Loop Id: 40 | Module: exec | Source: miniqmc.cpp:476-488 [...] | Coverage: 0.09% |
---|
Loop Id: 40 | Module: exec | Source: miniqmc.cpp:476-488 [...] | Coverage: 0.09% |
---|
0x40cb60 MOV -0x40(%RBP),%RDX |
0x40cb64 INC %RDX |
0x40cb67 MOV %RDX,%RAX |
0x40cb6a MOV %RDX,-0x40(%RBP) |
0x40cb6e CMP -0x218(%RBP),%RDX |
0x40cb75 JE 40cae0 |
0x40cb7b VMOVSD -0x220(%RBP),%XMM0 |
0x40cb83 MOV -0x40(%RBP),%RAX |
0x40cb87 VUCOMISD (%RBX,%RAX,8),%XMM0 |
0x40cb8c LEA -0x328(%RBP),%RDX |
0x40cb93 JBE 40cb60 |
0x40cb95 MOV -0x40(%RBP),%RAX |
0x40cb99 VPBROADCASTQ %RAX,%XMM0 |
0x40cb9f VMOVDQU %XMM0,-0x110(%RBP) |
0x40cba7 MOV -0x208(%RBP),%RAX |
0x40cbae MOV -0x210(%RBP),%R13 |
0x40cbb5 NOPW %CS:(%RAX,%RAX,1) |
(41) 0x40cbc0 MOV %RAX,-0x48(%RBP) |
(41) 0x40cbc4 MOVQ $0,-0x300(%RBP) |
(41) 0x40cbcf MOV -0x40(%RBP),%R8 |
(41) 0x40cbd3 VMOVDDUP (%RBX,%R8,8),%XMM0 |
(41) 0x40cbd9 VMULPD -0x10(%R13),%XMM0,%XMM1 |
(41) 0x40cbdf VMOVUPD %XMM1,-0x310(%RBP) |
(41) 0x40cbe7 VMULSD (%R13),%XMM0,%XMM0 |
(41) 0x40cbed VMOVSD %XMM0,-0x300(%RBP) |
(41) 0x40cbf5 MOV (%RCX),%RAX |
(41) 0x40cbf8 MOV -0x38(%RBP),%RCX |
(41) 0x40cbfc MOVSXD -0x10(%RCX),%RCX |
(41) 0x40cc00 VMOVQ %RCX,%XMM0 |
(41) 0x40cc05 VPSLLDQ $0x8,%XMM0,%XMM0 |
(41) 0x40cc0a VPADDQ -0x110(%RBP),%XMM0,%XMM0 |
(41) 0x40cc12 VPBROADCASTQ %RAX,%XMM2 |
(41) 0x40cc18 VPSLLQ $0x3,%XMM0,%XMM0 |
(41) 0x40cc1d VPADDQ %XMM0,%XMM2,%XMM0 |
(41) 0x40cc21 VMOVQ %XMM0,%RBX |
(41) 0x40cc26 VMOVSD (%RBX),%XMM2 |
(41) 0x40cc2a VPEXTRQ $0x1,%XMM0,%RBX |
(41) 0x40cc30 VMOVHPD (%RBX),%XMM2,%XMM0 |
(41) 0x40cc34 VMOVUPD %XMM0,-0x130(%RBP) |
(41) 0x40cc3c LEA (%R8,%RCX,2),%RCX |
(41) 0x40cc40 VMOVSD (%RAX,%RCX,8),%XMM0 |
(41) 0x40cc45 VMOVSD %XMM0,-0x120(%RBP) |
(41) 0x40cc4d VSUBSD %XMM2,%XMM1,%XMM0 |
(41) 0x40cc51 VMOVSD %XMM0,-0x328(%RBP) |
(41) 0x40cc59 VMOVUPD -0x308(%RBP),%XMM0 |
(41) 0x40cc61 VSUBPD -0x128(%RBP),%XMM0,%XMM0 |
(41) 0x40cc69 VMOVUPD %XMM0,-0x320(%RBP) |
(41) 0x40cc71 MOV %R12,%RDI |
(41) 0x40cc74 MOV %R14D,%ESI |
(41) 0x40cc77 CALL 458180 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEE> |
(41) 0x40cc7c MOV -0x68(%RBP),%RBX |
(41) 0x40cc80 MOV 0x20(%RBX),%RDI |
(41) 0x40cc84 CALL 464ec0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> |
(41) 0x40cc89 MOV -0x58(%RBP),%RDI |
(41) 0x40cc8d MOV %R12,%RSI |
(41) 0x40cc90 MOV %R14D,%EDX |
(41) 0x40cc93 CALL 411100 <_ZN11qmcplusplus12WaveFunction5ratioERNS_11ParticleSetEi> |
(41) 0x40cc98 MOV 0x20(%RBX),%RDI |
(41) 0x40cc9c CALL 4650a0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> |
(41) 0x40cca1 MOV %R12,%RDI |
(41) 0x40cca4 MOV %R14D,%ESI |
(41) 0x40cca7 CALL 458c80 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi> |
(41) 0x40ccac MOV -0x48(%RBP),%RAX |
(41) 0x40ccb0 LEA -0x328(%RBP),%RDX |
(41) 0x40ccb7 MOV -0x38(%RBP),%RCX |
(41) 0x40ccbb MOV -0xb8(%RBP),%RBX |
(41) 0x40ccc2 ADD $0x18,%R13 |
(41) 0x40ccc6 DEC %RAX |
(41) 0x40ccc9 JNE 40cbc0 |
0x40cccf JMP 40cb60 |
/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); } |
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 | 1.55 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 7.74 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.19 |
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 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.88 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 3.88 |
CQA cycles if fully vectorized | 0.50 |
Front-end cycles | 3.88 |
DIV/SQRT cycles | 1.75 |
P0 cycles | 1.75 |
P1 cycles | 3.25 |
P2 cycles | 3.25 |
P3 cycles | 1.50 |
P4 cycles | 1.75 |
P5 cycles | 1.75 |
P6 cycles | 1.50 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 4.04 |
Stall cycles (UFS) | 0.00 |
Nb insns | 14.50 |
Nb uops | 15.50 |
Nb loads | 6.50 |
Nb stores | 1.50 |
Nb stack references | 5.50 |
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 | 17.26 |
Bytes prefetched | 0.00 |
Bytes loaded | 52.00 |
Bytes stored | 16.00 |
Stride 0 | 2.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 0.50 |
Stride indirect | 0.00 |
Vectorization ratio all | 8.33 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 25.00 |
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 | 13.54 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 15.63 |
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 | 1.73 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 7.58 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.19 |
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 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.75 |
CQA cycles if no scalar integer | 2.75 |
CQA cycles if FP arith vectorized | 4.75 |
CQA cycles if fully vectorized | 0.63 |
Front-end cycles | 4.75 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 2.00 |
P1 cycles | 4.00 |
P2 cycles | 4.00 |
P3 cycles | 2.00 |
P4 cycles | 2.00 |
P5 cycles | 2.00 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 4.92 |
Stall cycles (UFS) | 0.00 |
Nb insns | 18.00 |
Nb uops | 19.00 |
Nb loads | 8.00 |
Nb stores | 2.00 |
Nb stack references | 7.00 |
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 | 18.53 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 24.00 |
Stride 0 | 3.00 |
Stride 1 | 1.00 |
Stride n | 2.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 16.67 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 50.00 |
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 | 14.58 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 18.75 |
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 | 1.33 |
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 | 1.20 |
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 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.00 |
CQA cycles if no scalar integer | 2.25 |
CQA cycles if FP arith vectorized | 3.00 |
CQA cycles if fully vectorized | 0.38 |
Front-end cycles | 3.00 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.50 |
P1 cycles | 2.50 |
P2 cycles | 2.50 |
P3 cycles | 1.00 |
P4 cycles | 1.50 |
P5 cycles | 1.50 |
P6 cycles | 1.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 3.16 |
Stall cycles (UFS) | 0.00 |
Nb insns | 11.00 |
Nb uops | 12.00 |
Nb loads | 5.00 |
Nb stores | 1.00 |
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 | 16.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 40.00 |
Bytes stored | 8.00 |
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 | 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 |
Path / |
Function | main.extracted.104 |
Source file and lines | miniqmc.cpp:476-488 |
Module | exec |
nb instructions | 14.50 |
nb uops | 15.50 |
loop length | 77 |
used x86 registers | 4.50 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5.50 |
micro-operation queue | 3.88 cycles |
front end | 3.88 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.75 | 1.75 | 3.25 | 3.25 | 1.50 | 1.75 | 1.75 | 1.50 |
cycles | 1.75 | 1.75 | 3.25 | 3.25 | 1.50 | 1.75 | 1.75 | 1.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 4.04 |
Stall cycles | 0.00 |
Front-end | 3.88 |
Dispatch | 3.25 |
Data deps. | 0.00 |
Overall L1 | 3.88 |
all | 12% |
load | 0% |
store | 25% |
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 | 8% |
load | 0% |
store | 25% |
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 | 14% |
load | 12% |
store | 15% |
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 | 13% |
load | 12% |
store | 15% |
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 | 18 |
nb uops | 19 |
loop length | 101 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 4.75 cycles |
front end | 4.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 4.00 | 4.00 | 2.00 | 2.00 | 2.00 | 2.00 |
cycles | 2.00 | 2.00 | 4.00 | 4.00 | 2.00 | 2.00 | 2.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 4.92 |
Stall cycles | 0.00 |
Front-end | 4.75 |
Dispatch | 4.00 |
Data deps. | 0.00 |
Overall L1 | 4.75 |
all | 25% |
load | 0% |
store | 50% |
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 | 16% |
load | 0% |
store | 50% |
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 | 15% |
load | 12% |
store | 18% |
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 | 14% |
load | 12% |
store | 18% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x40(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP -0x218(%RBP),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 40cae0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD -0x220(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VUCOMISD (%RBX,%RAX,8),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA -0x328(%RBP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JBE 40cb60 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VPBROADCASTQ %RAX,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQU %XMM0,-0x110(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 4 | 1 |
MOV -0x208(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x210(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 40cb60 | 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 | 12 |
loop length | 53 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 4 |
micro-operation queue | 3.00 cycles |
front end | 3.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.50 | 2.50 | 2.50 | 1.00 | 1.50 | 1.50 | 1.00 |
cycles | 1.50 | 1.50 | 2.50 | 2.50 | 1.00 | 1.50 | 1.50 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 3.16 |
Stall cycles | 0.00 |
Front-end | 3.00 |
Dispatch | 2.50 |
Data deps. | 0.00 |
Overall L1 | 3.00 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 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 | 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 | NA (no load vectorizable/vectorized instructions) |
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 | 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 | 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 |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x40(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP -0x218(%RBP),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 40cae0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD -0x220(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VUCOMISD (%RBX,%RAX,8),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA -0x328(%RBP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JBE 40cb60 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |