Loop Id: 243 | Module: exec | Source: TwoBodyJastrowRef.h:266-271 [...] | Coverage: 0.02% |
---|
Loop Id: 243 | Module: exec | Source: TwoBodyJastrowRef.h:266-271 [...] | Coverage: 0.02% |
---|
0x41c810 MOV 0x200(%RBX),%RCX [1] |
0x41c817 ADD -0x40(%RBP),%RCX [5] |
0x41c81b MOV (%RCX,%RAX,8),%RDI [3] |
0x41c81f MOV 0xa98(%R13),%RCX [4] |
0x41c826 MOV %R13,%R14 |
0x41c829 LEA 0x1(%RAX),%R13 |
0x41c82d MOV (%RCX,%RAX,4),%EDX [2] |
0x41c830 MOV 0x4(%RCX,%RAX,4),%ECX [2] |
0x41c834 MOV -0x38(%RBP),%RAX [5] |
0x41c838 CMP %EAX,%ECX |
0x41c83a CMOVGE %EAX,%ECX |
0x41c83d MOV %R15D,%ESI |
0x41c840 MOV %R8,%R12 |
0x41c843 MOV -0x30(%RBP),%R9 [5] |
0x41c847 PUSHQ 0x1e8(%RBX) [1] |
0x41c84d PUSHQ 0x1d0(%RBX) [1] |
0x41c853 PUSH %R11 |
0x41c855 PUSH %R10 |
0x41c857 CALL 41aa40 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi> |
0x41c85c MOV -0x48(%RBP),%R11 [5] |
0x41c860 MOV -0x50(%RBP),%R10 [5] |
0x41c864 MOV %R12,%R8 |
0x41c867 ADD $0x20,%RSP |
0x41c86b MOV %R13,%RAX |
0x41c86e CMP %R13,0xa0(%RBX) [1] |
0x41c875 MOV %R14,%R13 |
0x41c878 JA 41c810 |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 266 - 271 |
-------------------------------------------------------------------------------- |
266: for (int jg = 0; jg < NumGroups; ++jg) |
267: { |
268: const FuncType& f2(*F[igt + jg]); |
269: int iStart = P.first(jg); |
270: int iEnd = std::min(jelmax, P.last(jg)); |
271: f2.evaluateVGL(iat, iStart, iEnd, dist, u, du, d2u, DistCompressed.data(), DistIndice.data()); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 302 - 305 |
-------------------------------------------------------------------------------- |
302: inline int first(int igroup) const { return SubPtcl[igroup]; } |
303: |
304: /// return the last index of a group i |
305: inline int last(int igroup) const { return SubPtcl[igroup + 1]; } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 229 - 229 |
-------------------------------------------------------------------------------- |
229: return X[i]; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:207 | 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 / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 13.50 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.15 |
Bottlenecks | micro-operation queue, |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | TwoBodyJastrowRef.h:266-271,ParticleSet.h:302-305,OhmmsVector.h:229-229 |
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 | 7.50 |
CQA cycles if no scalar integer | 7.50 |
CQA cycles if FP arith vectorized | 7.50 |
CQA cycles if fully vectorized | 0.56 |
Front-end cycles | 7.50 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 2.00 |
P1 cycles | 6.50 |
P2 cycles | 6.50 |
P3 cycles | 5.00 |
P4 cycles | 2.00 |
P5 cycles | 2.00 |
P6 cycles | 5.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 7.38 |
Stall cycles (UFS) | 0.00 |
Nb insns | 27.00 |
Nb uops | 30.00 |
Nb loads | 13.00 |
Nb stores | 0.00 |
Nb stack references | 5.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 12.80 |
Bytes prefetched | 0.00 |
Bytes loaded | 96.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 1.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 10.80 |
Vector-efficiency ratio load | 11.25 |
Vector-efficiency ratio store | NA |
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 | 10.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 13.50 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.15 |
Bottlenecks | micro-operation queue, |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | TwoBodyJastrowRef.h:266-271,ParticleSet.h:302-305,OhmmsVector.h:229-229 |
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 | 7.50 |
CQA cycles if no scalar integer | 7.50 |
CQA cycles if FP arith vectorized | 7.50 |
CQA cycles if fully vectorized | 0.56 |
Front-end cycles | 7.50 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 2.00 |
P1 cycles | 6.50 |
P2 cycles | 6.50 |
P3 cycles | 5.00 |
P4 cycles | 2.00 |
P5 cycles | 2.00 |
P6 cycles | 5.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 7.38 |
Stall cycles (UFS) | 0.00 |
Nb insns | 27.00 |
Nb uops | 30.00 |
Nb loads | 13.00 |
Nb stores | 0.00 |
Nb stack references | 5.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 12.80 |
Bytes prefetched | 0.00 |
Bytes loaded | 96.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 1.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 10.80 |
Vector-efficiency ratio load | 11.25 |
Vector-efficiency ratio store | NA |
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 | 10.00 |
Path / |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:266-271 |
Module | exec |
nb instructions | 27 |
nb uops | 30 |
loop length | 106 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 7.50 cycles |
front end | 7.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 6.50 | 6.50 | 5.00 | 2.00 | 2.00 | 5.00 |
cycles | 2.00 | 2.00 | 6.50 | 6.50 | 5.00 | 2.00 | 2.00 | 5.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 7.38 |
Stall cycles | 0.00 |
Front-end | 7.50 |
Dispatch | 6.50 |
Data deps. | 1.00 |
Overall L1 | 7.50 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 0% |
all | 10% |
load | 11% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 10% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x200(%RBX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD -0x40(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV (%RCX,%RAX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa98(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R13,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA 0x1(%RAX),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%RCX,%RAX,4),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x4(%RCX,%RAX,4),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %EAX,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVGE %EAX,%ECX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R15D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x30(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSHQ 0x1e8(%RBX) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSHQ 0x1d0(%RBX) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R11 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R10 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 41aa40 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x48(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R13,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R13,0xa0(%RBX) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %R14,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JA 41c810 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:266-271 |
Module | exec |
nb instructions | 27 |
nb uops | 30 |
loop length | 106 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 7.50 cycles |
front end | 7.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 6.50 | 6.50 | 5.00 | 2.00 | 2.00 | 5.00 |
cycles | 2.00 | 2.00 | 6.50 | 6.50 | 5.00 | 2.00 | 2.00 | 5.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 7.38 |
Stall cycles | 0.00 |
Front-end | 7.50 |
Dispatch | 6.50 |
Data deps. | 1.00 |
Overall L1 | 7.50 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 0% |
all | 10% |
load | 11% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 10% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x200(%RBX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD -0x40(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV (%RCX,%RAX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa98(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R13,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA 0x1(%RAX),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%RCX,%RAX,4),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x4(%RCX,%RAX,4),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %EAX,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVGE %EAX,%ECX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R15D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x30(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSHQ 0x1e8(%RBX) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSHQ 0x1d0(%RBX) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R11 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R10 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 41aa40 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x48(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R13,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R13,0xa0(%RBX) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %R14,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JA 41c810 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |