | Module: libparcsr_mv.so | Source: par_csr_matop.c:3505-3608 [...] | Coverage: 0.06% |
---|
Loop Id: 383 | Module: libparcsr_mv.so | Source: par_csr_matop.c:3505-3608 [...] | Coverage: 0.06% |
---|
0x1caa0 VPCMPEQQ 0x20(%R15,%R14,8),%YMM0,%K0 [1] |
0x1caa8 VPCMPEQQ (%R15,%R14,8),%YMM0,%K1 [1] |
0x1caaf VPCMPEQQ 0x60(%R15,%R14,8),%YMM0,%K2 [1] |
0x1cab7 VPCMPEQQ 0x40(%R15,%R14,8),%YMM0,%K3 [1] |
0x1cabf KORB %K2,%K3,%K4 |
0x1cac3 KORB %K0,%K1,%K5 |
0x1cac7 KORTESTB %K4,%K5 |
0x1cacb JNE 1cb80 |
0x1cad1 ADD $0x10,%R14 |
0x1cad5 CMP %RBX,%R14 |
0x1cad8 JBE 1caa0 |
/home/eoseret/qaas_runs_CPU_9468/171-716-5699/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 3505 - 3608 |
-------------------------------------------------------------------------------- |
3505: if (send_map_elmts_A[j1] == ik) |
[...] |
3607: for (j1 = send_map_starts_A[jk]; j1 < send_map_starts_A[jk+1]; j1++) |
3608: if (send_map_elmts_A[j1] == ik) |
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 | 1.33 |
Bottlenecks | P5, |
Function | hypre_ParTMatmul.extracted |
Source | par_csr_matop.c:3505-3505,par_csr_matop.c:3607-3608 |
Source loop unroll info | unrolled by 16 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 16 |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 4.00 |
CQA cycles if fully vectorized | 2.00 |
Front-end cycles | 2.33 |
DIV/SQRT cycles | 3.00 |
P0 cycles | 0.00 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 4.00 |
P5 cycles | 2.00 |
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 | 1 |
FE+BE cycles (UFS) | 4.13 |
Stall cycles (UFS) | 1.11 |
Nb insns | 11.00 |
Nb uops | 14.00 |
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 | 32.00 |
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 | 100.00 |
Vectorization ratio load | 100.00 |
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 | 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 | NA |
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 | 1.33 |
Bottlenecks | P5, |
Function | hypre_ParTMatmul.extracted |
Source | par_csr_matop.c:3505-3505,par_csr_matop.c:3607-3608 |
Source loop unroll info | unrolled by 16 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 16 |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 4.00 |
CQA cycles if fully vectorized | 2.00 |
Front-end cycles | 2.33 |
DIV/SQRT cycles | 3.00 |
P0 cycles | 0.00 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.00 |
P4 cycles | 4.00 |
P5 cycles | 2.00 |
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 | 1 |
FE+BE cycles (UFS) | 4.13 |
Stall cycles (UFS) | 1.11 |
Nb insns | 11.00 |
Nb uops | 14.00 |
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 | 32.00 |
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 | 100.00 |
Vectorization ratio load | 100.00 |
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 | 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 | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 50.00 |
Path / |
Function | hypre_ParTMatmul.extracted |
Source file and lines | par_csr_matop.c:3505-3608 |
Module | libparcsr_mv.so |
nb instructions | 11 |
nb uops | 14 |
loop length | 58 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.33 cycles |
front end | 2.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.00 | 0.00 | 1.33 | 1.33 | 0.00 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
cycles | 3.00 | 0.00 | 1.33 | 1.33 | 0.00 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 4.13 |
Stall cycles | 1.11 |
RS full (events) | 2.02 |
Front-end | 2.33 |
Dispatch | 4.00 |
Data deps. | 1.00 |
Overall L1 | 4.00 |
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 | 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% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VPCMPEQQ 0x20(%R15,%R14,8),%YMM0,%K0 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
VPCMPEQQ (%R15,%R14,8),%YMM0,%K1 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
VPCMPEQQ 0x60(%R15,%R14,8),%YMM0,%K2 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
VPCMPEQQ 0x40(%R15,%R14,8),%YMM0,%K3 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
KORB %K2,%K3,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORB %K0,%K1,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTB %K4,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JNE 1cb80 <hypre_ParTMatmul.extracted+0xd40> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
ADD $0x10,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RBX,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 1caa0 <hypre_ParTMatmul.extracted+0xc60> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_ParTMatmul.extracted |
Source file and lines | par_csr_matop.c:3505-3608 |
Module | libparcsr_mv.so |
nb instructions | 11 |
nb uops | 14 |
loop length | 58 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.33 cycles |
front end | 2.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.00 | 0.00 | 1.33 | 1.33 | 0.00 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
cycles | 3.00 | 0.00 | 1.33 | 1.33 | 0.00 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 4.13 |
Stall cycles | 1.11 |
RS full (events) | 2.02 |
Front-end | 2.33 |
Dispatch | 4.00 |
Data deps. | 1.00 |
Overall L1 | 4.00 |
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 | 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% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VPCMPEQQ 0x20(%R15,%R14,8),%YMM0,%K0 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
VPCMPEQQ (%R15,%R14,8),%YMM0,%K1 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
VPCMPEQQ 0x60(%R15,%R14,8),%YMM0,%K2 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
VPCMPEQQ 0x40(%R15,%R14,8),%YMM0,%K3 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
KORB %K2,%K3,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORB %K0,%K1,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTB %K4,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JNE 1cb80 <hypre_ParTMatmul.extracted+0xd40> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
ADD $0x10,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RBX,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 1caa0 <hypre_ParTMatmul.extracted+0xc60> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |