Loop Id: 991 | Module: exec | Source: ParticleIOUtility.h:70-91 [...] | Coverage: 0.74% |
---|
Loop Id: 991 | Module: exec | Source: ParticleIOUtility.h:70-91 [...] | Coverage: 0.74% |
---|
0x45ab40 INC %R15 |
0x45ab43 ADD $0x18,%R13 |
0x45ab47 CMP %R15,%R14 |
0x45ab4a JE 45aaf0 |
0x45ab4c MOV -0x30(%RBP),%RAX [7] |
0x45ab50 CMP %EBX,(%RAX,%R15,4) [2] |
0x45ab54 JNE 45ab40 |
0x45ab56 VMOVUPD -0x10(%R13),%XMM0 [4] |
0x45ab5c VROUNDPD $0x9,%XMM0,%XMM1 |
0x45ab62 VSUBPD %XMM1,%XMM0,%XMM0 |
0x45ab66 VMOVSD (%R13),%XMM1 [4] |
0x45ab6c VROUNDSD $0x9,%XMM1,%XMM1,%XMM2 |
0x45ab72 VSUBSD %XMM2,%XMM1,%XMM1 |
0x45ab76 VMOVDDUP %XMM0,%XMM2 |
0x45ab7a VPERMILPD $0x1,%XMM0,%XMM7 |
0x45ab80 VPERMILPD $0x3,%XMM0,%XMM4 |
0x45ab86 VMOVDDUP %XMM1,%XMM5 |
0x45ab8a VFMADD132PD -0x160(%RBP),%XMM8,%XMM2 [7] |
0x45ab93 VFMADD132PD -0x150(%RBP),%XMM10,%XMM4 [7] |
0x45ab9c VADDPD %XMM2,%XMM4,%XMM2 |
0x45aba0 VFMADD132PD -0x140(%RBP),%XMM12,%XMM5 [7] |
0x45aba9 VADDPD %XMM5,%XMM2,%XMM3 |
0x45abad VFMADD132SD -0x190(%RBP),%XMM9,%XMM0 [7] |
0x45abb6 VFMADD132SD -0x180(%RBP),%XMM11,%XMM7 [7] |
0x45abbf VADDSD %XMM0,%XMM7,%XMM2 |
0x45abc3 VFMADD132SD -0x170(%RBP),%XMM13,%XMM1 [7] |
0x45abcc VMULSD 0xb0(%RSI),%XMM3,%XMM0 [9] |
0x45abd4 VPERMILPD $0x1,%XMM3,%XMM4 |
0x45abda VFMADD231SD 0xc8(%RSI),%XMM4,%XMM0 [9] |
0x45abe3 VADDSD %XMM1,%XMM2,%XMM5 |
0x45abe7 VFMADD231SD 0xe0(%RSI),%XMM5,%XMM0 [9] |
0x45abf0 VUCOMISD %XMM6,%XMM0 |
0x45abf4 VMOVUPD 0xb8(%RSI),%XMM1 [9] |
0x45abfc VMOVSD 0xd0(%RSI),%XMM2 [9] |
0x45ac04 VUNPCKLPD 0xc0(%RSI),%XMM2,%XMM2 [9] |
0x45ac0c VMOVHPD 0xd8(%RSI),%XMM1,%XMM7 [9] |
0x45ac14 VMULPD %XMM4,%XMM2,%XMM1 |
0x45ac18 VFMADD213PD %XMM1,%XMM3,%XMM7 |
0x45ac1d VMOVDDUP %XMM5,%XMM1 |
0x45ac21 VFMADD132PD 0xe8(%RSI),%XMM7,%XMM1 [9] |
0x45ac2a VCMPPD $0x1,%XMM14,%XMM1,%K0 |
0x45ac31 JB 45ab40 |
0x45ac37 VUCOMISD 0x3b801(%RIP),%XMM0 [5] |
0x45ac3f JAE 45ab40 |
0x45ac45 VUCOMISD %XMM6,%XMM1 |
0x45ac49 JB 45ab40 |
0x45ac4f KMOVD %K0,%EAX |
0x45ac53 TEST $0x1,%AL |
0x45ac55 JE 45ab40 |
0x45ac5b VPERMILPD $0x1,%XMM1,%XMM2 |
0x45ac61 VUCOMISD %XMM6,%XMM2 |
0x45ac65 JB 45ab40 |
0x45ac6b KSHIFTRB $0x1,%K0,%K0 |
0x45ac71 KMOVD %K0,%EAX |
0x45ac75 TEST $0x1,%AL |
0x45ac77 JE 45ab40 |
0x45ac7d MOV %EDI,%R14D |
0x45ac80 MOV $0x1f4,%ESI |
0x45ac85 MOV $0x496763,%EDX |
0x45ac8a LEA -0x3b0(%RBP),%RDI |
0x45ac91 VMOVUPD %XMM3,-0x70(%RBP) [7] |
0x45ac96 MOV %EBX,%ECX |
0x45ac98 MOV $0x6,%AL |
0x45ac9a VMOVUPD %XMM5,-0x130(%RBP) [7] |
0x45aca2 CALL 404580 <snprintf@plt> |
0x45aca7 MOV 0x9764a(%RIP),%R12 [5] |
0x45acae LEA -0x3b0(%RBP),%RDI |
0x45acb5 CALL 404160 <strlen@plt> |
0x45acba MOV %R12,%RDI |
0x45acbd LEA -0x3b0(%RBP),%RSI |
0x45acc4 MOV %RAX,%RDX |
0x45acc7 CALL 404340 <_ZSt16__ostream_insertIcSt11char_traitsIcEERSt13basic_ostreamIT_T0_ES6_PKS3_l@plt> |
0x45accc MOVSXD %R14D,%RAX |
0x45accf MOV -0x38(%RBP),%RSI [7] |
0x45acd3 MOV 0x5e8(%RSI),%RCX [10] |
0x45acda LEA (%RAX,%RAX,2),%RDX |
0x45acde VMOVUPS -0x70(%RBP),%XMM0 [7] |
0x45ace3 VMOVUPS %XMM0,(%RCX,%RDX,8) [1] |
0x45ace8 VMOVUPD -0x130(%RBP),%XMM0 [7] |
0x45acf0 VMOVSD %XMM0,0x10(%RCX,%RDX,8) [1] |
0x45acf6 MOV 0x5c0(%RSI),%RCX [10] |
0x45acfd MOV %EBX,(%RCX,%RAX,4) [6] |
0x45ad00 MOV 0x570(%RSI),%RCX [10] |
0x45ad07 MOV %EAX,(%RCX,%RAX,4) [8] |
0x45ad0a MOV 0x598(%RSI),%RCX [10] |
0x45ad11 MOV %R15D,(%RCX,%RAX,4) [3] |
0x45ad15 LEA 0x1(%RAX),%EDI |
0x45ad18 MOV -0x40(%RBP),%R14 [7] |
0x45ad1c VMOVSD 0x3b714(%RIP),%XMM6 [5] |
0x45ad24 VMOVUPD -0xf0(%RBP),%XMM14 [7] |
0x45ad2c VMOVUPD -0x100(%RBP),%XMM8 [7] |
0x45ad34 VMOVSD -0xa0(%RBP),%XMM9 [7] |
0x45ad3c VMOVUPD -0x110(%RBP),%XMM10 [7] |
0x45ad44 VMOVSD -0xa8(%RBP),%XMM11 [7] |
0x45ad4c VMOVUPD -0x120(%RBP),%XMM12 [7] |
0x45ad54 VMOVSD -0xb0(%RBP),%XMM13 [7] |
0x45ad5c JMP 45ab40 |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/ostream: 667 - 667 |
-------------------------------------------------------------------------------- |
667: __ostream_insert(__out, __s, |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/Tensor.h: 213 - 213 |
-------------------------------------------------------------------------------- |
213: inline Type_t operator[](unsigned int i) const { return X[i]; } |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 43 - 183 |
-------------------------------------------------------------------------------- |
43: return (a + b); |
[...] |
183: return (const_cast<T1&>(a) = b); |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/char_traits.h: 409 - 409 |
-------------------------------------------------------------------------------- |
409: return __builtin_strlen(__s); |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Particle/ParticleIOUtility.h: 70 - 91 |
-------------------------------------------------------------------------------- |
70: for (int iat = 0; iat < primPos.size(); iat++) |
71: { |
72: if (primTypes[iat] != ns) |
73: continue; |
74: SingleParticlePos_t uPrim = primPos[iat]; |
75: for (int i = 0; i < 3; i++) |
76: uPrim[i] -= std::floor(uPrim[i]); |
77: SingleParticlePos_t r = PrimCell.toCart(uPrim) + (double)i0 * PrimCell.a(0) + (double)i1 * PrimCell.a(1) + |
78: (double)i2 * PrimCell.a(2); |
79: SingleParticlePos_t uSuper = ref_.Lattice.toUnit(r); |
80: if ((uSuper[0] >= -1.0e-6) && (uSuper[0] < 0.9999) && (uSuper[1] >= -1.0e-6) && (uSuper[1] < 0.9999) && |
81: (uSuper[2] >= -1.0e-6) && (uSuper[2] < 0.9999)) |
82: { |
83: char buff[500]; |
84: snprintf(buff, 500, " %10.4f %10.4f %10.4f %12.6f %12.6f %12.6f %d\n", uSuper[0], uSuper[1], |
85: uSuper[2], r[0], r[1], r[2], ns); |
86: app_log() << buff; |
87: ref_.R[index] = r; |
88: ref_.GroupID[index] = ns; // primTypes[iat]; |
89: ref_.ID[index] = index; |
90: ref_.PCID[index] = iat; |
91: index++; |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 223 |
-------------------------------------------------------------------------------- |
223: return X[i]; |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h: 150 - 152 |
-------------------------------------------------------------------------------- |
150: return TinyVector<Type_t, 3>(lhs[0] * rhs[0] + lhs[1] * rhs[3] + lhs[2] * rhs[6], |
151: lhs[0] * rhs[1] + lhs[1] * rhs[4] + lhs[2] * rhs[7], |
152: lhs[0] * rhs[2] + lhs[1] * rhs[5] + lhs[2] * rhs[8]); |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Platforms/Host/InfoStream.h: 37 - 37 |
-------------------------------------------------------------------------------- |
37: std::ostream& getStream(const std::string& tag = "") { return *currStream; } |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::Tensor<double, 3u[...] | nio.hpp:76 | exec |
○ | qmcplusplus::build_ions(qmcplu[...] | Tensor.h:213 | exec |
○ | main | ParticleSet.h:263 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.58 |
CQA speedup if FP arith vectorized | 1.69 |
CQA speedup if fully vectorized | 7.72 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.44 |
Bottlenecks | micro-operation queue, |
Function | void qmcplusplus::expandSuperCell |
Source | ostream:667-667,Tensor.h:213-213,OperatorTags.h:43-183,char_traits.h:409-409,ParticleIOUtility.h:70-91,OhmmsVector.h:223-223,TinyVectorTensorOps.h:150-152,InfoStream.h:37-37 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 26.00 |
CQA cycles if no scalar integer | 16.50 |
CQA cycles if FP arith vectorized | 15.38 |
CQA cycles if fully vectorized | 3.37 |
Front-end cycles | 26.00 |
DIV/SQRT cycles | 16.50 |
P0 cycles | 16.50 |
P1 cycles | 18.00 |
P2 cycles | 18.00 |
P3 cycles | 10.00 |
P4 cycles | 16.50 |
P5 cycles | 16.50 |
P6 cycles | 10.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 29.37 |
Stall cycles (UFS) | 3.63 |
Nb insns | 97.00 |
Nb uops | 103.00 |
Nb loads | 36.00 |
Nb stores | 7.00 |
Nb stack references | 19.00 |
FLOP/cycle | 1.62 |
Nb FLOP add-sub | 9.00 |
Nb FLOP mul | 3.00 |
Nb FLOP fma | 15.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 17.54 |
Bytes prefetched | 0.00 |
Bytes loaded | 388.00 |
Bytes stored | 68.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 42.62 |
Vectorization ratio load | 40.00 |
Vectorization ratio store | 42.86 |
Vectorization ratio mul | 50.00 |
Vectorization ratio add_sub | 50.00 |
Vectorization ratio fma | 50.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 31.58 |
Vector-efficiency ratio all | 17.32 |
Vector-efficiency ratio load | 17.29 |
Vector-efficiency ratio store | 15.18 |
Vector-efficiency ratio mul | 18.75 |
Vector-efficiency ratio add_sub | 18.75 |
Vector-efficiency ratio fma | 18.75 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 15.79 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.58 |
CQA speedup if FP arith vectorized | 1.69 |
CQA speedup if fully vectorized | 7.72 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.44 |
Bottlenecks | micro-operation queue, |
Function | void qmcplusplus::expandSuperCell |
Source | ostream:667-667,Tensor.h:213-213,OperatorTags.h:43-183,char_traits.h:409-409,ParticleIOUtility.h:70-91,OhmmsVector.h:223-223,TinyVectorTensorOps.h:150-152,InfoStream.h:37-37 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 26.00 |
CQA cycles if no scalar integer | 16.50 |
CQA cycles if FP arith vectorized | 15.38 |
CQA cycles if fully vectorized | 3.37 |
Front-end cycles | 26.00 |
DIV/SQRT cycles | 16.50 |
P0 cycles | 16.50 |
P1 cycles | 18.00 |
P2 cycles | 18.00 |
P3 cycles | 10.00 |
P4 cycles | 16.50 |
P5 cycles | 16.50 |
P6 cycles | 10.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 29.37 |
Stall cycles (UFS) | 3.63 |
Nb insns | 97.00 |
Nb uops | 103.00 |
Nb loads | 36.00 |
Nb stores | 7.00 |
Nb stack references | 19.00 |
FLOP/cycle | 1.62 |
Nb FLOP add-sub | 9.00 |
Nb FLOP mul | 3.00 |
Nb FLOP fma | 15.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 17.54 |
Bytes prefetched | 0.00 |
Bytes loaded | 388.00 |
Bytes stored | 68.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 42.62 |
Vectorization ratio load | 40.00 |
Vectorization ratio store | 42.86 |
Vectorization ratio mul | 50.00 |
Vectorization ratio add_sub | 50.00 |
Vectorization ratio fma | 50.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 31.58 |
Vector-efficiency ratio all | 17.32 |
Vector-efficiency ratio load | 17.29 |
Vector-efficiency ratio store | 15.18 |
Vector-efficiency ratio mul | 18.75 |
Vector-efficiency ratio add_sub | 18.75 |
Vector-efficiency ratio fma | 18.75 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 15.79 |
Path / |
Function | void qmcplusplus::expandSuperCell |
Source file and lines | ParticleIOUtility.h:70-91 |
Module | exec |
nb instructions | 97 |
nb uops | 103 |
loop length | 545 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 15 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 19 |
ADD-SUB / MUL ratio | 3.00 |
micro-operation queue | 26.00 cycles |
front end | 26.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.50 | 16.50 | 18.00 | 18.00 | 10.00 | 16.50 | 16.50 | 10.00 |
cycles | 16.50 | 16.50 | 18.00 | 18.00 | 10.00 | 16.50 | 16.50 | 10.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 29.37 |
Stall cycles | 3.63 |
LB full (events) | 5.22 |
Front-end | 26.00 |
Dispatch | 18.00 |
Overall L1 | 26.00 |
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 | 50% |
load | 44% |
store | 75% |
mul | 50% |
add-sub | 50% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 40% |
all | 42% |
load | 40% |
store | 42% |
mul | 50% |
add-sub | 50% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 31% |
all | 9% |
load | 10% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 9% |
all | 18% |
load | 18% |
store | 21% |
mul | 18% |
add-sub | 18% |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 17% |
all | 17% |
load | 17% |
store | 15% |
mul | 18% |
add-sub | 18% |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x18,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R15,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45aaf0 | 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 |
CMP %EBX,(%RAX,%R15,4) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVUPD -0x10(%R13),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VROUNDPD $0x9,%XMM0,%XMM1 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VSUBPD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%R13),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VROUNDSD $0x9,%XMM1,%XMM1,%XMM2 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VSUBSD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVDDUP %XMM0,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPERMILPD $0x1,%XMM0,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPERMILPD $0x3,%XMM0,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDDUP %XMM1,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD132PD -0x160(%RBP),%XMM8,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PD -0x150(%RBP),%XMM10,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD %XMM2,%XMM4,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PD -0x140(%RBP),%XMM12,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD %XMM5,%XMM2,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD -0x190(%RBP),%XMM9,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD -0x180(%RBP),%XMM11,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM7,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD -0x170(%RBP),%XMM13,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0xb0(%RSI),%XMM3,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD231SD 0xc8(%RSI),%XMM4,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM1,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0xe0(%RSI),%XMM5,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUCOMISD %XMM6,%XMM0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVUPD 0xb8(%RSI),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xd0(%RSI),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VUNPCKLPD 0xc0(%RSI),%XMM2,%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVHPD 0xd8(%RSI),%XMM1,%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
VMULPD %XMM4,%XMM2,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %XMM1,%XMM3,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVDDUP %XMM5,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD132PD 0xe8(%RSI),%XMM7,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VCMPPD $0x1,%XMM14,%XMM1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
JB 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD 0x3b801(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JAE 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD %XMM6,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JB 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
KMOVD %K0,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
TEST $0x1,%AL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VPERMILPD $0x1,%XMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VUCOMISD %XMM6,%XMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JB 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
KSHIFTRB $0x1,%K0,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 4 | 1 |
KMOVD %K0,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
TEST $0x1,%AL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %EDI,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x1f4,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x496763,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x3b0(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPD %XMM3,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EBX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x6,%AL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVUPD %XMM5,-0x130(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 404580 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x9764a(%RIP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x3b0(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 404160 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x3b0(%RBP),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404340 <_ZSt16__ostream_insertIcSt11char_traitsIcEERSt13basic_ostreamIT_T0_ES6_PKS3_l@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD %R14D,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x5e8(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RAX,2),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPS -0x70(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM0,(%RCX,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD -0x130(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM0,0x10(%RCX,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x5c0(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EBX,(%RCX,%RAX,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x570(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EAX,(%RCX,%RAX,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x598(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15D,(%RCX,%RAX,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%RAX),%EDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x40(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x3b714(%RIP),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD -0xf0(%RBP),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD -0x100(%RBP),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0xa0(%RBP),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD -0x110(%RBP),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0xa8(%RBP),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD -0x120(%RBP),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0xb0(%RBP),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 45ab40 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | void qmcplusplus::expandSuperCell |
Source file and lines | ParticleIOUtility.h:70-91 |
Module | exec |
nb instructions | 97 |
nb uops | 103 |
loop length | 545 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 15 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 19 |
ADD-SUB / MUL ratio | 3.00 |
micro-operation queue | 26.00 cycles |
front end | 26.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.50 | 16.50 | 18.00 | 18.00 | 10.00 | 16.50 | 16.50 | 10.00 |
cycles | 16.50 | 16.50 | 18.00 | 18.00 | 10.00 | 16.50 | 16.50 | 10.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 29.37 |
Stall cycles | 3.63 |
LB full (events) | 5.22 |
Front-end | 26.00 |
Dispatch | 18.00 |
Overall L1 | 26.00 |
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 | 50% |
load | 44% |
store | 75% |
mul | 50% |
add-sub | 50% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 40% |
all | 42% |
load | 40% |
store | 42% |
mul | 50% |
add-sub | 50% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 31% |
all | 9% |
load | 10% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 9% |
all | 18% |
load | 18% |
store | 21% |
mul | 18% |
add-sub | 18% |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 17% |
all | 17% |
load | 17% |
store | 15% |
mul | 18% |
add-sub | 18% |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x18,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R15,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45aaf0 | 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 |
CMP %EBX,(%RAX,%R15,4) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVUPD -0x10(%R13),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VROUNDPD $0x9,%XMM0,%XMM1 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VSUBPD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%R13),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VROUNDSD $0x9,%XMM1,%XMM1,%XMM2 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VSUBSD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVDDUP %XMM0,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPERMILPD $0x1,%XMM0,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPERMILPD $0x3,%XMM0,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDDUP %XMM1,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD132PD -0x160(%RBP),%XMM8,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PD -0x150(%RBP),%XMM10,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD %XMM2,%XMM4,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PD -0x140(%RBP),%XMM12,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD %XMM5,%XMM2,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD -0x190(%RBP),%XMM9,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD -0x180(%RBP),%XMM11,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM7,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD -0x170(%RBP),%XMM13,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0xb0(%RSI),%XMM3,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD231SD 0xc8(%RSI),%XMM4,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM1,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0xe0(%RSI),%XMM5,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUCOMISD %XMM6,%XMM0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVUPD 0xb8(%RSI),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xd0(%RSI),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VUNPCKLPD 0xc0(%RSI),%XMM2,%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVHPD 0xd8(%RSI),%XMM1,%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
VMULPD %XMM4,%XMM2,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %XMM1,%XMM3,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVDDUP %XMM5,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD132PD 0xe8(%RSI),%XMM7,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VCMPPD $0x1,%XMM14,%XMM1,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
JB 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD 0x3b801(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JAE 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD %XMM6,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JB 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
KMOVD %K0,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
TEST $0x1,%AL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VPERMILPD $0x1,%XMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VUCOMISD %XMM6,%XMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JB 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
KSHIFTRB $0x1,%K0,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 4 | 1 |
KMOVD %K0,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
TEST $0x1,%AL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45ab40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %EDI,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x1f4,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x496763,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x3b0(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPD %XMM3,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EBX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x6,%AL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVUPD %XMM5,-0x130(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 404580 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x9764a(%RIP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x3b0(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 404160 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x3b0(%RBP),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404340 <_ZSt16__ostream_insertIcSt11char_traitsIcEERSt13basic_ostreamIT_T0_ES6_PKS3_l@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD %R14D,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x5e8(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RAX,2),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPS -0x70(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM0,(%RCX,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD -0x130(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM0,0x10(%RCX,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x5c0(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EBX,(%RCX,%RAX,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x570(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EAX,(%RCX,%RAX,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x598(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15D,(%RCX,%RAX,4) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%RAX),%EDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x40(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x3b714(%RIP),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD -0xf0(%RBP),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD -0x100(%RBP),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0xa0(%RBP),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD -0x110(%RBP),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0xa8(%RBP),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD -0x120(%RBP),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0xb0(%RBP),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 45ab40 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |