Loop Id: 680 | Module: libqmcwfs.so | Source: MultiBsplineRef.hpp:226-262 [...] | Coverage: 0.01% |
---|
Loop Id: 680 | Module: libqmcwfs.so | Source: MultiBsplineRef.hpp:226-262 [...] | Coverage: 0.01% |
---|
0x63bdb MOV -0x1e0(%RBP),%RCX |
0x63be2 MOV -0x1d0(%RBP),%R8 |
0x63be9 MOVQ $0,-0x170(%RBP) |
0x63bf4 MOV %RSI,-0x1b0(%RBP) |
0x63bfb VMOVSD (%R8,%RSI,1),%XMM9 |
0x63c01 VMOVSD (%RCX,%RSI,1),%XMM10 |
0x63c06 MOV %RAX,-0x1b8(%RBP) |
0x63c0d MOV -0x1d8(%RBP),%RCX |
0x63c14 MOV -0x178(%RBP),%R8 |
0x63c1b VMOVSD %XMM9,-0x180(%RBP) |
0x63c23 VMOVSD (%RCX,%RSI,1),%XMM6 |
0x63c28 LEA (%R8,%RAX,1),%RCX |
0x63c2c ADD %RCX,%R8 |
0x63c2f MOV %R8,-0x158(%RBP) |
0x63c36 MOV %RAX,%R8 |
(679) 0x63c39 MOV -0x178(%RBP),%RAX |
(679) 0x63c40 MOV %R8,%RSI |
(679) 0x63c43 VMOVSD -0x180(%RBP),%XMM0 |
(679) 0x63c4b SUB %RAX,%RSI |
(679) 0x63c4e MOV -0x170(%RBP),%RAX |
(679) 0x63c55 MOV %RSI,-0x160(%RBP) |
(679) 0x63c5c MOV -0x190(%RBP),%RSI |
(679) 0x63c63 VMOVSD (%RSI,%RAX,1),%XMM8 |
(679) 0x63c68 MOV -0x1a0(%RBP),%RSI |
(679) 0x63c6f VMOVSD (%RSI,%RAX,1),%XMM11 |
(679) 0x63c74 VMULSD %XMM8,%XMM10,%XMM9 |
(679) 0x63c79 MOV -0x198(%RBP),%RSI |
(679) 0x63c80 VMULSD %XMM0,%XMM8,%XMM14 |
(679) 0x63c84 VMULSD %XMM6,%XMM8,%XMM12 |
(679) 0x63c88 VMULSD %XMM11,%XMM6,%XMM13 |
(679) 0x63c8d VMULSD %XMM0,%XMM11,%XMM8 |
(679) 0x63c91 VMULSD (%RSI,%RAX,1),%XMM6,%XMM15 |
(679) 0x63c96 XOR %EAX,%EAX |
(679) 0x63c98 NOPL (%RAX,%RAX,1) |
(678) 0x63ca0 VMOVSD (%RCX,%RAX,8),%XMM1 |
(678) 0x63ca5 MOV -0x158(%RBP),%RSI |
(678) 0x63cac VMOVHPD (%RSI,%RAX,8),%XMM1,%XMM2 |
(678) 0x63cb1 MOV -0x160(%RBP),%RSI |
(678) 0x63cb8 VMOVSD (%RSI,%RAX,8),%XMM0 |
(678) 0x63cbd VMOVHPD (%R8,%RAX,8),%XMM0,%XMM11 |
(678) 0x63cc3 VINSERTF128 $0x1,%XMM2,%YMM11,%YMM1 |
(678) 0x63cc9 VMULPD %YMM5,%YMM1,%YMM11 |
(678) 0x63ccd VMULPD %YMM4,%YMM1,%YMM2 |
(678) 0x63cd1 VMULPD %YMM3,%YMM1,%YMM1 |
(678) 0x63cd5 VEXTRACTF128 $0x1,%YMM1,%XMM0 |
(678) 0x63cdb VADDPD %XMM1,%XMM0,%XMM1 |
(678) 0x63cdf VUNPCKHPD %XMM1,%XMM1,%XMM0 |
(678) 0x63ce3 VADDPD %XMM1,%XMM0,%XMM1 |
(678) 0x63ce7 VEXTRACTF128 $0x1,%YMM2,%XMM0 |
(678) 0x63ced VADDPD %XMM2,%XMM0,%XMM0 |
(678) 0x63cf1 VUNPCKHPD %XMM0,%XMM0,%XMM2 |
(678) 0x63cf5 VADDPD %XMM0,%XMM2,%XMM0 |
(678) 0x63cf9 VEXTRACTF128 $0x1,%YMM11,%XMM2 |
(678) 0x63cff VADDPD %XMM11,%XMM2,%XMM2 |
(678) 0x63d04 VUNPCKHPD %XMM2,%XMM2,%XMM11 |
(678) 0x63d08 VADDPD %XMM2,%XMM11,%XMM2 |
(678) 0x63d0c VMOVSD %XMM9,%XMM9,%XMM11 |
(678) 0x63d11 VFMADD213SD (%RBX,%RAX,8),%XMM1,%XMM11 |
(678) 0x63d17 VMOVSD %XMM11,(%RBX,%RAX,8) |
(678) 0x63d1c VMOVSD %XMM8,%XMM8,%XMM11 |
(678) 0x63d21 VFMADD213SD (%R14,%RAX,8),%XMM1,%XMM11 |
(678) 0x63d27 VMOVSD %XMM11,(%R14,%RAX,8) |
(678) 0x63d2d VMOVSD %XMM14,%XMM14,%XMM11 |
(678) 0x63d32 VFMADD213SD (%R15,%RAX,8),%XMM0,%XMM11 |
(678) 0x63d38 VMOVSD %XMM11,(%R15,%RAX,8) |
(678) 0x63d3e VMOVSD %XMM15,%XMM15,%XMM11 |
(678) 0x63d43 VFMADD213SD (%R13,%RAX,8),%XMM1,%XMM11 |
(678) 0x63d4a VMOVSD %XMM11,(%R13,%RAX,8) |
(678) 0x63d51 VMOVSD %XMM13,%XMM13,%XMM11 |
(678) 0x63d56 VFMADD213SD (%R9,%RAX,8),%XMM0,%XMM11 |
(678) 0x63d5c VMOVSD %XMM11,(%R9,%RAX,8) |
(678) 0x63d62 VFMADD213SD (%R11,%RAX,8),%XMM12,%XMM2 |
(678) 0x63d68 VMOVSD %XMM13,%XMM13,%XMM11 |
(678) 0x63d6d VMOVSD %XMM2,(%R11,%RAX,8) |
(678) 0x63d73 VMOVSD %XMM14,%XMM14,%XMM2 |
(678) 0x63d77 VFMADD213SD (%RDI,%RAX,8),%XMM1,%XMM2 |
(678) 0x63d7d VMOVSD %XMM2,(%RDI,%RAX,8) |
(678) 0x63d82 VFMADD213SD (%R12,%RAX,8),%XMM1,%XMM11 |
(678) 0x63d88 VFMADD213SD (%RDX,%RAX,8),%XMM12,%XMM1 |
(678) 0x63d8e VMOVSD %XMM11,(%R12,%RAX,8) |
(678) 0x63d94 VFMADD213SD (%R10,%RAX,8),%XMM12,%XMM0 |
(678) 0x63d9a VMOVSD %XMM1,(%RDX,%RAX,8) |
(678) 0x63d9f VMOVSD %XMM0,(%R10,%RAX,8) |
(678) 0x63da5 INC %RAX |
(678) 0x63da8 CMP %RAX,-0x168(%RBP) |
(678) 0x63daf JNE 63ca0 |
(679) 0x63db5 MOV -0x188(%RBP),%RAX |
(679) 0x63dbc ADDQ $0x8,-0x170(%RBP) |
(679) 0x63dc4 MOV -0x170(%RBP),%RSI |
(679) 0x63dcb ADD %RAX,-0x158(%RBP) |
(679) 0x63dd2 ADD %RAX,%R8 |
(679) 0x63dd5 ADD %RAX,%RCX |
(679) 0x63dd8 CMP $0x20,%RSI |
(679) 0x63ddc JNE 63c39 |
0x63de2 MOV -0x1b0(%RBP),%RSI |
0x63de9 MOV -0x1b8(%RBP),%RAX |
0x63df0 MOV -0x1c8(%RBP),%RCX |
0x63df7 ADD $0x8,%RSI |
0x63dfb ADD %RCX,%RAX |
0x63dfe CMP $0x20,%RSI |
0x63e02 JNE 63bdb |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp: 226 - 262 |
-------------------------------------------------------------------------------- |
226: for (int i = 0; i < 4; i++) |
227: for (int j = 0; j < 4; j++) |
228: { |
229: const T* restrict coefs = spline_m->coefs + (ix + i) * xs + (iy + j) * ys + iz * zs; |
230: const T* restrict coefszs = coefs + zs; |
231: const T* restrict coefs2zs = coefs + 2 * zs; |
232: const T* restrict coefs3zs = coefs + 3 * zs; |
233: |
234: const T pre20 = d2a[i] * b[j]; |
235: const T pre10 = da[i] * b[j]; |
236: const T pre00 = a[i] * b[j]; |
237: const T pre11 = da[i] * db[j]; |
238: const T pre01 = a[i] * db[j]; |
239: const T pre02 = a[i] * d2b[j]; |
240: |
241: const int iSplitPoint = num_splines; |
242: for (int n = 0; n < iSplitPoint; n++) |
[...] |
249: T sum0 = c[0] * coefsv + c[1] * coefsvzs + c[2] * coefsv2zs + c[3] * coefsv3zs; |
250: T sum1 = dc[0] * coefsv + dc[1] * coefsvzs + dc[2] * coefsv2zs + dc[3] * coefsv3zs; |
251: T sum2 = d2c[0] * coefsv + d2c[1] * coefsvzs + d2c[2] * coefsv2zs + d2c[3] * coefsv3zs; |
252: |
253: hxx[n] += pre20 * sum0; |
254: hxy[n] += pre11 * sum0; |
255: hxz[n] += pre10 * sum1; |
256: hyy[n] += pre02 * sum0; |
257: hyz[n] += pre01 * sum1; |
258: hzz[n] += pre00 * sum2; |
259: gx[n] += pre10 * sum0; |
260: gy[n] += pre01 * sum0; |
261: gz[n] += pre00 * sum1; |
262: vals[n] += pre00 * sum0; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►93.47+ | miniqmcreference::einspline_sp[...] | einspline_spo_ref.hpp:206 | libqmcwfs.so |
○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:100 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:198 | libqmcwfs.so |
○ | main._omp_fn.1 | refwrap.h:346 | exec |
○ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
►3.52+ | miniqmcreference::einspline_sp[...] | einspline_spo_ref.hpp:206 | libqmcwfs.so |
○ | qmcplusplus::SPOSet::evaluate_[...] | OhmmsVector.h:210 | libqmcwfs.so |
○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:263 | libqmcwfs.so |
○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:238 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:171 | libqmcwfs.so |
○ | main._omp_fn.0 | miniqmc.cpp:397 | exec |
○ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
►2.01+ | miniqmcreference::einspline_sp[...] | einspline_spo_ref.hpp:206 | libqmcwfs.so |
○ | qmcplusplus::SPOSet::evaluate_[...] | OhmmsVector.h:210 | libqmcwfs.so |
○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:263 | libqmcwfs.so |
○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:238 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:171 | libqmcwfs.so |
○ | main._omp_fn.0 | miniqmc.cpp:397 | exec |
○ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
►1.00+ | miniqmcreference::einspline_sp[...] | einspline_spo_ref.hpp:206 | libqmcwfs.so |
○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:100 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:198 | libqmcwfs.so |
○ | main._omp_fn.1 | refwrap.h:346 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.63 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.14 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | micro-operation queue, |
