coder(anonymous)

icon location Matrix

Results 10 issues of coder(anonymous)

Evaluation

Hello, why didn't I find /build_ scripts/build_ linux_ test.sh ?

For multithreaded GEMM in OpenBLAS, do I need to call API in the program to ensure thread affinity?

4 comment

blas_ API: for sgemm of armv8a, only 4x4 microkernel can be used?

9 comment

BLASFEO: Basic Linear Algebra Subroutines for Embedded Optimization

2 comment

BLASFEO convert matrix format from row-major into panel-major.Whether the cost is calculated in the experiment？

How to use mnemonics to express "prfm pldl1keep, [x1, #256]".

15 comment

What is the matrix size of the convolutional neural network?

ResNet50 performance evaluation

1 comment

Hello! excuse me. DNNL is an excellent work. I want to know the performance of training ResNet-50 on A64FX processor with DNNL. I wonder if you have done this performance...

How can I parallelize the execution of this benchmark? (https://github.com/google/XNNPACK/blob/master/bench/spmm-benchmark.h)

2 comment

The program encounters a segmentation fault when running on 6252N.

[The program encounters a segmentation fault when running on 6252N.](https://github.com/libxsmm/libxsmm/blob/main/samples/deeplearning/sparse_weight_mult/parallel_sparse_weight_B_conv.c)

Hello, is this code used to evaluate the performance of parallelized SPMM (Sparse Matrix-Matrix Multiplication)?

https://github.com/libxsmm/libxsmm/blob/main/samples/deeplearning/sparse_weight_mult/parallel_sparse_weight_B_mult.c