Loop Id: 174 | Module: exec | Source: field_summary.cpp:80-82 | Coverage: 0.02% |
---|
Loop Id: 174 | Module: exec | Source: field_summary.cpp:80-82 | Coverage: 0.02% |
---|
0x42aea0 KXORW %K0,%K0,%K0 |
0x42aea4 VXORPD %XMM16,%XMM16,%XMM16 |
0x42aeaa XOR %EAX,%EAX |
0x42aeac VMOVAPD %YMM16,%YMM2{%K1} |
0x42aeb2 KANDW %K0,%K1,%K1 |
0x42aeb6 KMOVD %K1,%ECX |
0x42aeba VMOVAPD %YMM16,%YMM15 |
0x42aec0 TEST $0xf,%CL |
0x42aec3 JE 42acb0 |
0x42aec9 KMOVD %K1,%ECX |
0x42aecd TEST $0xf,%CL |
0x42aed0 JE 42aea0 |
0x42aed2 VPBROADCASTQ %RAX,%YMM16 |
0x42aed8 VPXORD %XMM17,%XMM17,%XMM17 |
0x42aede VPMULLQ %YMM16,%YMM22,%YMM17 |
0x42aee4 VPADDQ %YMM17,%YMM3,%YMM17 |
0x42aeea VPMULLQ %YMM16,%YMM23,%YMM16 |
0x42aef0 VPADDQ %YMM16,%YMM4,%YMM18 |
0x42aef6 KXNORW %K0,%K0,%K2 |
0x42aefa MOV $0x1,%ECX |
0x42aeff NOP |
(175) 0x42af00 LEA -0x1(%RCX),%RDX |
(175) 0x42af04 KANDW %K2,%K1,%K3 |
(175) 0x42af08 VPBROADCASTQ %RDX,%YMM19 |
(175) 0x42af0e VPADDQ %YMM19,%YMM17,%YMM20 |
(175) 0x42af14 KMOVQ %K3,%K4 |
(175) 0x42af19 VXORPD %XMM21,%XMM21,%XMM21 |
(175) 0x42af1f VGATHERQPD (%RBX,%YMM20,8),%YMM21{%K4} |
(175) 0x42af26 VPADDQ %YMM19,%YMM18,%YMM19 |
(175) 0x42af2c KMOVQ %K3,%K4 |
(175) 0x42af31 VXORPD %XMM20,%XMM20,%XMM20 |
(175) 0x42af37 VGATHERQPD (%R15,%YMM19,8),%YMM20{%K4} |
(175) 0x42af3e VMOVAPD %YMM21,%YMM9{%K3} |
(175) 0x42af44 VMULPD %YMM9,%YMM9,%YMM19 |
(175) 0x42af4a VMOVAPD %YMM20,%YMM7{%K3} |
(175) 0x42af50 VFMADD231PD %YMM7,%YMM7,%YMM19 |
(175) 0x42af56 VFMADD231PD %YMM24,%YMM19,%YMM15 |
(175) 0x42af5c VPBROADCASTQ %RCX,%YMM19 |
(175) 0x42af62 VMOVAPD %YMM15,%YMM16{%K2} |
(175) 0x42af68 VPCMPGTQ %YMM19,%YMM5,%K2{%K2} |
(175) 0x42af6e KANDW %K2,%K1,%K0 |
(175) 0x42af72 KMOVD %K0,%EDX |
(175) 0x42af76 INC %RCX |
(175) 0x42af79 TEST $0xf,%DL |
(175) 0x42af7c JNE 42af00 |
0x42af7e INC %RAX |
0x42af81 VPBROADCASTQ %RAX,%YMM15 |
0x42af87 VPCMPGTQ %YMM15,%YMM6,%K0 |
0x42af8d JMP 42aeac |
/scratch_na/users/xoserete/qaas_runs/171-415-4969/intel/CloverLeafCXX/build/CloverLeafCXX/src/omp/field_summary.cpp: 80 - 82 |
-------------------------------------------------------------------------------- |
80: for (int kv = k; kv <= k + 1; ++kv) { |
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 | 1.10 - 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.67 - 5.65 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.33 - 1.29 |
Bottlenecks | |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source | field_summary.cpp:80-82 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.67 - 6.00 |
CQA cycles if no scalar integer | 4.25 - 6.00 |
CQA cycles if FP arith vectorized | 4.67 - 6.00 |
CQA cycles if fully vectorized | 1.00 - 1.06 |
Front-end cycles | 3.42 |
DIV/SQRT cycles | 4.67 |
P0 cycles | 2.87 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 0.00 |
P4 cycles | 2.87 |
P5 cycles | 2.20 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 1.40 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 4 - 6 |
FE+BE cycles (UFS) | 4.96 - 4.95 |
Stall cycles (UFS) | 1.03 - 1.03 |
Nb insns | 17.00 |
Nb uops | 20.50 |
Nb loads | 0.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.00 - 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 | 0.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 0.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 73.86 |
Vectorization ratio load | NA |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 66.07 |
Vector-efficiency ratio all | 34.87 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 50.00 |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 31.14 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.19 - 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.05 - 3.43 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.07 - 1.13 |
Bottlenecks | |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source | field_summary.cpp:80-82 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.33 - 6.00 |
CQA cycles if no scalar integer | 4.50 - 6.00 |
CQA cycles if FP arith vectorized | 5.33 - 6.00 |
CQA cycles if fully vectorized | 1.75 |
Front-end cycles | 5.00 |
DIV/SQRT cycles | 5.33 |
P0 cycles | 5.33 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 0.00 |
P4 cycles | 5.33 |
P5 cycles | 2.40 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 2.60 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 4 - 6 |
FE+BE cycles (UFS) | 5.86 - 5.84 |
Stall cycles (UFS) | 0.69 - 0.68 |
Nb insns | 22.00 |
Nb uops | 30.00 |
Nb loads | 0.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.00 - 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 | 0.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 0.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 72.73 |
Vectorization ratio load | NA |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 57.14 |
Vector-efficiency ratio all | 36.93 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 50.00 |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 29.46 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 16.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.00 - 1.50 |
Bottlenecks | |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source | field_summary.cpp:80-82 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.00 - 6.00 |
CQA cycles if no scalar integer | 4.00 - 6.00 |
CQA cycles if FP arith vectorized | 4.00 - 6.00 |
CQA cycles if fully vectorized | 0.25 - 0.38 |
Front-end cycles | 1.83 |
DIV/SQRT cycles | 4.00 |
P0 cycles | 0.40 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 0.00 |
P4 cycles | 0.40 |
P5 cycles | 2.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.20 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 4 - 6 |
FE+BE cycles (UFS) | 4.06 |
Stall cycles (UFS) | 1.38 |
Nb insns | 12.00 |
Nb uops | 11.00 |
Nb loads | 0.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.00 - 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 | 0.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 0.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 75.00 |
Vectorization ratio load | NA |
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 | 75.00 |
Vector-efficiency ratio all | 32.81 |
Vector-efficiency ratio load | NA |
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 | 32.81 |
Path / |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source file and lines | field_summary.cpp:80-82 |
Module | exec |
nb instructions | 17 |
nb uops | 20.50 |
loop length | 77 |
used x86 registers | 2 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 6.50 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.42 cycles |
front end | 3.42 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.67 | 2.87 | 0.00 | 0.00 | 0.00 | 2.87 | 2.20 | 0.00 | 0.00 | 0.00 | 1.40 | 0.00 |
cycles | 4.67 | 2.87 | 0.00 | 0.00 | 0.00 | 2.87 | 2.20 | 0.00 | 0.00 | 0.00 | 1.40 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00-6.00 |
FE+BE cycles | 4.96-4.95 |
Stall cycles | 1.03-1.03 |
ROB full (events) | 1.42-1.41 |
PRF_INT full (events) | 0.64 |
Front-end | 3.42 |
Dispatch | 4.67 |
Data deps. | 4.00-6.00 |
Overall L1 | 4.67-6.00 |
all | 33% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 20% |
all | 100% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 73% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 66% |
all | 20% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 13% |
all | 45% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 45% |
all | 34% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 31% |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source file and lines | field_summary.cpp:80-82 |
Module | exec |
nb instructions | 22 |
nb uops | 30 |
loop length | 104 |
used x86 registers | 2 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 10 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 5.00 cycles |
front end | 5.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.33 | 5.33 | 0.00 | 0.00 | 0.00 | 5.33 | 2.40 | 0.00 | 0.00 | 0.00 | 2.60 | 0.00 |
cycles | 5.33 | 5.33 | 0.00 | 0.00 | 0.00 | 5.33 | 2.40 | 0.00 | 0.00 | 0.00 | 2.60 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00-6.00 |
FE+BE cycles | 5.86-5.84 |
Stall cycles | 0.69-0.68 |
ROB full (events) | 0.92-0.91 |
Front-end | 5.00 |
Dispatch | 5.33 |
Data deps. | 4.00-6.00 |
Overall L1 | 5.33-6.00 |
all | 66% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 40% |
all | 100% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 72% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 57% |
all | 34% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 21% |
all | 50% |
load | NA (no load vectorizable/vectorized instructions) |
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% |
all | 36% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 29% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVAPD %YMM16,%YMM2{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
KANDW %K0,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KMOVD %K1,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVAPD %YMM16,%YMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
TEST $0xf,%CL | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 42acb0 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
KMOVD %K1,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
TEST $0xf,%CL | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 42aea0 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x410> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VPBROADCASTQ %RAX,%YMM16 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXORD %XMM17,%XMM17,%XMM17 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
VPMULLQ %YMM16,%YMM22,%YMM17 | 5 | 1.50 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
VPADDQ %YMM17,%YMM3,%YMM17 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPMULLQ %YMM16,%YMM23,%YMM16 | 5 | 1.50 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
VPADDQ %YMM16,%YMM4,%YMM18 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
KXNORW %K0,%K0,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
MOV $0x1,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VPBROADCASTQ %RAX,%YMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPCMPGTQ %YMM15,%YMM6,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0-3 | 1 |
JMP 42aeac <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x41c> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source file and lines | field_summary.cpp:80-82 |
Module | exec |
nb instructions | 12 |
nb uops | 11 |
loop length | 50 |
used x86 registers | 2 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 3 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.83 cycles |
front end | 1.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.00 | 0.40 | 0.00 | 0.00 | 0.00 | 0.40 | 2.00 | 0.00 | 0.00 | 0.00 | 0.20 | 0.00 |
cycles | 4.00 | 0.40 | 0.00 | 0.00 | 0.00 | 0.40 | 2.00 | 0.00 | 0.00 | 0.00 | 0.20 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00-6.00 |
FE+BE cycles | 4.06 |
Stall cycles | 1.38 |
ROB full (events) | 1.91 |
PRF_INT full (events) | 1.27 |
Front-end | 1.83 |
Dispatch | 4.00 |
Data deps. | 4.00-6.00 |
Overall L1 | 4.00-6.00 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 0% |
all | 100% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 75% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 75% |
all | 6% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 6% |
all | 41% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 41% |
all | 32% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 32% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
KXORW %K0,%K0,%K0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM16,%XMM16,%XMM16 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVAPD %YMM16,%YMM2{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
KANDW %K0,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KMOVD %K1,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVAPD %YMM16,%YMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
TEST $0xf,%CL | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 42acb0 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
KMOVD %K1,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
TEST $0xf,%CL | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 42aea0 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x410> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |