Loop Id: 30 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.01% |
---|
Loop Id: 30 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.01% |
---|
0x257510 MOV -0xe0(%RBP),%RDX |
0x257517 INC %RDX |
0x25751a CMP %RDX,-0x38(%RBP) |
0x25751e JE 257490 |
0x257524 MOV -0x60(%RBP),%RCX |
0x257528 MOV %RDX,-0xe0(%RBP) |
0x25752f XOR %ESI,%ESI |
0x257531 LEA (%RDX,%RCX,1),%R11 |
0x257535 MOV -0xd8(%RBP),%RDX |
0x25753c LEA (%RDX,%R11,1),%RCX |
0x257540 IMUL -0xc8(%RBP),%R11 |
0x257548 MOV %RCX,-0x40(%RBP) |
0x25754c ADD -0xd0(%RBP),%R11 |
0x257553 JMP 25758c |
(31) 0x257560 VXORPD %XMM0,%XMM0,%XMM0 |
(31) 0x257564 MOV -0x100(%RBP),%RDI |
(31) 0x25756b LEA (%R11,%RCX,1),%RDX |
(31) 0x25756f ADD %R9,%RCX |
(31) 0x257572 INC %RSI |
(31) 0x257575 VMOVSD (%RDI,%RDX,8),%XMM1 |
(31) 0x25757a VFMADD213SD (%R15,%RCX,8),%XMM0,%XMM1 |
(31) 0x257580 VMOVSD %XMM1,(%R15,%RCX,8) |
(31) 0x257586 CMP -0x48(%RBP),%RSI |
(31) 0x25758a JE 257510 |
(31) 0x25758c MOV -0x68(%RBP),%RCX |
(31) 0x257590 MOV -0x108(%RBP),%RDX |
(31) 0x257597 ADD %RSI,%RCX |
(31) 0x25759a MOVSXD (%RDX,%RCX,4),%R8 |
(31) 0x25759e TEST %R8,%R8 |
(31) 0x2575a1 JLE 257560 |
(31) 0x2575a3 MOV -0xf0(%RBP),%RDX |
(31) 0x2575aa VXORPD %XMM0,%XMM0,%XMM0 |
(31) 0x2575ae MOV (%RDX,%RCX,8),%R10 |
(31) 0x2575b2 MOV -0xf8(%RBP),%RDX |
(31) 0x2575b9 MOV (%RDX,%RAX,8),%RDX |
(31) 0x2575bd ADD %R10,%R8 |
(31) 0x2575c0 IMUL -0xe8(%RBP),%RDX |
(31) 0x2575c8 ADD -0x40(%RBP),%RDX |
(31) 0x2575cc NOPL (%RAX) |
(32) 0x2575d0 MOV (%R14,%R10,8),%RDI |
(32) 0x2575d4 IMUL %R12,%RDI |
(32) 0x2575d8 ADD %RDX,%RDI |
(32) 0x2575db VMOVSD (%R13,%RDI,8),%XMM1 |
(32) 0x2575e2 VFMADD231SD (%RBX,%R10,8),%XMM1,%XMM0 |
(32) 0x2575e8 INC %R10 |
(32) 0x2575eb CMP %R8,%R10 |
(32) 0x2575ee JL 2575d0 |
(31) 0x2575f0 JMP 257564 |
/home/kcamus/qaas_runs/170-247-8274/intel/Kripke/build/Kripke/src/Kripke/Kernel/Scattering.cpp: 88 - 97 |
-------------------------------------------------------------------------------- |
88: MixElem mix_stop = mix_start + zone_to_num_mixelem(z); |
89: |
90: double sigs_z = 0.0; |
91: for(MixElem mix = mix_start;mix < mix_stop;++ mix){ |
92: Material mat = mixelem_to_material(mix); |
93: double fraction = mixelem_to_fraction(mix); |
94: |
95: sigs_z += sigs(mat, n, global_g, global_gp) * fraction; |
96: } |
97: phi_out(nm, g, z) += sigs_z * phi(nm, gp, z); |
/home/kcamus/qaas_runs/170-247-8274/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/IndexValue.hpp: 83 - 217 |
-------------------------------------------------------------------------------- |
83: value++; |
[...] |
217: return (value < x.value); |
/home/kcamus/qaas_runs/170-247-8274/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp: 59 - 59 |
-------------------------------------------------------------------------------- |
59: for (decltype(distance_it) i = 0; i < distance_it; ++i) { |
/home/kcamus/qaas_runs/170-247-8274/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 177 - 177 |
-------------------------------------------------------------------------------- |
177: return value_type(val + rhs); |
/home/kcamus/qaas_runs/170-247-8274/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
/home/kcamus/qaas_runs/170-247-8274/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp: 55 - 55 |
-------------------------------------------------------------------------------- |
55: return a * b; |
/home/kcamus/qaas_runs/170-247-8274/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp: 83 - 83 |
-------------------------------------------------------------------------------- |
83: for (i0 = 0; i0 < l0; ++i0) { |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.57 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.23 |
Bottlenecks | P5, P6, P7, |
Function | .omp_outlined.#0x2572a0 |
Source | forall.hpp:59-59,Collapse.hpp:83-83 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.67 |
CQA cycles if no scalar integer | 2.67 |
CQA cycles if FP arith vectorized | 2.67 |
CQA cycles if fully vectorized | 0.58 |
Front-end cycles | 2.17 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.50 |
P1 cycles | 1.50 |
P2 cycles | 1.50 |
P3 cycles | 1.00 |
P4 cycles | 2.67 |
P5 cycles | 2.67 |
P6 cycles | 2.67 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 14.00 |
Nb uops | 13.00 |
Nb loads | 6.00 |
Nb stores | 2.00 |
Nb stack references | 7.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 48.00 |
Bytes stored | 16.00 |
Stride 0 | 1.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 6.00 |
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 | 0.00 |
Vector-efficiency ratio all | 10.94 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
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 | 9.38 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.57 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.23 |
Bottlenecks | P5, P6, P7, |
Function | .omp_outlined.#0x2572a0 |
Source | forall.hpp:59-59,Collapse.hpp:83-83 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.67 |
CQA cycles if no scalar integer | 2.67 |
CQA cycles if FP arith vectorized | 2.67 |
CQA cycles if fully vectorized | 0.58 |
Front-end cycles | 2.17 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.50 |
P1 cycles | 1.50 |
P2 cycles | 1.50 |
P3 cycles | 1.00 |
P4 cycles | 2.67 |
P5 cycles | 2.67 |
P6 cycles | 2.67 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 14.00 |
Nb uops | 13.00 |
Nb loads | 6.00 |
Nb stores | 2.00 |
Nb stack references | 7.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 48.00 |
Bytes stored | 16.00 |
Stride 0 | 1.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 6.00 |
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 | 0.00 |
Vector-efficiency ratio all | 10.94 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
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 | 9.38 |
Path / |
Function | .omp_outlined.#0x2572a0 |
Source file and lines | forall.hpp:59-59 |
Module | exec |
nb instructions | 14 |
nb uops | 13 |
loop length | 69 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 2.17 cycles |
front end | 2.17 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.50 | 1.50 | 1.50 | 1.00 | 2.67 | 2.67 | 2.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 1.50 | 1.50 | 1.50 | 1.50 | 1.00 | 2.67 | 2.67 | 2.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 2.17 |
Dispatch | 2.67 |
Data deps. | 0.00 |
Overall L1 | 2.67 |
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 | 0% |
all | 10% |
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 | 9% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0xe0(%RBP),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
INC %RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
CMP %RDX,-0x38(%RBP) | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JE 257490 <.omp_outlined.+0x1f0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV %RDX,-0xe0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA (%RDX,%RCX,1),%R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
MOV -0xd8(%RBP),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
LEA (%RDX,%R11,1),%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
IMUL -0xc8(%RBP),%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %RCX,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD -0xd0(%RBP),%R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JMP 25758c <.omp_outlined.+0x2ec> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
Function | .omp_outlined.#0x2572a0 |
Source file and lines | forall.hpp:59-59 |
Module | exec |
nb instructions | 14 |
nb uops | 13 |
loop length | 69 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 2.17 cycles |
front end | 2.17 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.50 | 1.50 | 1.50 | 1.00 | 2.67 | 2.67 | 2.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 1.50 | 1.50 | 1.50 | 1.50 | 1.00 | 2.67 | 2.67 | 2.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 2.17 |
Dispatch | 2.67 |
Data deps. | 0.00 |
Overall L1 | 2.67 |
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 | 0% |
all | 10% |
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 | 9% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0xe0(%RBP),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
INC %RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
CMP %RDX,-0x38(%RBP) | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JE 257490 <.omp_outlined.+0x1f0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV %RDX,-0xe0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA (%RDX,%RCX,1),%R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
MOV -0xd8(%RBP),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
LEA (%RDX,%R11,1),%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
IMUL -0xc8(%RBP),%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %RCX,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD -0xd0(%RBP),%R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JMP 25758c <.omp_outlined.+0x2ec> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |