This repo currently contains example Metal shaders (kernels) for performing matrix multiplication on the GPU. Code is included for measuring the performance of the shaders. The fastest one is ...
The multiplication example is here. The example takes value contained in Y as a counter for the loop, decreases it by 1 untill the counter reaches 0. Load Y Subt one Store Y The multiplication fails ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback