Loop Id: 218 | Module: exec | Source: field_summary.cpp:80-82 | Coverage: 0.02% |
---|
Loop Id: 218 | Module: exec | Source: field_summary.cpp:80-82 | Coverage: 0.02% |
---|
0x432500 INC %RAX |
0x432503 VPBROADCASTQ %RAX,%ZMM19 |
0x432509 VPCMPGTQ %ZMM19,%ZMM6,%K0 |
0x43250f VMOVAPD %ZMM18,%ZMM0{%K1} |
0x432515 KANDB %K0,%K1,%K1 |
0x432519 KORTESTB %K1,%K1 |
0x43251d VMOVAPD %ZMM18,%ZMM19 |
0x432523 JE 432300 |
0x432529 KORTESTB %K1,%K1 |
0x43252d JE 432640 |
0x432533 VPBROADCASTQ %RAX,%ZMM18 |
0x432539 VPXORD %XMM20,%XMM20,%XMM20 |
0x43253f VPMULLQ %ZMM18,%ZMM25,%ZMM20 |
0x432545 VPXORD %XMM21,%XMM21,%XMM21 |
0x43254b VPMULLQ %ZMM18,%ZMM26,%ZMM21 |
0x432551 KXNORW %K0,%K0,%K2 |
0x432555 XOR %ECX,%ECX |
0x432557 JMP 432603 |
(219) 0x432580 VPBROADCASTQ %RCX,%ZMM22 |
(219) 0x432586 VPADDQ %ZMM3,%ZMM22,%ZMM23 |
(219) 0x43258c VPADDQ %ZMM20,%ZMM23,%ZMM23 |
(219) 0x432592 KMOVQ %K3,%K4 |
(219) 0x432597 VXORPD %XMM24,%XMM24,%XMM24 |
(219) 0x43259d VGATHERQPD (%R15,%ZMM23,8),%ZMM24{%K4} |
(219) 0x4325a4 VMOVAPD %ZMM24,%ZMM7{%K3} |
(219) 0x4325aa VPADDQ %ZMM4,%ZMM22,%ZMM22 |
(219) 0x4325b0 VPADDQ %ZMM21,%ZMM22,%ZMM22 |
(219) 0x4325b6 KMOVQ %K3,%K4 |
(219) 0x4325bb VXORPD %XMM23,%XMM23,%XMM23 |
(219) 0x4325c1 VGATHERQPD (%R12,%ZMM22,8),%ZMM23{%K4} |
(219) 0x4325c8 VMULPD %ZMM7,%ZMM7,%ZMM22 |
(219) 0x4325ce VMOVAPD %ZMM23,%ZMM9{%K3} |
(219) 0x4325d4 VFMADD231PD %ZMM9,%ZMM9,%ZMM22 |
(219) 0x4325da VFMADD231PD %ZMM27,%ZMM22,%ZMM19 |
(219) 0x4325e0 INC %RCX |
(219) 0x4325e3 VPBROADCASTQ %RCX,%ZMM22 |
(219) 0x4325e9 VPCMPGTQ %ZMM22,%ZMM5,%K0 |
(219) 0x4325ef VMOVAPD %ZMM19,%ZMM18{%K2} |
(219) 0x4325f5 KANDB %K0,%K2,%K2 |
(219) 0x4325f9 KTESTB %K2,%K1 |
(219) 0x4325fd JE 432500 |
(219) 0x432603 KANDB %K2,%K1,%K3 |
(219) 0x432607 KORTESTB %K3,%K3 |
(219) 0x43260b JNE 432580 |
(219) 0x432611 KXORW %K0,%K0,%K0 |
(219) 0x432615 VXORPD %XMM19,%XMM19,%XMM19 |
(219) 0x43261b XOR %ECX,%ECX |
(219) 0x43261d VMOVAPD %ZMM19,%ZMM18{%K2} |
(219) 0x432623 KANDB %K0,%K2,%K2 |
(219) 0x432627 KTESTB %K2,%K1 |
(219) 0x43262b JNE 432603 |
0x43262d JMP 432500 |
0x432640 KXORW %K0,%K0,%K0 |
0x432644 VXORPD %XMM18,%XMM18,%XMM18 |
0x43264a XOR %EAX,%EAX |
0x43264c JMP 43250f |
/home/eoseret/qaas_runs_CPU_9468/171-112-9712/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)); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.21 - 1.06 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.45 - 1.60 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.57 - 1.48 |
Bottlenecks | |
Function | _Z13field_summaryR16global_variablesR9parallel_.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 | 5.67 - 6.33 |
CQA cycles if no scalar integer | 4.67 - 6.00 |
CQA cycles if FP arith vectorized | 5.67 - 6.33 |
CQA cycles if fully vectorized | 3.92 - 3.96 |
Front-end cycles | 3.56 |
DIV/SQRT cycles | 5.67 |
P0 cycles | 1.33 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 0.00 |
P4 cycles | 4.33 |
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 - 6 |
FE+BE cycles (UFS) | 5.94 - 5.98 |
Stall cycles (UFS) | 2.06 - 2.09 |
Nb insns | 16.00 |
Nb uops | 21.33 |
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 | 0.67 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 71.67 |
Vectorization ratio load | NA |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 66.67 |
Vector-efficiency ratio all | 58.02 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 51.04 |
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 | _Z13field_summaryR16global_variablesR9parallel_.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 | 0.00 |
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 - 6 |
FE+BE cycles (UFS) | 4.04 |
Stall cycles (UFS) | 1.36 |
Nb insns | 11.00 |
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 | 57.81 |
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 | 57.81 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.30 - 1.08 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.13 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.44 |
Bottlenecks | P0, P5, |
Function | _Z13field_summaryR16global_variablesR9parallel_.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 | 6.50 |
CQA cycles if no scalar integer | 5.00 - 6.00 |
CQA cycles if FP arith vectorized | 6.50 |
CQA cycles if fully vectorized | 5.75 |
Front-end cycles | 4.50 |
DIV/SQRT cycles | 6.50 |
P0 cycles | 2.00 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 0.00 |
P4 cycles | 6.50 |
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 - 6 |
FE+BE cycles (UFS) | 6.89 - 6.95 |
Stall cycles (UFS) | 2.30 - 2.36 |
Nb insns | 19.00 |
Nb uops | 27.00 |
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 | 70.00 |
Vectorization ratio load | NA |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 62.50 |
Vector-efficiency ratio all | 58.13 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 47.66 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.30 - 1.08 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.13 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.50 |
Bottlenecks | P0, P5, |
Function | _Z13field_summaryR16global_variablesR9parallel_.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 | 6.50 |
CQA cycles if no scalar integer | 5.00 - 6.00 |
CQA cycles if FP arith vectorized | 6.50 |
CQA cycles if fully vectorized | 5.75 |
Front-end cycles | 4.33 |
DIV/SQRT cycles | 6.50 |
P0 cycles | 2.00 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 0.00 |
P4 cycles | 6.50 |
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 - 6 |
FE+BE cycles (UFS) | 6.90 - 6.95 |
Stall cycles (UFS) | 2.51 - 2.54 |
Nb insns | 18.00 |
Nb uops | 26.00 |
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 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 70.00 |
Vectorization ratio load | NA |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 62.50 |
Vector-efficiency ratio all | 58.13 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 47.66 |
Path / |
Function | _Z13field_summaryR16global_variablesR9parallel_.extracted |
Source file and lines | field_summary.cpp:80-82 |
Module | exec |
nb instructions | 16 |
nb uops | 21.33 |
loop length | 80.67 |
used x86 registers | 1.67 |
used mmx registers | 0 |
used xmm registers | 1.67 |
used ymm registers | 0 |
used zmm registers | 6.33 |
nb stack references | 0 |
micro-operation queue | 3.56 cycles |
front end | 3.56 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.67 | 1.33 | 0.00 | 0.00 | 0.00 | 4.33 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 5.67 | 1.33 | 0.00 | 0.00 | 0.00 | 4.33 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00-6.00 |
FE+BE cycles | 5.94-5.98 |
Stall cycles | 2.06-2.09 |
ROB full (events) | 0.84 |
RS full (events) | 3.05-3.07 |
Front-end | 3.56 |
Dispatch | 5.67 |
Data deps. | 4.00-6.00 |
Overall L1 | 5.67-6.33 |
all | 41% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 33% |
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 | 71% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
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 | 33% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 22% |
all | 91% |
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 | 91% |
all | 58% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
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 | 51% |
Function | _Z13field_summaryR16global_variablesR9parallel_.extracted |
Source file and lines | field_summary.cpp:80-82 |
Module | exec |
nb instructions | 11 |
nb uops | 11 |
loop length | 53 |
used x86 registers | 1 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 3 |
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 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 4.00 | 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) | 4.00-6.00 |
FE+BE cycles | 4.04 |
Stall cycles | 1.36 |
ROB full (events) | 2.51 |
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 | 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 | 57% |
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 | 57% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVAPD %ZMM18,%ZMM0{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
KANDB %K0,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTB %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VMOVAPD %ZMM18,%ZMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
JE 432300 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
KORTESTB %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JE 432640 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x560> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
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 %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 43250f <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x42f> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | _Z13field_summaryR16global_variablesR9parallel_.extracted |
Source file and lines | field_summary.cpp:80-82 |
Module | exec |
nb instructions | 19 |
nb uops | 27 |
loop length | 97 |
used x86 registers | 2 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 8 |
nb stack references | 0 |
micro-operation queue | 4.50 cycles |
front end | 4.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 6.50 | 2.00 | 0.00 | 0.00 | 0.00 | 6.50 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 6.50 | 2.00 | 0.00 | 0.00 | 0.00 | 6.50 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00-6.00 |
FE+BE cycles | 6.89-6.95 |
Stall cycles | 2.30-2.36 |
RS full (events) | 4.33-4.35 |
Front-end | 4.50 |
Dispatch | 6.50 |
Data deps. | 4.00-6.00 |
Overall L1 | 6.50 |
all | 62% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 50% |
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 | 70% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
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 | 47% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 30% |
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 | 58% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
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 | 47% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VPBROADCASTQ %RAX,%ZMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPCMPGTQ %ZMM19,%ZMM6,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0-3 | 1 |
VMOVAPD %ZMM18,%ZMM0{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
KANDB %K0,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTB %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VMOVAPD %ZMM18,%ZMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
JE 432300 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
KORTESTB %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JE 432640 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x560> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VPBROADCASTQ %RAX,%ZMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXORD %XMM20,%XMM20,%XMM20 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
VPMULLQ %ZMM18,%ZMM25,%ZMM20 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
VPXORD %XMM21,%XMM21,%XMM21 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
VPMULLQ %ZMM18,%ZMM26,%ZMM21 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
KXNORW %K0,%K0,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 432603 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x523> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
JMP 432500 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x420> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | _Z13field_summaryR16global_variablesR9parallel_.extracted |
Source file and lines | field_summary.cpp:80-82 |
Module | exec |
nb instructions | 18 |
nb uops | 26 |
loop length | 92 |
used x86 registers | 2 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 8 |
nb stack references | 0 |
micro-operation queue | 4.33 cycles |
front end | 4.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 6.50 | 2.00 | 0.00 | 0.00 | 0.00 | 6.50 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 6.50 | 2.00 | 0.00 | 0.00 | 0.00 | 6.50 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00-6.00 |
FE+BE cycles | 6.90-6.95 |
Stall cycles | 2.51-2.54 |
RS full (events) | 4.82-4.87 |
Front-end | 4.33 |
Dispatch | 6.50 |
Data deps. | 4.00-6.00 |
Overall L1 | 6.50 |
all | 62% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 50% |
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 | 70% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
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 | 47% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 30% |
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 | 58% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
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 | 47% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VPBROADCASTQ %RAX,%ZMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPCMPGTQ %ZMM19,%ZMM6,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0-3 | 1 |
VMOVAPD %ZMM18,%ZMM0{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
KANDB %K0,%K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
KORTESTB %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VMOVAPD %ZMM18,%ZMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
JE 432300 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
KORTESTB %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JE 432640 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x560> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
VPBROADCASTQ %RAX,%ZMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXORD %XMM20,%XMM20,%XMM20 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
VPMULLQ %ZMM18,%ZMM25,%ZMM20 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
VPXORD %XMM21,%XMM21,%XMM21 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
VPMULLQ %ZMM18,%ZMM26,%ZMM21 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
KXNORW %K0,%K0,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 432603 <_Z13field_summaryR16global_variablesR9parallel_.extracted+0x523> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |