Function: miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::ratio( ... | Module: exec | Source: DiracDeterminantRef.cpp:189-206 [...] | Coverage: 0.74% |
---|
Function: miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::ratio( ... | Module: exec | Source: DiracDeterminantRef.cpp:189-206 [...] | Coverage: 0.74% |
---|
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/unique_ptr.h: 199 - 199 |
-------------------------------------------------------------------------------- |
199: pointer _M_ptr() const noexcept { return std::get<0>(_M_t); } |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 178 - 248 |
-------------------------------------------------------------------------------- |
178: inline size_t size() const { return nLocal; } |
[...] |
248: inline pointer data() { return X; } |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp: 81 - 82 |
-------------------------------------------------------------------------------- |
81: for (int i = 0; i < n; i++) |
82: res += a[i] * b[i]; |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp: 189 - 206 |
-------------------------------------------------------------------------------- |
189: { |
190: UpdateMode = ORB_PBYP_RATIO; |
191: const int WorkingIndex = iat - FirstIndex; |
192: SPOVTimer->start(); |
193: Phi->evaluate(P, iat, psiV); |
194: SPOVTimer->stop(); |
195: RatioTimer->start(); |
196: // This is an optimization. |
197: // check invRow_id against WorkingIndex to see if getInvRow() has been called |
198: // This is intended to save redundant compuation in TM1 and TM3 |
199: if (invRow_id != WorkingIndex) |
200: { |
201: invRow_id = WorkingIndex; |
202: updateEng.getInvRow(psiM, WorkingIndex, invRow); |
203: } |
204: curRatio = simd::dot(invRow.data(), psiV.data(), invRow.size()); |
205: RatioTimer->stop(); |
206: return curRatio; |
0x444fe0 PUSH %RBP |
0x444fe1 MOV %RSP,%RBP |
0x444fe4 PUSH %R15 |
0x444fe6 PUSH %R14 |
0x444fe8 PUSH %R12 |
0x444fea PUSH %RBX |
0x444feb MOV %EDX,%R15D |
0x444fee MOV %RSI,%R12 |
0x444ff1 MOV %RDI,%RBX |
0x444ff4 MOVL $0,0xc(%RDI) |
0x444ffb MOV %EDX,%R14D |
0x444ffe SUB 0x478(%RDI),%R14D |
0x445005 MOV 0x460(%RDI),%RDI |
0x44500c CALL 45de10 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> |
0x445011 MOV 0x470(%RBX),%RDI |
0x445018 LEA 0x190(%RBX),%RCX |
0x44501f MOV (%RDI),%RAX |
0x445022 MOV %R12,%RSI |
0x445025 MOV %R15D,%EDX |
0x445028 CALLQ 0x10(%RAX) |
0x44502b MOV 0x460(%RBX),%RDI |
0x445032 CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> |
0x445037 MOV 0x448(%RBX),%RDI |
0x44503e CALL 45de10 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> |
0x445043 CMP %R14D,0x430(%RBX) |
0x44504a JE 445070 |
0x44504c MOV %R14D,0x430(%RBX) |
0x445053 LEA 0x208(%RBX),%RDI |
0x44505a LEA 0xd0(%RBX),%RSI |
0x445061 LEA 0x408(%RBX),%RCX |
0x445068 MOV %R14D,%EDX |
0x44506b CALL 4423b0 <_ZN11qmcplusplus13DelayedUpdateIddE9getInvRowINS_6VectorIdSaIdEEEEEvRKNS_6MatrixIdS4_EEiRT_> |
0x445070 MOV 0x410(%RBX),%RDX |
0x445077 TEST %EDX,%EDX |
0x445079 JLE 4450e5 |
0x44507b MOV 0x420(%RBX),%RAX |
0x445082 MOV 0x1a8(%RBX),%RCX |
0x445089 MOVSXD %EDX,%RSI |
0x44508c MOV %RSI,%RDX |
0x44508f AND $-0x8,%RDX |
0x445093 JE 4450eb |
0x445095 VXORPD %XMM0,%XMM0,%XMM0 |
0x445099 XOR %EDI,%EDI |
0x44509b NOPL (%RAX,%RAX,1) |
(778) 0x4450a0 VMOVUPD (%RCX,%RDI,8),%ZMM1 |
(778) 0x4450a7 VFMADD231PD (%RAX,%RDI,8),%ZMM1,%ZMM0 |
(778) 0x4450ae ADD $0x8,%RDI |
(778) 0x4450b2 CMP %RDX,%RDI |
(778) 0x4450b5 JL 4450a0 |
0x4450b7 VEXTRACTF64X4 $0x1,%ZMM0,%YMM1 |
0x4450be VADDPD %ZMM1,%ZMM0,%ZMM0 |
0x4450c4 VEXTRACTF128 $0x1,%YMM0,%XMM1 |
0x4450ca VADDPD %XMM1,%XMM0,%XMM0 |
0x4450ce VPERMILPD $0x1,%XMM0,%XMM1 |
0x4450d4 VADDSD %XMM1,%XMM0,%XMM0 |
0x4450d8 CMP %RDX,%RSI |
0x4450db JE 445147 |
0x4450dd VPBROADCASTQ %RSI,%ZMM1 |
0x4450e3 JMP 4450f7 |
0x4450e5 VXORPD %XMM0,%XMM0,%XMM0 |
0x4450e9 JMP 445147 |
0x4450eb VPBROADCASTQ %RSI,%ZMM1 |
0x4450f1 VXORPD %XMM0,%XMM0,%XMM0 |
0x4450f5 XOR %EDX,%EDX |
0x4450f7 VPBROADCASTQ %RDX,%ZMM2 |
0x4450fd VPORQ 0x4e739(%RIP),%ZMM2,%ZMM2 |
0x445107 VPCMPLTUQ %ZMM1,%ZMM2,%K1 |
0x44510e VMOVUPD (%RCX,%RDX,8),%ZMM1{%K1}{z} |
0x445115 VMOVUPD (%RAX,%RDX,8),%ZMM2{%K1}{z} |
0x44511c VMULPD %ZMM2,%ZMM1,%ZMM1{%K1}{z} |
0x445122 VEXTRACTF64X4 $0x1,%ZMM1,%YMM2 |
0x445129 VADDPD %ZMM2,%ZMM1,%ZMM1 |
0x44512f VEXTRACTF128 $0x1,%YMM1,%XMM2 |
0x445135 VADDPD %XMM2,%XMM1,%XMM1 |
0x445139 VPERMILPD $0x1,%XMM1,%XMM2 |
0x44513f VADDSD %XMM2,%XMM1,%XMM1 |
0x445143 VADDSD %XMM1,%XMM0,%XMM0 |
0x445147 VMOVSD %XMM0,0x438(%RBX) |
0x44514f MOV 0x448(%RBX),%RDI |
0x445156 VZEROUPPER |
0x445159 CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> |
0x44515e VMOVSD 0x438(%RBX),%XMM0 |
0x445166 POP %RBX |
0x445167 POP %R12 |
0x445169 POP %R14 |
0x44516b POP %R15 |
0x44516d POP %RBP |
0x44516e RET |
0x44516f NOP |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:214 | exec |
○ | main.extracted.104 | stl_vector.h:1126 | exec |
○ | __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 / |
Source file and lines | DiracDeterminantRef.cpp:189-206 |
Module | exec |
nb instructions | 84 |
nb uops | 93 |
loop length | 377 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 3 |
used zmm registers | 3 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 7.00 |
micro-operation queue | 23.25 cycles |
front end | 23.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 10.25 | 10.25 | 12.17 | 11.83 | 14.00 | 10.25 | 10.25 | 12.00 |
cycles | 10.25 | 10.25 | 12.17 | 11.83 | 14.00 | 10.25 | 10.25 | 12.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 21.37 |
Stall cycles | 0.00 |
Front-end | 23.25 |
Dispatch | 14.00 |
Overall L1 | 23.25 |
all | 20% |
load | 33% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 25% |
all | 76% |
load | 66% |
store | 0% |
mul | 100% |
add-sub | 57% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 52% |
load | 50% |
store | 0% |
mul | 100% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 57% |
all | 22% |
load | 37% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 26% |
all | 42% |
load | 70% |
store | 12% |
mul | 100% |
add-sub | 41% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 30% |
all | 33% |
load | 54% |
store | 8% |
mul | 100% |
add-sub | 36% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 27% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EDX,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVL $0,0xc(%RDI) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV %EDX,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB 0x478(%RDI),%R14D | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV 0x460(%RDI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 45de10 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x470(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x190(%RBX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R15D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALLQ 0x10(%RAX) | 3 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 1 | 0.33 | 0 | 4 |
MOV 0x460(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x448(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 45de10 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
CMP %R14D,0x430(%RBX) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 445070 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R14D,0x430(%RBX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x208(%RBX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0xd0(%RBX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x408(%RBX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R14D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4423b0 <_ZN11qmcplusplus13DelayedUpdateIddE9getInvRowINS_6VectorIdSaIdEEEEEvRKNS_6MatrixIdS4_EEiRT_> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x410(%RBX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %EDX,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4450e5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x420(%RBX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x1a8(%RBX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD %EDX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4450eb | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VEXTRACTF64X4 $0x1,%ZMM0,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %ZMM1,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VEXTRACTF128 $0x1,%YMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
CMP %RDX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 445147 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VPBROADCASTQ %RSI,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
JMP 4450f7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 445147 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VPBROADCASTQ %RSI,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPBROADCASTQ %RDX,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPORQ 0x4e739(%RIP),%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPCMPLTUQ %ZMM1,%ZMM2,%K1 | |||||||||||
VMOVUPD (%RCX,%RDX,8),%ZMM1{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMOVUPD (%RAX,%RDX,8),%ZMM2{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMULPD %ZMM2,%ZMM1,%ZMM1{%K1}{z} | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VEXTRACTF64X4 $0x1,%ZMM1,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %ZMM2,%ZMM1,%ZMM1 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VEXTRACTF128 $0x1,%YMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,0x438(%RBX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x448(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD 0x438(%RBX),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | DiracDeterminantRef.cpp:189-206 |
Module | exec |
nb instructions | 84 |
nb uops | 93 |
loop length | 377 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 3 |
used zmm registers | 3 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 7.00 |
micro-operation queue | 23.25 cycles |
front end | 23.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 10.25 | 10.25 | 12.17 | 11.83 | 14.00 | 10.25 | 10.25 | 12.00 |
cycles | 10.25 | 10.25 | 12.17 | 11.83 | 14.00 | 10.25 | 10.25 | 12.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 21.37 |
Stall cycles | 0.00 |
Front-end | 23.25 |
Dispatch | 14.00 |
Overall L1 | 23.25 |
all | 20% |
load | 33% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 25% |
all | 76% |
load | 66% |
store | 0% |
mul | 100% |
add-sub | 57% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 52% |
load | 50% |
store | 0% |
mul | 100% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 57% |
all | 22% |
load | 37% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 26% |
all | 42% |
load | 70% |
store | 12% |
mul | 100% |
add-sub | 41% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 30% |
all | 33% |
load | 54% |
store | 8% |
mul | 100% |
add-sub | 36% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 27% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EDX,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVL $0,0xc(%RDI) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV %EDX,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB 0x478(%RDI),%R14D | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV 0x460(%RDI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 45de10 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x470(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x190(%RBX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R15D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALLQ 0x10(%RAX) | 3 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 1 | 0.33 | 0 | 4 |
MOV 0x460(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x448(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 45de10 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
CMP %R14D,0x430(%RBX) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 445070 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R14D,0x430(%RBX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x208(%RBX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0xd0(%RBX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x408(%RBX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R14D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4423b0 <_ZN11qmcplusplus13DelayedUpdateIddE9getInvRowINS_6VectorIdSaIdEEEEEvRKNS_6MatrixIdS4_EEiRT_> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x410(%RBX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %EDX,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4450e5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x420(%RBX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x1a8(%RBX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD %EDX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4450eb | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VEXTRACTF64X4 $0x1,%ZMM0,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %ZMM1,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VEXTRACTF128 $0x1,%YMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
CMP %RDX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 445147 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VPBROADCASTQ %RSI,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
JMP 4450f7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 445147 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VPBROADCASTQ %RSI,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPBROADCASTQ %RDX,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPORQ 0x4e739(%RIP),%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPCMPLTUQ %ZMM1,%ZMM2,%K1 | |||||||||||
VMOVUPD (%RCX,%RDX,8),%ZMM1{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMOVUPD (%RAX,%RDX,8),%ZMM2{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMULPD %ZMM2,%ZMM1,%ZMM1{%K1}{z} | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VEXTRACTF64X4 $0x1,%ZMM1,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %ZMM2,%ZMM1,%ZMM1 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VEXTRACTF128 $0x1,%YMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,0x438(%RBX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x448(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD 0x438(%RBX),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼miniqmcreference::DiracDeterminantRef | 0.74 | 0 |
○Loop 778 - inner_product.hpp:81-82 - exec | 0.74 | 0 |