onnxruntime
Implement QLinearMul in mlas
#4593
Merged

Implement QLinearMul in mlas #4593

zhanghuanrong merged 9 commits into master from zhalei/qlmul
zhanghuanrong
zhanghuanrong zhanghuanrong requested a review 5 years ago
zhanghuanrong zhanghuanrong requested a review from tracysh tracysh 5 years ago
zhanghuanrong Implement QLinearMul
6089b2b7
zhanghuanrong zhanghuanrong force pushed from 94af793a to 6089b2b7 5 years ago
tracysh
tracysh requested changes on 2020-08-21
zhanghuanrong refactor sse2 code according to pr review.
403ea73a
zhanghuanrong Roll back noneed generalization part at first IsScalarB part.
44869610
zhanghuanrong drafting arm enhance.
0f402a6c
zhanghuanrong pass arm64 build.
9b6598a4
zhanghuanrong Try to descrease the rounding mode difference in arm neon and SSE/AVX...
9a656c94
zhanghuanrong using correct rounding mode on vcvt instructions.
7161508c
zhanghuanrong Fix ARM32 NEON have no vcvtnq instructions issues (Or should we tolerant
060b94d2
zhanghuanrong Let the arm32 use standard C path.
c1ade81b
zhanghuanrong zhanghuanrong requested a review from tracysh tracysh 5 years ago
tracysh
tracysh approved these changes on 2020-09-04
zhanghuanrong zhanghuanrong merged ec88f14a into master 5 years ago
zhanghuanrong zhanghuanrong deleted the zhalei/qlmul branch 5 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone