Loop Id: 1425 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 1.36% |
---|
Loop Id: 1425 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 1.36% |
---|
0x4a50f0 VDIVSD (%R14,%R10,1),%XMM1,%XMM5 [2] |
0x4a50f6 VMOVSD (%RAX,%R9,1),%XMM6 [4] |
0x4a50fc VMOVSD (%R13,%R10,1),%XMM7 [6] |
0x4a5103 VFMADD231SD %XMM5,%XMM0,%XMM6 |
0x4a5108 VMOVSD (%RSI,%R10,1),%XMM8 [5] |
0x4a510e VADDSD %XMM5,%XMM4,%XMM5 |
0x4a5112 VADDSD (%RCX,%R9,1),%XMM5,%XMM5 [3] |
0x4a5118 VFMADD231SD %XMM2,%XMM7,%XMM6 |
0x4a511d VFMADD231SD %XMM3,%XMM8,%XMM6 |
0x4a5122 VDIVSD %XMM5,%XMM6,%XMM5 |
0x4a5126 VADDSD %XMM5,%XMM5,%XMM6 |
0x4a512a VSUBSD %XMM7,%XMM6,%XMM7 |
0x4a512e VMOVSD %XMM5,(%RDX,%R9,1) [1] |
0x4a5134 VMOVSD %XMM7,(%R13,%R10,1) [6] |
0x4a513b VSUBSD %XMM0,%XMM6,%XMM0 |
0x4a513f VSUBSD %XMM8,%XMM6,%XMM5 |
0x4a5144 VMOVSD %XMM5,(%RSI,%R10,1) [5] |
0x4a514a ADD %R15,%R10 |
0x4a514d ADD %RBX,%R9 |
0x4a5150 DEC %R11 |
0x4a5153 JNE 4a50f0 |
/scratch_na/users/xoserete/qaas_runs/171-416-9860/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) { |
/scratch_na/users/xoserete/qaas_runs/171-416-9860/intel/Kripke/build/Kripke/src/Kripke/Kernel/SweepSubdomain.cpp: 87 - 105 |
-------------------------------------------------------------------------------- |
87: double xcos_dxi = 2.0 * xcos(d) / dx(i); |
[...] |
95: + psi_lf(d, g, j, k) * xcos_dxi |
96: + psi_fr(d, g, i, k) * ycos_dyj |
97: + psi_bo(d, g, i, j) * zcos_dzk) |
98: / (xcos_dxi + ycos_dyj + zcos_dzk + sigt(g, z)); |
99: |
100: psi(d, g, z) = psi_d_g_z; |
101: |
102: /* Apply diamond-difference relationships */ |
103: psi_lf(d, g, j, k) = 2.0 * psi_d_g_z - psi_lf(d, g, j, k); |
104: psi_fr(d, g, i, k) = 2.0 * psi_d_g_z - psi_fr(d, g, i, k); |
105: psi_bo(d, g, i, j) = 2.0 * psi_d_g_z - psi_bo(d, g, i, j); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 2.40 |
CQA speedup if fully vectorized | 7.75 - 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | NA |
Bottlenecks | |
Function | void Kripke::DispatchHelper |
Source | forall.hpp:59-59,SweepSubdomain.cpp:87-87,SweepSubdomain.cpp:95-105 |
Source loop unroll info | unrolled by 2 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 31.00 - 33.00 |
CQA cycles if no scalar integer | 31.00 - 33.00 |
CQA cycles if FP arith vectorized | 12.92 - 13.75 |
CQA cycles if fully vectorized | 4.00 - 4.13 |
Front-end cycles | 3.67 |
DIV/SQRT cycles | 3.00 |
P0 cycles | 4.50 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 1.50 |
P4 cycles | 4.00 |
P5 cycles | 1.60 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 1.40 |
P10 cycles | 1.67 |
P11 cycles | 8.00 |
Inter-iter dependencies cycles | 31 - 33 |
FE+BE cycles (UFS) | 31.44 - 33.36 |
Stall cycles (UFS) | 27.09 - 29.01 |
Nb insns | 21.00 |
Nb uops | 20.00 |
Nb loads | 5.00 |
Nb stores | 3.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.45 - 0.42 |
Nb FLOP add-sub | 6.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 3.00 |
Nb FLOP div | 2.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 1.94 - 2.06 |
Bytes prefetched | 0.00 |
Bytes loaded | 40.00 |
Bytes stored | 24.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
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 | 0.00 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 2.40 |
CQA speedup if fully vectorized | 7.75 - 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | NA |
Bottlenecks | |
Function | void Kripke::DispatchHelper |
Source | forall.hpp:59-59,SweepSubdomain.cpp:87-87,SweepSubdomain.cpp:95-105 |
Source loop unroll info | unrolled by 2 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 31.00 - 33.00 |
CQA cycles if no scalar integer | 31.00 - 33.00 |
CQA cycles if FP arith vectorized | 12.92 - 13.75 |
CQA cycles if fully vectorized | 4.00 - 4.13 |
Front-end cycles | 3.67 |
DIV/SQRT cycles | 3.00 |
P0 cycles | 4.50 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 1.50 |
P4 cycles | 4.00 |
P5 cycles | 1.60 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 1.40 |
P10 cycles | 1.67 |
P11 cycles | 8.00 |
Inter-iter dependencies cycles | 31 - 33 |
FE+BE cycles (UFS) | 31.44 - 33.36 |
Stall cycles (UFS) | 27.09 - 29.01 |
Nb insns | 21.00 |
Nb uops | 20.00 |
Nb loads | 5.00 |
Nb stores | 3.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.45 - 0.42 |
Nb FLOP add-sub | 6.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 3.00 |
Nb FLOP div | 2.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 1.94 - 2.06 |
Bytes prefetched | 0.00 |
Bytes loaded | 40.00 |
Bytes stored | 24.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
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 | 0.00 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | NA |
Path / |
Function | void Kripke::DispatchHelper |
Source file and lines | forall.hpp:59-59 |
Module | exec |
nb instructions | 21 |
nb uops | 20 |
loop length | 101 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 9 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.67 cycles |
front end | 3.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.00 | 4.00 | 1.67 | 1.67 | 1.50 | 4.00 | 1.60 | 1.50 | 1.50 | 1.50 | 1.40 | 1.67 |
cycles | 3.00 | 4.50 | 1.67 | 1.67 | 1.50 | 4.00 | 1.60 | 1.50 | 1.50 | 1.50 | 1.40 | 1.67 |
Cycles executing div or sqrt instructions | 8.00 |
Longest recurrence chain latency (RecMII) | 31.00-33.00 |
FE+BE cycles | 31.44-33.36 |
Stall cycles | 27.09-29.01 |
RS full (events) | 30.81-32.75 |
Front-end | 3.67 |
Dispatch | 4.50 |
DIV/SQRT | 8.00 |
Data deps. | 31.00-33.00 |
Overall L1 | 31.00-33.00 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | 0% |
div/sqrt | 0% |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | 12% |
div/sqrt | 12% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VDIVSD (%R14,%R10,1),%XMM1,%XMM5 | 1 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 13-15 | 4 |
VMOVSD (%RAX,%R9,1),%XMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%R13,%R10,1),%XMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD231SD %XMM5,%XMM0,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%RSI,%R10,1),%XMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VADDSD %XMM5,%XMM4,%XMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDSD (%RCX,%R9,1),%XMM5,%XMM5 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VFMADD231SD %XMM2,%XMM7,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM3,%XMM8,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VDIVSD %XMM5,%XMM6,%XMM5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 4 |
VADDSD %XMM5,%XMM5,%XMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSUBSD %XMM7,%XMM6,%XMM7 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVSD %XMM5,(%RDX,%R9,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD %XMM7,(%R13,%R10,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VSUBSD %XMM0,%XMM6,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSUBSD %XMM8,%XMM6,%XMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVSD %XMM5,(%RSI,%R10,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD %R15,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %RBX,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
DEC %R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 4a50f0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x12a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | void Kripke::DispatchHelper |
Source file and lines | forall.hpp:59-59 |
Module | exec |
nb instructions | 21 |
nb uops | 20 |
loop length | 101 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 9 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.67 cycles |
front end | 3.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.00 | 4.00 | 1.67 | 1.67 | 1.50 | 4.00 | 1.60 | 1.50 | 1.50 | 1.50 | 1.40 | 1.67 |
cycles | 3.00 | 4.50 | 1.67 | 1.67 | 1.50 | 4.00 | 1.60 | 1.50 | 1.50 | 1.50 | 1.40 | 1.67 |
Cycles executing div or sqrt instructions | 8.00 |
Longest recurrence chain latency (RecMII) | 31.00-33.00 |
FE+BE cycles | 31.44-33.36 |
Stall cycles | 27.09-29.01 |
RS full (events) | 30.81-32.75 |
Front-end | 3.67 |
Dispatch | 4.50 |
DIV/SQRT | 8.00 |
Data deps. | 31.00-33.00 |
Overall L1 | 31.00-33.00 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | 0% |
div/sqrt | 0% |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | 12% |
div/sqrt | 12% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VDIVSD (%R14,%R10,1),%XMM1,%XMM5 | 1 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 13-15 | 4 |
VMOVSD (%RAX,%R9,1),%XMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%R13,%R10,1),%XMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD231SD %XMM5,%XMM0,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%RSI,%R10,1),%XMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VADDSD %XMM5,%XMM4,%XMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDSD (%RCX,%R9,1),%XMM5,%XMM5 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VFMADD231SD %XMM2,%XMM7,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM3,%XMM8,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VDIVSD %XMM5,%XMM6,%XMM5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 4 |
VADDSD %XMM5,%XMM5,%XMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSUBSD %XMM7,%XMM6,%XMM7 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVSD %XMM5,(%RDX,%R9,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD %XMM7,(%R13,%R10,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VSUBSD %XMM0,%XMM6,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSUBSD %XMM8,%XMM6,%XMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVSD %XMM5,(%RSI,%R10,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD %R15,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %RBX,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
DEC %R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 4a50f0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x12a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |