Loop Id: 300 | Module: exec | Source: TwoBodyJastrowRef.h:107-132 [...] | Coverage: 0.01% |
---|
Loop Id: 300 | Module: exec | Source: TwoBodyJastrowRef.h:107-132 [...] | Coverage: 0.01% |
---|
0x41aa60 VXORPD %XMM1,%XMM1,%XMM1 |
0x41aa64 VMOVSD -0x48(%RBP),%XMM0 |
0x41aa69 VSUBSD %XMM1,%XMM0,%XMM0 |
0x41aa6d CALL 4caa90 <exp> |
0x41aa72 MOV -0x40(%RBP),%RCX |
0x41aa76 MOV (%RCX),%RAX |
0x41aa79 MOV -0x50(%RBP),%RBX |
0x41aa7d VMOVSD %XMM0,(%RAX,%RBX,8) |
0x41aa82 INC %RBX |
0x41aa85 MOV 0x8(%RCX),%RCX |
0x41aa89 SUB %RAX,%RCX |
0x41aa8c SAR $0x3,%RCX |
0x41aa90 CMP %RBX,%RCX |
0x41aa93 MOV -0x38(%RBP),%RDI |
0x41aa97 JBE 41ab7b |
0x41aa9d CMPB $0,0x298(%RDI) |
0x41aaa4 JE 41ab8a |
0x41aaaa MOVSXD 0x2a0(%RDI),%R12 |
0x41aab1 MOV 0xd8(%R15),%RAX |
0x41aab8 VMOVSD (%RAX,%R12,8),%XMM0 |
0x41aabe VMOVSD %XMM0,-0x48(%RBP) |
0x41aac3 MOV 0x290(%RDI),%RAX |
0x41aaca MOV %RAX,-0x30(%RBP) |
0x41aace MOV 0x248(%R15),%ESI |
0x41aad5 CALL 453d50 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi> |
0x41aada MOV 0xa0(%R15),%RCX |
0x41aae1 TEST %RCX,%RCX |
0x41aae4 MOV %RBX,-0x50(%RBP) |
0x41aae8 JE 41aa60 |
0x41aaee MOV 0x48(%RAX),%RAX |
0x41aaf2 LEA (%RBX,%RBX,4),%RDX |
0x41aaf6 MOV 0x18(%RAX,%RDX,8),%R13 |
0x41aafb MOV -0x30(%RBP),%RAX |
0x41aaff MOV 0x18(%RAX),%RAX |
0x41ab03 IMUL (%RAX,%R12,4),%ECX |
0x41ab08 MOVSXD %ECX,%RBX |
0x41ab0b SAL $0x3,%RBX |
0x41ab0f VXORPS %XMM1,%XMM1,%XMM1 |
0x41ab13 MOV $0x1,%R14D |
0x41ab19 NOPL (%RAX) |
(301) 0x41ab20 VMOVSD %XMM1,-0x58(%RBP) |
(301) 0x41ab25 MOV 0x200(%R15),%RAX |
(301) 0x41ab2c ADD %RBX,%RAX |
(301) 0x41ab2f MOV -0x8(%RAX,%R14,8),%RDI |
(301) 0x41ab34 MOV -0x30(%RBP),%RAX |
(301) 0x41ab38 MOV 0x268(%RAX),%RAX |
(301) 0x41ab3f MOV 0x18(%RAX),%RAX |
(301) 0x41ab43 MOV -0x4(%RAX,%R14,4),%EDX |
(301) 0x41ab48 MOV (%RAX,%R14,4),%ECX |
(301) 0x41ab4c MOV 0x1d0(%R15),%R9 |
(301) 0x41ab53 MOV %R12D,%ESI |
(301) 0x41ab56 MOV %R13,%R8 |
(301) 0x41ab59 CALL 417f60 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
(301) 0x41ab5e VMOVSD -0x58(%RBP),%XMM1 |
(301) 0x41ab63 VADDSD %XMM1,%XMM0,%XMM1 |
(301) 0x41ab67 MOV %R14D,%EAX |
(301) 0x41ab6a INC %R14 |
(301) 0x41ab6d CMP %RAX,0xa0(%R15) |
(301) 0x41ab74 JA 41ab20 |
0x41ab76 JMP 41aa64 |
/usr/lib/gcc/x86_64-redhat-linux/8/../../../../include/c++/8/bits/refwrap.h: 313 - 313 |
-------------------------------------------------------------------------------- |
313: { return *_M_data; } |
/usr/lib/gcc/x86_64-redhat-linux/8/../../../../include/c++/8/bits/shared_ptr_base.h: 1308 - 1308 |
-------------------------------------------------------------------------------- |
1308: { return _M_ptr; } |
/scratch_na/users/xoserete/qaas_runs/171-284-5201/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249 |
-------------------------------------------------------------------------------- |
223: return X[i]; |
[...] |
229: return X[i]; |
[...] |
249: inline const_pointer data() const { return X; } |
/scratch_na/users/xoserete/qaas_runs/171-284-5201/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 107 - 132 |
-------------------------------------------------------------------------------- |
107: for (int k = 0; k < ratios.size(); ++k) |
108: ratios[k] = std::exp(Uat[VP.refPtcl] - computeU(VP.getRefPS(), VP.refPtcl, VP.getDistTableAB(myTableID).getDistRow(k).data())); |
[...] |
126: const int igt = P.GroupID[iat] * NumGroups; |
127: for (int jg = 0; jg < NumGroups; ++jg) |
128: { |
129: const FuncType& f2(*F[igt + jg]); |
130: int iStart = P.first(jg); |
131: int iEnd = P.last(jg); |
132: curUat += f2.evaluateV(iat, iStart, iEnd, dist, DistCompressed.data()); |
/usr/lib/gcc/x86_64-redhat-linux/8/../../../../include/c++/8/optional: 897 - 1213 |
-------------------------------------------------------------------------------- |
897: { return this->_M_payload._M_engaged; } |
[...] |
1213: return this->_M_is_engaged() |
/scratch_na/users/xoserete/qaas_runs/171-284-5201/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 313 - 316 |
-------------------------------------------------------------------------------- |
313: inline int first(int igroup) const { return (*group_offsets_)[igroup]; } |
314: |
315: ///return the last index of a group i |
316: inline int last(int igroup) const { return (*group_offsets_)[igroup + 1]; } |
/usr/lib/gcc/x86_64-redhat-linux/8/../../../../include/c++/8/bits/stl_vector.h: 806 - 1056 |
-------------------------------------------------------------------------------- |
806: { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); } |
[...] |
933: return *(this->_M_impl._M_start + __n); |
[...] |
951: return *(this->_M_impl._M_start + __n); |
[...] |
1056: { return _M_data_ptr(this->_M_impl._M_start); } |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.28 |
CQA speedup if FP arith vectorized | 2.69 |
CQA speedup if fully vectorized | 21.90 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.18 |
Bottlenecks | |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | refwrap.h:313-313,OhmmsVector.h:223-223,OhmmsVector.h:229-229,OhmmsVector.h:249-249,TwoBodyJastrowRef.h:107-108,TwoBodyJastrowRef.h:126-127,optional:897-897,optional:1213-1213,stl_vector.h:806-806,stl_vector.h:933-933,stl_vector.h:951-951 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 6.08 |
CQA cycles if no scalar integer | 2.67 |
CQA cycles if FP arith vectorized | 2.27 |
CQA cycles if fully vectorized | 0.28 |
Front-end cycles | 6.08 |
DIV/SQRT cycles | 2.35 |
P0 cycles | 2.15 |
P1 cycles | 5.17 |
P2 cycles | 5.17 |
P3 cycles | 3.00 |
P4 cycles | 2.15 |
P5 cycles | 2.25 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 2.10 |
P10 cycles | 5.17 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 6.55 - 6.55 |
Stall cycles (UFS) | 0.57 |
Nb insns | 34.50 |
Nb uops | 36.50 |
Nb loads | 15.50 |
Nb stores | 4.00 |
Nb stack references | 5.00 |
FLOP/cycle | 0.16 |
Nb FLOP add-sub | 1.00 |
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 | 22.92 |
Bytes prefetched | 0.00 |
Bytes loaded | 107.00 |
Bytes stored | 32.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 5.50 |
Stride indirect | 1.00 |
Vectorization ratio all | 8.39 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 29.17 |
Vector-efficiency ratio all | 11.87 |
Vector-efficiency ratio load | 8.63 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.17 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.47 |
CQA speedup if FP arith vectorized | 2.91 |
CQA speedup if fully vectorized | 24.15 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.17 |
Bottlenecks | micro-operation queue, |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | refwrap.h:313-313,OhmmsVector.h:223-223,OhmmsVector.h:229-229,OhmmsVector.h:249-249,TwoBodyJastrowRef.h:107-108,TwoBodyJastrowRef.h:126-127,optional:897-897,optional:1213-1213,stl_vector.h:806-806,stl_vector.h:933-933,stl_vector.h:951-951 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 7.00 |
CQA cycles if no scalar integer | 2.83 |
CQA cycles if FP arith vectorized | 2.41 |
CQA cycles if fully vectorized | 0.29 |
Front-end cycles | 7.00 |
DIV/SQRT cycles | 2.70 |
P0 cycles | 2.60 |
P1 cycles | 6.00 |
P2 cycles | 6.00 |
P3 cycles | 3.00 |
P4 cycles | 2.60 |
P5 cycles | 2.50 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 2.60 |
P10 cycles | 6.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 7.86 - 7.87 |
Stall cycles (UFS) | 0.96 |
Nb insns | 40.00 |
Nb uops | 42.00 |
Nb loads | 18.00 |
Nb stores | 4.00 |
Nb stack references | 5.00 |
FLOP/cycle | 0.14 |
Nb FLOP add-sub | 1.00 |
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 | 22.43 |
Bytes prefetched | 0.00 |
Bytes loaded | 125.00 |
Bytes stored | 32.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 8.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 7.69 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 25.00 |
Vector-efficiency ratio all | 11.66 |
Vector-efficiency ratio load | 9.06 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 11.33 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.07 |
CQA speedup if FP arith vectorized | 2.43 |
CQA speedup if fully vectorized | 19.45 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.19 |
Bottlenecks | micro-operation queue, |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | refwrap.h:313-313,OhmmsVector.h:223-223,OhmmsVector.h:229-229,OhmmsVector.h:249-249,TwoBodyJastrowRef.h:107-108,TwoBodyJastrowRef.h:126-127,optional:897-897,optional:1213-1213,stl_vector.h:806-806,stl_vector.h:933-933,stl_vector.h:951-951 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.17 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 2.13 |
CQA cycles if fully vectorized | 0.27 |
Front-end cycles | 5.17 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 1.70 |
P1 cycles | 4.33 |
P2 cycles | 4.33 |
P3 cycles | 3.00 |
P4 cycles | 1.70 |
P5 cycles | 2.00 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 1.60 |
P10 cycles | 4.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 5.24 |
Stall cycles (UFS) | 0.19 |
Nb insns | 29.00 |
Nb uops | 31.00 |
Nb loads | 13.00 |
Nb stores | 4.00 |
Nb stack references | 5.00 |
FLOP/cycle | 0.19 |
Nb FLOP add-sub | 1.00 |
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 | 23.42 |
Bytes prefetched | 0.00 |
Bytes loaded | 89.00 |
Bytes stored | 32.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 3.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 9.09 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 33.33 |
Vector-efficiency ratio all | 12.07 |
Vector-efficiency ratio load | 8.20 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 13.02 |
Path / |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:107-132 |
Module | exec |
nb instructions | 34.50 |
nb uops | 36.50 |
loop length | 167.50 |
used x86 registers | 9.50 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 6.08 cycles |
front end | 6.08 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.35 | 2.15 | 5.17 | 5.17 | 3.00 | 2.15 | 2.25 | 3.00 | 3.00 | 3.00 | 2.10 | 5.17 |
cycles | 2.35 | 2.15 | 5.17 | 5.17 | 3.00 | 2.15 | 2.25 | 3.00 | 3.00 | 3.00 | 2.10 | 5.17 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 6.55-6.55 |
Stall cycles | 0.57 |
LM full (events) | 1.55 |
Front-end | 6.08 |
Dispatch | 5.17 |
Data deps. | 0.00 |
Overall L1 | 6.08 |
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 | 16% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 8% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 29% |
all | 9% |
load | 5% |
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 | 6% |
all | 14% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 11% |
load | 8% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:107-132 |
Module | exec |
nb instructions | 40 |
nb uops | 42 |
loop length | 193 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 7.00 cycles |
front end | 7.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.70 | 2.60 | 6.00 | 6.00 | 3.00 | 2.60 | 2.50 | 3.00 | 3.00 | 3.00 | 2.60 | 6.00 |
cycles | 2.70 | 2.60 | 6.00 | 6.00 | 3.00 | 2.60 | 2.50 | 3.00 | 3.00 | 3.00 | 2.60 | 6.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 7.86-7.87 |
Stall cycles | 0.96 |
LM full (events) | 2.18 |
Front-end | 7.00 |
Dispatch | 6.00 |
Data deps. | 0.00 |
Overall L1 | 7.00 |
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 | 16% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 7% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 9% |
load | 6% |
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 | 6% |
all | 14% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 11% |
load | 9% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 11% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD -0x48(%RBP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VSUBSD %XMM1,%XMM0,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
CALL 4caa90 <exp> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV -0x40(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RCX),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x50(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM0,(%RAX,%RBX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x8(%RCX),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
SUB %RAX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
SAR $0x3,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
CMP %RBX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x38(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JBE 41ab7b <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x14b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPB $0,0x298(%RDI) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 41ab8a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x15a> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOVSXD 0x2a0(%RDI),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0xd8(%R15),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM0,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x290(%RDI),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RAX,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x248(%R15),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 453d50 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0xa0(%R15),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %RCX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
MOV %RBX,-0x50(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JE 41aa60 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x30> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x48(%RAX),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RBX,%RBX,4),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x18(%RAX,%RDX,8),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x18(%RAX),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
IMUL (%RAX,%R12,4),%ECX | 1 | 0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD %ECX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
SAL $0x3,%RBX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
VXORPS %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV $0x1,%R14D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 41aa64 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x34> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:107-132 |
Module | exec |
nb instructions | 29 |
nb uops | 31 |
loop length | 142 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 5.17 cycles |
front end | 5.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 1.70 | 4.33 | 4.33 | 3.00 | 1.70 | 2.00 | 3.00 | 3.00 | 3.00 | 1.60 | 4.33 |
cycles | 2.00 | 1.70 | 4.33 | 4.33 | 3.00 | 1.70 | 2.00 | 3.00 | 3.00 | 3.00 | 1.60 | 4.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 5.24 |
Stall cycles | 0.19 |
LM full (events) | 0.91 |
Front-end | 5.17 |
Dispatch | 4.33 |
Data deps. | 0.00 |
Overall L1 | 5.17 |
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 | 16% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 9% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 33% |
all | 9% |
load | 3% |
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 | 7% |
all | 14% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 12% |
load | 8% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 13% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVSD -0x48(%RBP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VSUBSD %XMM1,%XMM0,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
CALL 4caa90 <exp> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV -0x40(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RCX),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x50(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM0,(%RAX,%RBX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x8(%RCX),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
SUB %RAX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
SAR $0x3,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
CMP %RBX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x38(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JBE 41ab7b <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x14b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPB $0,0x298(%RDI) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 41ab8a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x15a> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOVSXD 0x2a0(%RDI),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0xd8(%R15),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM0,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x290(%RDI),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RAX,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x248(%R15),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 453d50 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0xa0(%R15),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %RCX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
MOV %RBX,-0x50(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JE 41aa60 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x30> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |