Loop Id: 175 | Module: exec | Source: field_summary.cpp:81-82 | Coverage: 0.13% |
---|
Loop Id: 175 | Module: exec | Source: field_summary.cpp:81-82 | Coverage: 0.13% |
---|
0x4379c0 KXORW %K0,%K0,%K0 |
0x4379c4 VXORPD %XMM18,%XMM18,%XMM18 |
0x4379ca XOR %ECX,%ECX |
0x4379cc VMOVAPD %ZMM18,%ZMM17{%K2} |
0x4379d2 KANDB %K0,%K2,%K2 |
0x4379d6 KTESTB %K2,%K1 |
0x4379da JE 437a6d |
0x4379e0 KANDB %K2,%K1,%K3 |
0x4379e4 KORTESTB %K3,%K3 |
0x4379e8 JE 4379c0 |
0x4379ea VPBROADCASTQ %RCX,%ZMM21 |
0x4379f0 VPADDQ %ZMM3,%ZMM21,%ZMM22 |
0x4379f6 VPADDQ %ZMM19,%ZMM22,%ZMM22 |
0x4379fc KMOVQ %K3,%K4 |
0x437a01 VXORPD %XMM23,%XMM23,%XMM23 |
0x437a07 VGATHERQPD (%RBX,%ZMM22,8),%ZMM23{%K4} [2] |
0x437a0e VMOVAPD %ZMM23,%ZMM7{%K3} |
0x437a14 VPADDQ %ZMM4,%ZMM21,%ZMM21 |
0x437a1a VPADDQ %ZMM20,%ZMM21,%ZMM21 |
0x437a20 KMOVQ %K3,%K4 |
0x437a25 VXORPD %XMM22,%XMM22,%XMM22 |
0x437a2b VGATHERQPD (%R12,%ZMM21,8),%ZMM22{%K4} [1] |
0x437a32 VMULPD %ZMM7,%ZMM7,%ZMM21 |
0x437a38 VMOVAPD %ZMM22,%ZMM9{%K3} |
0x437a3e VFMADD231PD %ZMM9,%ZMM9,%ZMM21 |
0x437a44 VFMADD231PD %ZMM26,%ZMM21,%ZMM18 |
0x437a4a INC %RCX |
0x437a4d VPBROADCASTQ %RCX,%ZMM21 |
0x437a53 VPCMPGTQ %ZMM21,%ZMM5,%K0 |
0x437a59 VMOVAPD %ZMM18,%ZMM17{%K2} |
0x437a5f KANDB %K0,%K2,%K2 |
0x437a63 KTESTB %K2,%K1 |
0x437a67 JNE 4379e0 |
/scratch_na/users/xoserete/qaas_runs/171-320-5323/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)); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.33 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.51 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.09 |
Bottlenecks | |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source | field_summary.cpp:81-82 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 8.00 |
CQA cycles if no scalar integer | 6.00 |
CQA cycles if FP arith vectorized | 8.00 |
CQA cycles if fully vectorized | 5.28 |
Front-end cycles | 3.67 |
DIV/SQRT cycles | 8.00 |
P0 cycles | 0.75 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 0.00 |
P4 cycles | 5.50 |
P5 cycles | 2.00 |
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) | 8.13 - 46.53 |
Stall cycles (UFS) | 4.21 - 42.44 |
Nb insns | 18.00 |
Nb uops | 22.00 |
Nb loads | 1.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.50 |
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 | 5.82 |
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 | 1.00 |
Vectorization ratio all | 77.45 |
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 | 73.33 |
Vector-efficiency ratio all | 62.32 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | 100.00 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 55.63 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.38 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.07 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.94 |
Bottlenecks | P0, P5, |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source | field_summary.cpp:81-82 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 11.00 |
CQA cycles if no scalar integer | 8.00 |
CQA cycles if FP arith vectorized | 11.00 |
CQA cycles if fully vectorized | 10.25 |
Front-end cycles | 5.67 |
DIV/SQRT cycles | 11.00 |
P0 cycles | 1.50 |
P1 cycles | 5.33 |
P2 cycles | 5.33 |
P3 cycles | 0.00 |
P4 cycles | 11.00 |
P5 cycles | 2.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 5.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 4 |
FE+BE cycles (UFS) | 11.22 - 88.03 |
Stall cycles (UFS) | 5.72 - 82.19 |
Nb insns | 26.00 |
Nb uops | 34.00 |
Nb loads | 2.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 3.64 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 8.00 |
Nb FLOP fma | 16.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 11.64 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
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 | 88.24 |
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 | 80.88 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | 100.00 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 67.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.25 |
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 | 2.50 |
Bottlenecks | P0, |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source | field_summary.cpp:81-82 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 5.00 |
CQA cycles if fully vectorized | 0.31 |
Front-end cycles | 1.67 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 0.00 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 0.00 |
P4 cycles | 0.00 |
P5 cycles | 2.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 4 |
FE+BE cycles (UFS) | 5.04 |
Stall cycles (UFS) | 2.69 |
Nb insns | 10.00 |
Nb uops | 10.00 |
Nb loads | 0.00 |
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 | 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 | 66.67 |
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 | 66.67 |
Vector-efficiency ratio all | 43.75 |
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 | 43.75 |
Path / |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source file and lines | field_summary.cpp:81-82 |
Module | exec |
nb instructions | 18 |
nb uops | 22 |
loop length | 91.50 |
used x86 registers | 2 |
used mmx registers | 0 |
used xmm registers | 1.50 |
used ymm registers | 0 |
used zmm registers | 7.50 |
nb stack references | 0 |
micro-operation queue | 3.67 cycles |
front end | 3.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 8.00 | 0.00 | 2.67 | 2.67 | 0.00 | 5.50 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2.67 |
cycles | 8.00 | 0.75 | 2.67 | 2.67 | 0.00 | 5.50 | 2.00 | 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 | 8.13-46.54 |
Stall cycles | 4.21-42.44 |
RS full (events) | 7.32-2.24 |
Front-end | 3.67 |
Dispatch | 8.00 |
Data deps. | 4.00 |
Overall L1 | 8.00 |
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 | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 16% |
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 | 77% |
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 | 73% |
all | 40% |
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 | 23% |
all | 73% |
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 | 70% |
all | 62% |
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 | 55% |
Function | field_summary(global_variables&, parallel_&) [clone .extracted] |
Source file and lines | field_summary.cpp:81-82 |
Module | exec |
nb instructions | 26 |
nb uops | 34 |
loop length | 141 |
used x86 registers | 3 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 13 |
nb stack references | 0 |
micro-operation queue | 5.67 cycles |
front end | 5.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 11.00 | 0.00 | 5.33 | 5.33 | 0.00 | 11.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 5.33 |
cycles | 11.00 | 1.50 | 5.33 | 5.33 | 0.00 | 11.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 5.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00 |
FE+BE cycles | 11.22-88.03 |
Stall cycles | 5.72-82.19 |
RS full (events) | 10.50-0.34 |
Front-end | 5.67 |
Dispatch | 11.00 |
Data deps. | 4.00 |
Overall L1 | 11.00 |
all | 71% |
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 | 88% |
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 | 75% |
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 | 41% |
all | 85% |
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 | 78% |
all | 80% |
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 | 67% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
KANDB %K2,%K1,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTB %K3,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JE 4379c0 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x460> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VPBROADCASTQ %RCX,%ZMM21 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPADDQ %ZMM3,%ZMM21,%ZMM22 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPADDQ %ZMM19,%ZMM22,%ZMM22 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
KMOVQ %K3,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VXORPD %XMM23,%XMM23,%XMM23 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD (%RBX,%ZMM22,8),%ZMM23{%K4} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VMOVAPD %ZMM23,%ZMM7{%K3} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VPADDQ %ZMM4,%ZMM21,%ZMM21 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPADDQ %ZMM20,%ZMM21,%ZMM21 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
KMOVQ %K3,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VXORPD %XMM22,%XMM22,%XMM22 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD (%R12,%ZMM21,8),%ZMM22{%K4} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VMULPD %ZMM7,%ZMM7,%ZMM21 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM22,%ZMM9{%K3} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VFMADD231PD %ZMM9,%ZMM9,%ZMM21 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %ZMM26,%ZMM21,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
INC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VPBROADCASTQ %RCX,%ZMM21 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPCMPGTQ %ZMM21,%ZMM5,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0-3 | 1 |
VMOVAPD %ZMM18,%ZMM17{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
KANDB %K0,%K2,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KTESTB %K2,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JNE 4379e0 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x480> | 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 | 10 |
nb uops | 10 |
loop length | 42 |
used x86 registers | 1 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 2 |
nb stack references | 0 |
micro-operation queue | 1.67 cycles |
front end | 1.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 5.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00 |
FE+BE cycles | 5.04 |
Stall cycles | 2.69 |
RS full (events) | 4.14 |
Front-end | 1.67 |
Dispatch | 5.00 |
Data deps. | 4.00 |
Overall L1 | 5.00 |
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 | 66% |
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 | 66% |
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 | 62% |
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 | 62% |
all | 43% |
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 | 43% |
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 %XMM18,%XMM18,%XMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVAPD %ZMM18,%ZMM17{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
KANDB %K0,%K2,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KTESTB %K2,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JE 437a6d <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x50d> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
KANDB %K2,%K1,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTB %K3,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JE 4379c0 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x460> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |