ppanchad-amd

Results 676 comments of ppanchad-amd

Configuration fails when trying to compile HIPFORT with a CUDA backend

@drtpotter @cgmb Internal ticket has been created to fix documentation. Thanks!

Add GeMM Solver

@iq136boy Is this fixed with latest ROCm 6.0.2 (HIP 6.0.32831)? If resolved, please close ticket. Thanks!

Dedicated primitive (e.g. `Fused`) for fused convolutions?

@DrizztDoUrden Has this been resolved? Thanks!

[Question] Where to delete the dropoutDesc in RNNDescriptor

@junliume Has this issue been resolved? Thanks!

[bug][gfx908] 1x1 convolution failure passing from MIOpen to rocBLAS

@junliume Is this issue fixed with latest ROCm 6.0.2 (HIP 6.0.32831)? Thanks!

Batch norm failure on gfx908

@junliume Is this ticket still relevant? Thanks!

[Tests][fp16] test_bn_3d_spatial_test fails CI test frequently

@junliume Is this ticket still relevant? Thanks!

Do we need many members in PerformanceConfigAsmImplicitGemmGTC?

@carlushuang @shaojiewang Is this fixed with latest ROCm 6.0.2 (HIP 6.0.32831)? If resolved, please close ticket. Thanks!

[gfx90a][COMGR][Fp16][Bf16] Verification errors of ImplicitGemm kernels (no errors with hip-clang)

@atamazov Is this fixed with latest ROCm 6.0.2 (HIP 6.0.32831)? Thanks!

MIOpen cache default location issue

@junliume Created internal ticket to get the MIOpen public documentation fixed. Thanks!