Peter Caday

Results 35 comments of Peter Caday

Hi @jakub-homola, thanks for raising this issue! You're right, the spec should explain which arguments (if any) are allowed to alias. For (non-sparse) BLAS routines, no overlap is allowed between...

make test disable test_device_cpu enable test_device_gpu disable benchdnn_all enable benchdnn_matmul enable benchdnn_ip enable benchdnn_rnn

make test perf-gpu set primitive=matmul ip

make test disable test_device_cpu enable test_device_gpu disable benchdnn_all enable benchdnn_matmul enable benchdnn_ip enable benchdnn_rnn

make test perf-gpu set primitive=matmul ip

Note: the DG2 dynamic quantization regressions reported in perf CI are the same as in #3357, and are not true issues in this PR.

make test disable test_device_cpu enable test_device_gpu disable benchdnn_all enable benchdnn_matmul enable benchdnn_ip enable benchdnn_rnn

make test perf-gpu set primitive=matmul ip

make test disable test_device_cpu enable test_device_gpu disable benchdnn_all enable benchdnn_matmul enable benchdnn_ip enable benchdnn_rnn