saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-30 20:18:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

MLAS: update SGEMM threading parameters (#2808)

Browse source
This commit is contained in:
Tracy Sharpe 2020-01-09 14:48:20 -08:00 committed by GitHub
parent 71b5165ed3
commit 7ef6570e27
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 0 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
onnxruntime/core/mlas/lib/mlasi.h
View file

@ -554,21 +554,8 @@ extern "C" {
// Define the target number of per-thread multiplies before using another
// thread to perform additional work.
//
// The number is derived from performance results running SGEMM across a
// range of workloads and observing the ideal number of threads to complete
// that workload.
//
#if defined(_OPENMP)
#define MLAS_SGEMM_THREAD_COMPLEXITY (64 * 1024)
#else
#if defined(MLAS_TARGET_AMD64)
#define MLAS_SGEMM_THREAD_COMPLEXITY (2 * 1024 * 1024)
#else
#define MLAS_SGEMM_THREAD_COMPLEXITY (1 * 1024 * 1024)
#endif
#endif
#define MLAS_DGEMM_THREAD_COMPLEXITY (64 * 1024)
//