Function | void miniqmcreference::MultiBsplineEvalRef::evaluate_vgh |
Source | MultiBsplineRef.hpp:226-226,MultiBsplineRef.hpp:234-236 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.50 |
CQA cycles if no scalar integer | 1.33 |
CQA cycles if FP arith vectorized | 3.50 |
CQA cycles if fully vectorized | 0.29 |
Front-end cycles | 3.50 |
DIV/SQRT cycles | 0.70 |
P0 cycles | 0.60 |
P1 cycles | 3.33 |
P2 cycles | 3.33 |
P3 cycles | 2.50 |
P4 cycles | 0.60 |
P5 cycles | 0.50 |
P6 cycles | 2.50 |
P7 cycles | 2.50 |
P8 cycles | 2.50 |
P9 cycles | 0.60 |
P10 cycles | 3.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 3.67 |
Stall cycles (UFS) | 0.01 |
Nb insns | 22.00 |
Nb uops | 21.00 |
Nb loads | 10.00 |
Nb stores | 5.00 |
Nb stack references | 10.00 |
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 | 34.29 |
Bytes prefetched | 0.00 |
Bytes loaded | 80.00 |
Bytes stored | 40.00 |
Stride 0 | 1.00 |
Stride 1 | 12.00 |
Stride n | 2.00 |
Stride unknown | 2.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 11.72 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 11.25 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.63 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.14 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | micro-operation queue, |
Function | void miniqmcreference::MultiBsplineEvalRef::evaluate_vgh |
Source | MultiBsplineRef.hpp:226-226,MultiBsplineRef.hpp:234-236 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.50 |
CQA cycles if no scalar integer | 1.33 |
CQA cycles if FP arith vectorized | 3.50 |
CQA cycles if fully vectorized | 0.29 |
Front-end cycles | 3.50 |
DIV/SQRT cycles | 0.70 |
P0 cycles | 0.60 |
P1 cycles | 3.33 |
P2 cycles | 3.33 |
P3 cycles | 2.50 |
P4 cycles | 0.60 |
P5 cycles | 0.50 |
P6 cycles | 2.50 |
P7 cycles | 2.50 |
P8 cycles | 2.50 |
P9 cycles | 0.60 |
P10 cycles | 3.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 3.67 |
Stall cycles (UFS) | 0.01 |
Nb insns | 22.00 |
Nb uops | 21.00 |
Nb loads | 10.00 |
Nb stores | 5.00 |
Nb stack references | 10.00 |
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 | 34.29 |
Bytes prefetched | 0.00 |
Bytes loaded | 80.00 |
Bytes stored | 40.00 |
Stride 0 | 1.00 |
Stride 1 | 12.00 |
Stride n | 2.00 |
Stride unknown | 2.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 11.72 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 11.25 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | void miniqmcreference::MultiBsplineEvalRef::evaluate_vgh |
Source file and lines | MultiBsplineRef.hpp:226-262 |
Module | libqmcwfs.so |
nb instructions | 22 |
nb uops | 21 |
loop length | 132 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 10 |
micro-operation queue | 3.50 cycles |
front end | 3.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.70 | 0.60 | 3.33 | 3.33 | 2.50 | 0.60 | 0.50 | 2.50 | 2.50 | 2.50 | 0.60 | 3.33 |
cycles | 0.70 | 0.60 | 3.33 | 3.33 | 2.50 | 0.60 | 0.50 | 2.50 | 2.50 | 2.50 | 0.60 | 3.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 3.67 |
Stall cycles | 0.01 |
LM full (events) | 0.03 |
Front-end | 3.50 |
Dispatch | 3.33 |
Data deps. | 0.00 |
Overall L1 | 3.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 10% |
load | NA (no load vectorizable/vectorized instructions) |
store | 10% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 11% |
load | 12% |
store | 11% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x1e0(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1d0(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVQ $0,-0x170(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RSI,-0x1b0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%RSI,1),%XMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%RCX,%RSI,1),%XMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RAX,-0x1b8(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x1d8(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x178(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM9,-0x180(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%RCX,%RSI,1),%XMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%R8,%RAX,1),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
ADD %RCX,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %R8,-0x158(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x1b0(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1b8(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1c8(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD $0x8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD %RCX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP $0x20,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 63bdb <_ZN16miniqmcreference19MultiBsplineEvalRef12evaluate_vghIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_S9_S9_m+0x42b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | void miniqmcreference::MultiBsplineEvalRef::evaluate_vgh |
Source file and lines | MultiBsplineRef.hpp:226-262 |
Module | libqmcwfs.so |
nb instructions | 22 |
nb uops | 21 |
loop length | 132 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 10 |
micro-operation queue | 3.50 cycles |
front end | 3.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.70 | 0.60 | 3.33 | 3.33 | 2.50 | 0.60 | 0.50 | 2.50 | 2.50 | 2.50 | 0.60 | 3.33 |
cycles | 0.70 | 0.60 | 3.33 | 3.33 | 2.50 | 0.60 | 0.50 | 2.50 | 2.50 | 2.50 | 0.60 | 3.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 3.67 |
Stall cycles | 0.01 |
LM full (events) | 0.03 |
Front-end | 3.50 |
Dispatch | 3.33 |
Data deps. | 0.00 |
Overall L1 | 3.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 10% |
load | NA (no load vectorizable/vectorized instructions) |
store | 10% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 11% |
load | 12% |
store | 11% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x1e0(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1d0(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVQ $0,-0x170(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RSI,-0x1b0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%RSI,1),%XMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%RCX,%RSI,1),%XMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RAX,-0x1b8(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x1d8(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x178(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM9,-0x180(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%RCX,%RSI,1),%XMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%R8,%RAX,1),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
ADD %RCX,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %R8,-0x158(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x1b0(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1b8(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1c8(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD $0x8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD %RCX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP $0x20,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 63bdb <_ZN16miniqmcreference19MultiBsplineEvalRef12evaluate_vghIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_S9_S9_m+0x42b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |