Loop Id: 175 | Module: exec | Source: field_summary.cpp:81-82 | Coverage: 0.1% |
---|
Loop Id: 175 | Module: exec | Source: field_summary.cpp:81-82 | Coverage: 0.1% |
---|
0x42af00 LEA -0x1(%RCX),%RDX |
0x42af04 KANDW %K2,%K1,%K3 |
0x42af08 VPBROADCASTQ %RDX,%YMM19 |
0x42af0e VPADDQ %YMM19,%YMM17,%YMM20 |
0x42af14 KMOVQ %K3,%K4 |
0x42af19 VXORPD %XMM21,%XMM21,%XMM21 |
0x42af1f VGATHERQPD (%RBX,%YMM20,8),%YMM21{%K4} [2] |
0x42af26 VPADDQ %YMM19,%YMM18,%YMM19 |
0x42af2c KMOVQ %K3,%K4 |
0x42af31 VXORPD %XMM20,%XMM20,%XMM20 |
0x42af37 VGATHERQPD (%R15,%YMM19,8),%YMM20{%K4} [1] |
0x42af3e VMOVAPD %YMM21,%YMM9{%K3} |
0x42af44 VMULPD %YMM9,%YMM9,%YMM19 |
0x42af4a VMOVAPD %YMM20,%YMM7{%K3} |
0x42af50 VFMADD231PD %YMM7,%YMM7,%YMM19 |
0x42af56 VFMADD231PD %YMM24,%YMM19,%YMM15 |
0x42af5c VPBROADCASTQ %RCX,%YMM19 |
0x42af62 VMOVAPD %YMM15,%YMM16{%K2} |
0x42af68 VPCMPGTQ %YMM19,%YMM5,%K2{%K2} |
0x42af6e KANDW %K2,%K1,%K0 |
0x42af72 KMOVD %K0,%EDX |
0x42af76 INC %RCX |
0x42af79 TEST $0xf,%DL |
0x42af7c JNE 42af00 |
/scratch_na/users/xoserete/qaas_runs/171-415-4687/intel/CloverLeafCXX/build/CloverLeafCXX/src/omp/field_summary.cpp: 81 - 82 |
-------------------------------------------------------------------------------- |
81: for (int jv = j; jv <= j + 1; ++jv) { |
82: vsqrd += 0.25 * (field.xvel0(jv, kv) * field.xvel0(jv, kv) + field.yvel0(jv, kv) * field.yvel0(jv, kv)); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.45 |
CQA speedup if FP arith vectorized | 1.38 |
CQA speedup if fully vectorized | 2.95 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.08 |
Bottlenecks | P0, |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source | field_summary.cpp:81-82 |
Source loop unroll info | unrolled by 2 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 7.00 |
CQA cycles if no scalar integer | 4.83 |
CQA cycles if FP arith vectorized | 5.08 |
CQA cycles if fully vectorized | 2.38 |
Front-end cycles | 5.17 |
DIV/SQRT cycles | 7.00 |
P0 cycles | 6.50 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 0.00 |
P4 cycles | 5.50 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 4 |
FE+BE cycles (UFS) | 7.30 - 87.46 |
Stall cycles (UFS) | 2.23 - 82.12 |
Nb insns | 24.00 |
Nb uops | 31.00 |
Nb loads | 2.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.86 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 4.00 |
Nb FLOP fma | 8.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 9.14 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 86.67 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 80.00 |
Vector-efficiency ratio all | 41.67 |
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 | 50.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 37.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.45 |
CQA speedup if FP arith vectorized | 1.38 |
CQA speedup if fully vectorized | 2.95 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.08 |
Bottlenecks | P0, |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source | field_summary.cpp:81-82 |
Source loop unroll info | unrolled by 2 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 7.00 |
CQA cycles if no scalar integer | 4.83 |
CQA cycles if FP arith vectorized | 5.08 |
CQA cycles if fully vectorized | 2.38 |
Front-end cycles | 5.17 |
DIV/SQRT cycles | 7.00 |
P0 cycles | 6.50 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 0.00 |
P4 cycles | 5.50 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 4 |
FE+BE cycles (UFS) | 7.30 - 87.46 |
Stall cycles (UFS) | 2.23 - 82.12 |
Nb insns | 24.00 |
Nb uops | 31.00 |
Nb loads | 2.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.86 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 4.00 |
Nb FLOP fma | 8.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 9.14 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 86.67 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 80.00 |
Vector-efficiency ratio all | 41.67 |
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 | 50.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 37.50 |
Path / |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source file and lines | field_summary.cpp:81-82 |
Module | exec |
nb instructions | 24 |
nb uops | 31 |
loop length | 126 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 11 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 5.17 cycles |
front end | 5.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 7.00 | 6.50 | 2.67 | 2.67 | 0.00 | 5.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2.67 |
cycles | 7.00 | 6.50 | 2.67 | 2.67 | 0.00 | 5.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00 |
FE+BE cycles | 7.30-87.46 |
Stall cycles | 2.23-82.12 |
RS full (events) | 5.88-0.14 |
Front-end | 5.17 |
Dispatch | 7.00 |
Data deps. | 4.00 |
Overall L1 | 7.00 |
all | 60% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 33% |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 86% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 80% |
all | 35% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 25% |
all | 45% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 42% |
all | 41% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 37% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LEA -0x1(%RCX),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KANDW %K2,%K1,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VPBROADCASTQ %RDX,%YMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDQ %YMM19,%YMM17,%YMM20 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
KMOVQ %K3,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VXORPD %XMM21,%XMM21,%XMM21 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD (%RBX,%YMM20,8),%YMM21{%K4} | 5 | 1 | 1 | 1.33 | 1.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 1.33 | 0-29 | 2 |
VPADDQ %YMM19,%YMM18,%YMM19 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
KMOVQ %K3,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VXORPD %XMM20,%XMM20,%XMM20 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD (%R15,%YMM19,8),%YMM20{%K4} | 5 | 1 | 1 | 1.33 | 1.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 1.33 | 0-29 | 2 |
VMOVAPD %YMM21,%YMM9{%K3} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VMULPD %YMM9,%YMM9,%YMM19 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %YMM20,%YMM7{%K3} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VFMADD231PD %YMM7,%YMM7,%YMM19 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %YMM24,%YMM19,%YMM15 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPBROADCASTQ %RCX,%YMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVAPD %YMM15,%YMM16{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VPCMPGTQ %YMM19,%YMM5,%K2{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0-3 | 1 |
KANDW %K2,%K1,%K0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KMOVD %K0,%EDX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
INC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
TEST $0xf,%DL | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JNE 42af00 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x470> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source file and lines | field_summary.cpp:81-82 |
Module | exec |
nb instructions | 24 |
nb uops | 31 |
loop length | 126 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 11 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 5.17 cycles |
front end | 5.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 7.00 | 6.50 | 2.67 | 2.67 | 0.00 | 5.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2.67 |
cycles | 7.00 | 6.50 | 2.67 | 2.67 | 0.00 | 5.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00 |
FE+BE cycles | 7.30-87.46 |
Stall cycles | 2.23-82.12 |
RS full (events) | 5.88-0.14 |
Front-end | 5.17 |
Dispatch | 7.00 |
Data deps. | 4.00 |
Overall L1 | 7.00 |
all | 60% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 33% |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 86% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 80% |
all | 35% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 25% |
all | 45% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 42% |
all | 41% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 37% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LEA -0x1(%RCX),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KANDW %K2,%K1,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VPBROADCASTQ %RDX,%YMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDQ %YMM19,%YMM17,%YMM20 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
KMOVQ %K3,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VXORPD %XMM21,%XMM21,%XMM21 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD (%RBX,%YMM20,8),%YMM21{%K4} | 5 | 1 | 1 | 1.33 | 1.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 1.33 | 0-29 | 2 |
VPADDQ %YMM19,%YMM18,%YMM19 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
KMOVQ %K3,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VXORPD %XMM20,%XMM20,%XMM20 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD (%R15,%YMM19,8),%YMM20{%K4} | 5 | 1 | 1 | 1.33 | 1.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 1.33 | 0-29 | 2 |
VMOVAPD %YMM21,%YMM9{%K3} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VMULPD %YMM9,%YMM9,%YMM19 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %YMM20,%YMM7{%K3} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VFMADD231PD %YMM7,%YMM7,%YMM19 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %YMM24,%YMM19,%YMM15 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPBROADCASTQ %RCX,%YMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVAPD %YMM15,%YMM16{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VPCMPGTQ %YMM19,%YMM5,%K2{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0-3 | 1 |
KANDW %K2,%K1,%K0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KMOVD %K0,%EDX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
INC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
TEST $0xf,%DL | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JNE 42af00 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x470> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |