| Commit message (Collapse) | Author | Age |
| |
|
| |
|
| |
|
| |
|
|
|
|
|
|
| |
SSE and AVX are unified.
To this end, I added the following functions: pzero, pcmp_*, pfrexp, pset1frombits functions.
|
| |
|
| |
|
| |
|
| |
|
|\ |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
|/ |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Commit aa110e681b8b2237757a652ba47da49e1fbd2cd6
optimised the multiplication of small dyanmically
sized matrices by restricting the packet size to a maximum of 4, increasing
the chances that SIMD instructions are used in the computation. However, it
introduced a mismatch between the packet size and the requestedAlignment. This
mismatch can lead to crashes when the destination is not aligned. This patch
fixes the issue by ensuring that the AssignmentTraits are correctly computed
when using a restricted packet size.
* * *
Bind LinearPacketType to MaxPacketSize
This commit applies any packet size limit specified when instantiating
copy_using_evaluator_traits to the LinearPacketType, providing that the
size of the destination is not known at compile time.
* * *
Add unit test for restricted packet assignment
A new unit test is added to check that multiplication of small dynamically
sized matrices works correctly when the packet size is restricted to 4 and
the destination is unaligned.
|
| |
|
| |
|
| |
|
| |
|
| |
|
|\
| |
| |
| |
| |
| | |
Add parallel memcpy to TensorThreadPoolDevice in Eigen, but limit the number of threads to 4, beyond which we just seem to be wasting CPU cycles as the threads contend for memory bandwidth.
Approved-by: Eugene Zhulenev <ezhulenev@google.com>
|
| | |
|
| |
| |
| |
| | |
of threads to 4, beyond which we just seem to be wasting CPU cycles as the threads contend for memory bandwidth.
|
|/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
From 68d431b4c14ad60a778ee93c1f59ecc4b931950e Mon Sep 17 00:00:00 2001
Found via `codespell -q 3 -I ../eigen-word-whitelist.txt` where the whitelists consists of:
```
als
ans
cas
dum
lastr
lowd
nd
overfl
pres
preverse
substraction
te
uint
whch
```
---
CMakeLists.txt | 26 +++++++++----------
Eigen/src/Core/GenericPacketMath.h | 2 +-
Eigen/src/SparseLU/SparseLU.h | 2 +-
bench/bench_norm.cpp | 2 +-
doc/HiPerformance.dox | 2 +-
doc/QuickStartGuide.dox | 2 +-
.../Eigen/CXX11/src/Tensor/TensorChipping.h | 6 ++---
.../Eigen/CXX11/src/Tensor/TensorDeviceGpu.h | 2 +-
.../src/Tensor/TensorForwardDeclarations.h | 4 +--
.../src/Tensor/TensorGpuHipCudaDefines.h | 2 +-
.../Eigen/CXX11/src/Tensor/TensorReduction.h | 2 +-
.../CXX11/src/Tensor/TensorReductionGpu.h | 2 +-
.../test/cxx11_tensor_concatenation.cpp | 2 +-
unsupported/test/cxx11_tensor_executor.cpp | 2 +-
14 files changed, 29 insertions(+), 29 deletions(-)
|
|
|
|
| |
about 50% faster than the existing version on Haswell using AVX.
|
| |
|
| |
|
|
|
|
| |
code, and b) supporting matrix exponential on platforms with 113 bits of mantissa for long doubles.
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|\
| |
| |
| | |
Vectorize row-by-row gebp loop iterations on 16 packets as well
|
| | |
|
| |
| |
| |
| |
| | |
Signed-off-by: Gustavo Lima Chaves <gustavo.lima.chaves@intel.com>
Signed-off-by: Mark D. Ryan <mark.d.ryan@intel.com>
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
The Packet16f, Packet8f and Packet8d types are too large to use with dynamically
sized matrices typically processed by the SliceVectorizedTraversal specialization of
the dense_assignment_loop. Using these types is likely to lead to little or no
vectorization. Significant slowdown in the multiplication of these small matrices can
be observed when building with AVX and AVX512 enabled.
This patch introduces a new dense_assignment_kernel that is used when
computing small products whose operands have dynamic dimensions. It ensures that the
PacketSize used is no larger than 4, thereby increasing the chance that vectorized
instructions will be used when computing the product.
I tested all 969 possible combinations of M, K, and N that are handled by the
dense_assignment_loop on x86 builds. Although a few combinations are slowed down
by this patch they are far outnumbered by the cases that are sped up, as the
following results demonstrate.
Disabling Packed8d on AVX512 builds:
Total Cases: 969
Better: 511
Worse: 85
Same: 373
Max Improvement: 169.00% (4 8 6)
Max Degradation: 36.50% (8 5 3)
Median Improvement: 35.46%
Median Degradation: 17.41%
Total FLOPs Improvement: 19.42%
Disabling Packet16f and Packed8f on AVX512 builds:
Total Cases: 969
Better: 658
Worse: 5
Same: 306
Max Improvement: 214.05% (8 6 5)
Max Degradation: 22.26% (16 2 1)
Median Improvement: 60.05%
Median Degradation: 13.32%
Total FLOPs Improvement: 59.58%
Disabling Packed8f on AVX builds:
Total Cases: 969
Better: 663
Worse: 96
Same: 210
Max Improvement: 155.29% (4 10 5)
Max Degradation: 35.12% (8 3 2)
Median Improvement: 34.28%
Median Degradation: 15.05%
Total FLOPs Improvement: 26.02%
|
| | |
|