Loop Id: 38 | Module: exec | Source: miniqmc.cpp:476-488 [...] | Coverage: 0.04% |
---|
Loop Id: 38 | Module: exec | Source: miniqmc.cpp:476-488 [...] | Coverage: 0.04% |
---|
0x40ad40 INC %RDI |
0x40ad43 CMP -0x1e0(%RBP),%RDI |
0x40ad4a JE 40acc0 |
0x40ad50 VMOVSD -0x1e8(%RBP),%XMM0 |
0x40ad58 VUCOMISD (%RSI,%RDI,8),%XMM0 |
0x40ad5d LEA -0x258(%RBP),%RDX |
0x40ad64 MOV -0x80(%RBP),%RBX |
0x40ad68 JBE 40ad40 |
0x40ad6a MOV 0x30(%RBP),%RAX |
0x40ad6e TEST %EAX,%EAX |
0x40ad70 JLE 40ad40 |
0x40ad72 MOV -0x1d8(%RBP),%R12 |
0x40ad79 MOV -0x58(%RBP),%R13 |
0x40ad7d MOV %RDI,-0x48(%RBP) |
0x40ad81 NOPW %CS:(%RAX,%RAX,1) |
(39) 0x40ad90 MOVQ $0,-0x230(%RBP) |
(39) 0x40ad9b VMOVDDUP (%RSI,%RDI,8),%XMM0 |
(39) 0x40ada0 VMULPD -0x10(%R13),%XMM0,%XMM1 |
(39) 0x40ada6 VMOVUPD %XMM1,-0x240(%RBP) |
(39) 0x40adae VMULSD (%R13),%XMM0,%XMM0 |
(39) 0x40adb4 VMOVSD %XMM0,-0x230(%RBP) |
(39) 0x40adbc MOV (%RCX),%RAX |
(39) 0x40adbf MOV -0x38(%RBP),%RCX |
(39) 0x40adc3 MOVSXD -0x10(%RCX),%RCX |
(39) 0x40adc7 VMOVSD (%RAX,%RDI,8),%XMM0 |
(39) 0x40adcc LEA (%RDI,%RCX,1),%RSI |
(39) 0x40add0 VMOVHPD (%RAX,%RSI,8),%XMM0,%XMM2 |
(39) 0x40add5 VMOVUPD %XMM2,-0x110(%RBP) |
(39) 0x40addd LEA (%RDI,%RCX,2),%RCX |
(39) 0x40ade1 VMOVSD (%RAX,%RCX,8),%XMM2 |
(39) 0x40ade6 VMOVSD %XMM2,-0x100(%RBP) |
(39) 0x40adee VSUBSD %XMM0,%XMM1,%XMM0 |
(39) 0x40adf2 VMOVSD %XMM0,-0x258(%RBP) |
(39) 0x40adfa VMOVUPD -0x238(%RBP),%XMM0 |
(39) 0x40ae02 VSUBPD -0x108(%RBP),%XMM0,%XMM0 |
(39) 0x40ae0a VMOVUPD %XMM0,-0x250(%RBP) |
(39) 0x40ae12 MOV %RBX,%RDI |
(39) 0x40ae15 MOV %R15D,%ESI |
(39) 0x40ae18 CALL 451c30 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEE> |
(39) 0x40ae1d MOV %RBX,%R14 |
(39) 0x40ae20 MOV -0xb8(%RBP),%RBX |
(39) 0x40ae27 MOV (%RBX),%RAX |
(39) 0x40ae2a MOV 0x20(%RAX),%RDI |
(39) 0x40ae2e CALL 45de10 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> |
(39) 0x40ae33 MOV -0x88(%RBP),%RDI |
(39) 0x40ae3a MOV %R14,%RSI |
(39) 0x40ae3d MOV %R15D,%EDX |
(39) 0x40ae40 CALL 40ea20 <_ZN11qmcplusplus12WaveFunction5ratioERNS_11ParticleSetEi> |
(39) 0x40ae45 MOV (%RBX),%RAX |
(39) 0x40ae48 MOV %R14,%RBX |
(39) 0x40ae4b MOV 0x20(%RAX),%RDI |
(39) 0x40ae4f CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> |
(39) 0x40ae54 MOV %R14,%RDI |
(39) 0x40ae57 MOV %R15D,%ESI |
(39) 0x40ae5a CALL 4526e0 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi> |
(39) 0x40ae5f MOV -0x48(%RBP),%RDI |
(39) 0x40ae63 LEA -0x258(%RBP),%RDX |
(39) 0x40ae6a MOV -0x38(%RBP),%RCX |
(39) 0x40ae6e MOV -0x30(%RBP),%RSI |
(39) 0x40ae72 ADD $0x18,%R13 |
(39) 0x40ae76 DEC %R12 |
(39) 0x40ae79 JNE 40ad90 |
0x40ae7f JMP 40ad40 |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h: 85 - 111 |
-------------------------------------------------------------------------------- |
85: ret[d] = op(lhs[d], rhs[d]); |
[...] |
111: ret[d] = op(lhs, rhs[d]); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 53 - 183 |
-------------------------------------------------------------------------------- |
53: return (a - b); |
[...] |
63: return (a * b); |
[...] |
183: return (const_cast<T1&>(a) = b); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Drivers/miniqmc.cpp: 476 - 488 |
-------------------------------------------------------------------------------- |
476: for (int iat = 0; iat < nions; ++iat) |
477: if (dist[iat] < Rmax) |
478: for (int k = 0; k < nknots; k++) |
479: { |
480: PosType deltar(dist[iat] * rOnSphere[k] - displ[iat]); |
481: |
482: els.makeMove(jel, deltar); |
483: |
484: Timers[Timer_Value].get().start(); |
485: wavefunction.ratio(els, jel); |
486: Timers[Timer_Value].get().stop(); |
487: |
488: els.rejectMove(jel); |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/refwrap.h: 347 - 347 |
-------------------------------------------------------------------------------- |
347: { return *_M_data; } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 146 - 146 |
-------------------------------------------------------------------------------- |
146: X[i] = base[i * offset]; |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 203 - 203 |
-------------------------------------------------------------------------------- |
203: const Type_t operator[](size_t i) const { return Type_t(myData + i, nGhosts); } |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/stl_vector.h: 1126 - 1126 |
-------------------------------------------------------------------------------- |
1126: return *(this->_M_impl._M_start + __n); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | main | miniqmc.cpp:404 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.61 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.16 |
Bottlenecks | |
Function | main.extracted.104 |
Source | TinyVectorOps.h:85-111,OperatorTags.h:53-183,miniqmc.cpp:476-488,refwrap.h:347-347,TinyVector.h:146-146,VectorSoAContainer.h:203-203,stl_vector.h:1126-1126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.08 |
CQA cycles if no scalar integer | 1.92 |
CQA cycles if FP arith vectorized | 3.08 |
CQA cycles if fully vectorized | 0.39 |
Front-end cycles | 3.08 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 1.67 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 0.33 |
P4 cycles | 1.67 |
P5 cycles | 2.00 |
P6 cycles | 0.33 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 3.21 |
Stall cycles (UFS) | 0.00 |
Nb insns | 11.67 |
Nb uops | 12.33 |
Nb loads | 5.33 |
Nb stores | 0.33 |
Nb stack references | 5.67 |
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 | 14.61 |
Bytes prefetched | 0.00 |
Bytes loaded | 42.67 |
Bytes stored | 2.67 |
Stride 0 | 1.00 |
Stride 1 | 1.67 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 0.67 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
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 | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.29 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.13 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.104 |
Source | TinyVectorOps.h:85-111,OperatorTags.h:53-183,miniqmc.cpp:476-488,refwrap.h:347-347,TinyVector.h:146-146,VectorSoAContainer.h:203-203,stl_vector.h:1126-1126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.25 |
CQA cycles if no scalar integer | 1.75 |
CQA cycles if FP arith vectorized | 2.25 |
CQA cycles if fully vectorized | 0.28 |
Front-end cycles | 2.25 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.50 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 0.00 |
P4 cycles | 1.50 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.38 |
Stall cycles (UFS) | 0.00 |
Nb insns | 8.00 |
Nb uops | 9.00 |
Nb loads | 4.00 |
Nb stores | 0.00 |
Nb stack references | 4.00 |
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 | 14.22 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
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 | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
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 | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.13 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.21 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.104 |
Source | TinyVectorOps.h:85-111,OperatorTags.h:53-183,miniqmc.cpp:476-488,refwrap.h:347-347,TinyVector.h:146-146,VectorSoAContainer.h:203-203,stl_vector.h:1126-1126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.25 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 4.25 |
CQA cycles if fully vectorized | 0.53 |
Front-end cycles | 4.25 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.00 |
P1 cycles | 3.50 |
P2 cycles | 3.50 |
P3 cycles | 1.00 |
P4 cycles | 2.00 |
P5 cycles | 2.50 |
P6 cycles | 1.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 4.38 |
Stall cycles (UFS) | 0.00 |
Nb insns | 16.00 |
Nb uops | 17.00 |
Nb loads | 7.00 |
Nb stores | 1.00 |
Nb stack references | 8.00 |
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 | 15.06 |
Bytes prefetched | 0.00 |
Bytes loaded | 56.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
Stride 1 | 3.00 |
Stride n | 3.00 |
Stride unknown | 0.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
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 | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.38 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.10 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.104 |
Source | TinyVectorOps.h:85-111,OperatorTags.h:53-183,miniqmc.cpp:476-488,refwrap.h:347-347,TinyVector.h:146-146,VectorSoAContainer.h:203-203,stl_vector.h:1126-1126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.75 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 2.75 |
CQA cycles if fully vectorized | 0.34 |
Front-end cycles | 2.75 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 1.50 |
P1 cycles | 2.50 |
P2 cycles | 2.50 |
P3 cycles | 0.00 |
P4 cycles | 1.50 |
P5 cycles | 2.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.87 |
Stall cycles (UFS) | 0.00 |
Nb insns | 11.00 |
Nb uops | 11.00 |
Nb loads | 5.00 |
Nb stores | 0.00 |
Nb stack references | 5.00 |
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 | 14.55 |
Bytes prefetched | 0.00 |
Bytes loaded | 40.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
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 | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
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 | 12.50 |
Path / |
Function | main.extracted.104 |
Source file and lines | miniqmc.cpp:476-488 |
Module | exec |
nb instructions | 11.67 |
nb uops | 12.33 |
loop length | 59 |
used x86 registers | 6.33 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5.67 |
micro-operation queue | 3.08 cycles |
front end | 3.08 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 1.67 | 2.67 | 2.67 | 0.33 | 1.67 | 2.00 | 0.33 |
cycles | 2.00 | 1.67 | 2.67 | 2.67 | 0.33 | 1.67 | 2.00 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 3.21 |
Stall cycles | 0.00 |
Front-end | 3.08 |
Dispatch | 2.67 |
Data deps. | 1.00 |
Overall L1 | 3.08 |
all | 0% |
load | 0% |
store | 0% |
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 | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
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 | 0% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
load | 12% |
store | 12% |
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 | 12% |
Function | main.extracted.104 |
Source file and lines | miniqmc.cpp:476-488 |
Module | exec |
nb instructions | 8 |
nb uops | 9 |
loop length | 42 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 4 |
micro-operation queue | 2.25 cycles |
front end | 2.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.50 | 2.00 | 2.00 | 0.00 | 1.50 | 1.50 | 0.00 |
cycles | 1.50 | 1.50 | 2.00 | 2.00 | 0.00 | 1.50 | 1.50 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.38 |
Stall cycles | 0.00 |
Front-end | 2.25 |
Dispatch | 2.00 |
Data deps. | 1.00 |
Overall L1 | 2.25 |
all | 0% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 12% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP -0x1e0(%RBP),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 40acc0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD -0x1e8(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VUCOMISD (%RSI,%RDI,8),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA -0x258(%RBP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JBE 40ad40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | main.extracted.104 |
Source file and lines | miniqmc.cpp:476-488 |
Module | exec |
nb instructions | 16 |
nb uops | 17 |
loop length | 85 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 4.25 cycles |
front end | 4.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.00 | 3.50 | 3.50 | 1.00 | 2.00 | 2.50 | 1.00 |
cycles | 2.50 | 2.00 | 3.50 | 3.50 | 1.00 | 2.00 | 2.50 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 4.38 |
Stall cycles | 0.00 |
Front-end | 4.25 |
Dispatch | 3.50 |
Data deps. | 1.00 |
Overall L1 | 4.25 |
all | 0% |
load | 0% |
store | 0% |
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 | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
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 | 0% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
load | 12% |
store | 12% |
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 | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP -0x1e0(%RBP),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 40acc0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD -0x1e8(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VUCOMISD (%RSI,%RDI,8),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA -0x258(%RBP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JBE 40ad40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 40ad40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x1d8(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDI,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 40ad40 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | main.extracted.104 |
Source file and lines | miniqmc.cpp:476-488 |
Module | exec |
nb instructions | 11 |
nb uops | 11 |
loop length | 50 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 2.75 cycles |
front end | 2.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 1.50 | 2.50 | 2.50 | 0.00 | 1.50 | 2.00 | 0.00 |
cycles | 2.00 | 1.50 | 2.50 | 2.50 | 0.00 | 1.50 | 2.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.87 |
Stall cycles | 0.00 |
Front-end | 2.75 |
Dispatch | 2.50 |
Data deps. | 1.00 |
Overall L1 | 2.75 |
all | 0% |
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 | 0% |
all | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
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 | 12% |
all | 12% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP -0x1e0(%RBP),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 40acc0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD -0x1e8(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VUCOMISD (%RSI,%RDI,8),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA -0x258(%RBP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JBE 40ad40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 40ad40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |