onnxruntime
[MLAS] AVX-512 16-wide Erf kernel and NCHWc reorder transpose for MobileClip-S0 model
#31958

Merged

[MLAS] AVX-512 16-wide Erf kernel and NCHWc reorder transpose for MobileClip-S0 model #31958

mirounga merged 5 commits into microsoft:main from swetha097:swe_fork/perf/mlas-mobileclip-opt

hariharans29 changed the title ~~AVX-512 16-wide Erf kernel and NCHWc reorder transpose for MobileClip-S0 model~~ [MLAS] AVX-512 16-wide Erf kernel and NCHWc reorder transpose for MobileClip-S0 model 22 days ago

hariharans29 requested a review from

copilot-pull-request-reviewer 22 days ago

copilot-pull-request-reviewer commented on 2026-08-11

mirounga requested a review from

mirounga 16 days ago

swetha097 force pushed from 1046c071 to 7aa07779 15 days ago

[MLAS] AVX-512 16-wide Erf kernel and NCHWc reorder transpose for Mob…

01737bf9

Add MLAS unit tests for the MobileClip-S0 AVX-512 kernels

e3cb510e

Strengthen Erf unit test with direct base-kernel comparison

a8ae744a

Address review comments on reorder_avx512f

2385c09c

test_erf: guard AVX-512/FMA3 kernel helpers with MLAS_TARGET_AMD64

93b47735

swetha097 force pushed from 7aa07779 to 93b47735 15 days ago

mirounga enabled auto-merge (squash) 12 days ago

mirounga approved these changes on 2026-08-21

mirounga merged a88c1168 into main 12 days ago

Reviewers

mirounga

copilot-pull-request-reviewer

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

onnxruntime [MLAS] AVX-512 16-wide Erf kernel and NCHWc reorder transpose for MobileClip-S0 model #31958 Merged

[MLAS] AVX-512 16-wide Erf kernel and NCHWc reorder transpose for MobileClip-S0 model #31958

onnxruntime
[MLAS] AVX-512 16-wide Erf kernel and NCHWc reorder transpose for MobileClip-S0 model
#31958

Merged