Andy Kassen comments

Results 9 comments of


                                            Andy Kassen

[WIP] common, xe: adjust stochastic rounding bias alignment

> > The result has an ~3% bias of rounding up, likely related to the distribution of bits generated by the Philox engine, or the seeds generated by the Mersenne...

[WIP] common, xe: adjust stochastic rounding bias alignment

make test disable test_device_cpu disable benchdnn_all enable benchdnn_reorder enable benchdnn_matmul set test_scope=NIGHTLY

[WIP] common, xe: adjust stochastic rounding bias alignment

make test disable test_device_cpu disable benchdnn_all enable benchdnn_reorder enable benchdnn_matmul set test_scope=NIGHTLY

[WIP] common, xe: adjust stochastic rounding bias alignment

make test disable test_device_cpu disable benchdnn_all enable benchdnn_reorder enable benchdnn_matmul set test_scope=NIGHTLY

[WIP] common, xe: adjust stochastic rounding bias alignment

make test disable benchdnn_all enable benchdnn_reorder enable benchdnn_matmul set test_scope=NIGHTLY

[WIP] common, xe: adjust stochastic rounding bias alignment

@mgouicem @vpirogov does it make sense to merge this (+ backport?) to have stochastic rounding in a working state, while a decision is made about what sort of support we...

xe: pooling: avoid register spills in ref impl

make test disable test_device_cpu disable benchdnn_all enable benchdnn_pool

xe: pooling: avoid register spills in ref impl

make test disable test_device_cpu disable benchdnn_all enable benchdnn_pool set test_scope=NIGHTLY

gpu: intel: ocl: add a size guard to stateless addressing flag

make test perf-gpu