Loop Id: 857 | Module: libparcsr_ls.so | Source: par_indepset.c:65-67 | Coverage: 0.01% |
---|
Loop Id: 857 | Module: libparcsr_ls.so | Source: par_indepset.c:65-67 | Coverage: 0.01% |
---|
0x46a10 VZEROUPPER |
0x46a13 CALL e110 <hypre_Rand@plt> |
0x46a18 VMOVUPD %XMM0,-0x40(%RBP) [1] |
0x46a1d CALL e110 <hypre_Rand@plt> |
0x46a22 VMOVUPD %XMM0,-0x90(%RBP) [1] |
0x46a2a CALL e110 <hypre_Rand@plt> |
0x46a2f VMOVUPD %XMM0,-0x60(%RBP) [1] |
0x46a34 CALL e110 <hypre_Rand@plt> |
0x46a39 VMOVUPD -0x40(%RBP),%XMM1 [1] |
0x46a3e VPUNPCKLQDQ -0x90(%RBP),%XMM1,%XMM1 [1] |
0x46a46 VMOVUPD -0x60(%RBP),%XMM2 [1] |
0x46a4b VPUNPCKLQDQ %XMM0,%XMM2,%XMM0 |
0x46a4f VINSERTF128 $0x1,%XMM0,%YMM1,%YMM0 |
0x46a55 VADDPD -0x20(%RBX),%YMM0,%YMM0 [2] |
0x46a5a VMOVUPD %YMM0,-0x20(%RBX) [2] |
0x46a5f VZEROUPPER |
0x46a62 CALL e110 <hypre_Rand@plt> |
0x46a67 VMOVUPD %XMM0,-0x40(%RBP) [1] |
0x46a6c CALL e110 <hypre_Rand@plt> |
0x46a71 VMOVUPD %XMM0,-0x90(%RBP) [1] |
0x46a79 CALL e110 <hypre_Rand@plt> |
0x46a7e VMOVUPD %XMM0,-0x60(%RBP) [1] |
0x46a83 CALL e110 <hypre_Rand@plt> |
0x46a88 VMOVUPD -0x40(%RBP),%XMM1 [1] |
0x46a8d VPUNPCKLQDQ -0x90(%RBP),%XMM1,%XMM1 [1] |
0x46a95 VMOVUPD -0x60(%RBP),%XMM2 [1] |
0x46a9a VPUNPCKLQDQ %XMM0,%XMM2,%XMM0 |
0x46a9e VINSERTF128 $0x1,%XMM0,%YMM1,%YMM0 |
0x46aa4 VADDPD (%RBX),%YMM0,%YMM0 [2] |
0x46aa8 VMOVUPD %YMM0,(%RBX) [2] |
0x46aac ADD $0x40,%RBX |
0x46ab0 DEC %R13 |
0x46ab3 JNE 46a10 |
/home/eoseret/qaas_runs_CPU_9468/171-716-5699/intel/AMG/build/AMG/AMG/parcsr_ls/par_indepset.c: 65 - 67 |
-------------------------------------------------------------------------------- |
65: for (i = 0; i < S_num_nodes; i++) |
66: { |
67: measure_array[i] += hypre_Rand(); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.22 |
CQA speedup if fully vectorized | 4.47 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.25 |
Bottlenecks | |
Function | hypre_BoomerAMGCoarsenPMIS |
Source | par_indepset.c:65-67 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 8 |
CQA cycles | 18.00 |
CQA cycles if no scalar integer | 18.00 |
CQA cycles if FP arith vectorized | 14.73 |
CQA cycles if fully vectorized | 4.02 |
Front-end cycles | 7.00 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 4.00 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 8.00 |
P4 cycles | 4.00 |
P5 cycles | 0.50 |
P6 cycles | 8.00 |
P7 cycles | 8.00 |
P8 cycles | 8.00 |
P9 cycles | 0.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 18 |
FE+BE cycles (UFS) | 14.15 |
Stall cycles (UFS) | 8.06 |
Nb insns | 33.00 |
Nb uops | 42.00 |
Nb loads | 8.00 |
Nb stores | 8.00 |
Nb stack references | 3.00 |
FLOP/cycle | 0.44 |
Nb FLOP add-sub | 8.00 |
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 | 17.78 |
Bytes prefetched | 0.00 |
Bytes loaded | 160.00 |
Bytes stored | 160.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 81.82 |
Vectorization ratio load | 75.00 |
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 | 50.00 |
Vector-efficiency ratio all | 27.27 |
Vector-efficiency ratio load | 28.13 |
Vector-efficiency ratio store | 31.25 |
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 | 18.75 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.22 |
CQA speedup if fully vectorized | 4.47 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.25 |
Bottlenecks | |
Function | hypre_BoomerAMGCoarsenPMIS |
Source | par_indepset.c:65-67 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 8 |
CQA cycles | 18.00 |
CQA cycles if no scalar integer | 18.00 |
CQA cycles if FP arith vectorized | 14.73 |
CQA cycles if fully vectorized | 4.02 |
Front-end cycles | 7.00 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 4.00 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 8.00 |
P4 cycles | 4.00 |
P5 cycles | 0.50 |
P6 cycles | 8.00 |
P7 cycles | 8.00 |
P8 cycles | 8.00 |
P9 cycles | 0.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 18 |
FE+BE cycles (UFS) | 14.15 |
Stall cycles (UFS) | 8.06 |
Nb insns | 33.00 |
Nb uops | 42.00 |
Nb loads | 8.00 |
Nb stores | 8.00 |
Nb stack references | 3.00 |
FLOP/cycle | 0.44 |
Nb FLOP add-sub | 8.00 |
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 | 17.78 |
Bytes prefetched | 0.00 |
Bytes loaded | 160.00 |
Bytes stored | 160.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 81.82 |
Vectorization ratio load | 75.00 |
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 | 50.00 |
Vector-efficiency ratio all | 27.27 |
Vector-efficiency ratio load | 28.13 |
Vector-efficiency ratio store | 31.25 |
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 | 18.75 |
Path / |
Function | hypre_BoomerAMGCoarsenPMIS |
Source file and lines | par_indepset.c:65-67 |
Module | libparcsr_ls.so |
nb instructions | 33 |
nb uops | 42 |
loop length | 169 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 7.00 cycles |
front end | 7.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 4.00 | 2.67 | 2.67 | 8.00 | 4.00 | 0.50 | 8.00 | 8.00 | 8.00 | 0.00 | 2.67 |
cycles | 0.50 | 4.00 | 2.67 | 2.67 | 8.00 | 4.00 | 0.50 | 8.00 | 8.00 | 8.00 | 0.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 18.00 |
FE+BE cycles | 14.15 |
Stall cycles | 8.06 |
RS full (events) | 5.91 |
SB full (events) | 5.85 |
Front-end | 7.00 |
Dispatch | 8.00 |
Data deps. | 18.00 |
Overall L1 | 18.00 |
all | 33% |
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) |
other | 33% |
all | 100% |
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 | 100% |
all | 81% |
load | 75% |
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% |
all | 16% |
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) |
other | 16% |
all | 31% |
load | 33% |
store | 31% |
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 | 25% |
all | 27% |
load | 28% |
store | 31% |
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 | 18% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VZEROUPPER | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x90(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x60(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD -0x40(%RBP),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPUNPCKLQDQ -0x90(%RBP),%XMM1,%XMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.50 |
VMOVUPD -0x60(%RBP),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPUNPCKLQDQ %XMM0,%XMM2,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VINSERTF128 $0x1,%XMM0,%YMM1,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPD -0x20(%RBX),%YMM0,%YMM0 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD %YMM0,-0x20(%RBX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VZEROUPPER | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x90(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x60(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD -0x40(%RBP),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPUNPCKLQDQ -0x90(%RBP),%XMM1,%XMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.50 |
VMOVUPD -0x60(%RBP),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPUNPCKLQDQ %XMM0,%XMM2,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VINSERTF128 $0x1,%XMM0,%YMM1,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPD (%RBX),%YMM0,%YMM0 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD %YMM0,(%RBX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
ADD $0x40,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 46a10 <hypre_BoomerAMGCoarsenPMIS+0x750> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_BoomerAMGCoarsenPMIS |
Source file and lines | par_indepset.c:65-67 |
Module | libparcsr_ls.so |
nb instructions | 33 |
nb uops | 42 |
loop length | 169 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 7.00 cycles |
front end | 7.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 4.00 | 2.67 | 2.67 | 8.00 | 4.00 | 0.50 | 8.00 | 8.00 | 8.00 | 0.00 | 2.67 |
cycles | 0.50 | 4.00 | 2.67 | 2.67 | 8.00 | 4.00 | 0.50 | 8.00 | 8.00 | 8.00 | 0.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 18.00 |
FE+BE cycles | 14.15 |
Stall cycles | 8.06 |
RS full (events) | 5.91 |
SB full (events) | 5.85 |
Front-end | 7.00 |
Dispatch | 8.00 |
Data deps. | 18.00 |
Overall L1 | 18.00 |
all | 33% |
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) |
other | 33% |
all | 100% |
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 | 100% |
all | 81% |
load | 75% |
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% |
all | 16% |
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) |
other | 16% |
all | 31% |
load | 33% |
store | 31% |
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 | 25% |
all | 27% |
load | 28% |
store | 31% |
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 | 18% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VZEROUPPER | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x90(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x60(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD -0x40(%RBP),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPUNPCKLQDQ -0x90(%RBP),%XMM1,%XMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.50 |
VMOVUPD -0x60(%RBP),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPUNPCKLQDQ %XMM0,%XMM2,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VINSERTF128 $0x1,%XMM0,%YMM1,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPD -0x20(%RBX),%YMM0,%YMM0 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD %YMM0,-0x20(%RBX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VZEROUPPER | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x90(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD %XMM0,-0x60(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CALL e110 <hypre_Rand@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVUPD -0x40(%RBP),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPUNPCKLQDQ -0x90(%RBP),%XMM1,%XMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.50 |
VMOVUPD -0x60(%RBP),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VPUNPCKLQDQ %XMM0,%XMM2,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VINSERTF128 $0x1,%XMM0,%YMM1,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPD (%RBX),%YMM0,%YMM0 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD %YMM0,(%RBX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
ADD $0x40,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 46a10 <hypre_BoomerAMGCoarsenPMIS+0x750> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |