ppanchad-amd

Results 676 comments of ppanchad-amd

Measuring time spent for reduction operation in AllReduce.

Hi @jain-jainendra. Internal ticket has been created to assist with your issue. Thanks!

debug build got error: R_X86_64_REX_GOTPCRELX | R_X86_64_PC32 out of range

@ZJLi2013 Internal ticket has been created to investigate this issue. Thanks!

[Issue]: Dependency on msgpack even when -DTensile_LIBRARY_FORMAT=yaml

Hi @trixirt. Internal ticket has been created to investigate this issue. Thanks!

[Issue]: RFE header only install

Hi @trixirt. Internal ticket has been created to assist with your issue. Thanks!

WMMA / RDNA3+ kernels for backwards fused attention?

Hi @Googulator. Internal ticket has been created to assist with your issue. Thanks!

[Issue]: failure of `AMDGPU DAG->DAG Pattern Instruction Selection` due to `llvm.llrint.i64.f32`

@ravil-mobile Internal ticket has been created to investigate this issue. Thanks!

[Issue]: failure of `AMDGPU DAG->DAG Pattern Instruction Selection` due to `llvm.llrint.i64.f32`

Fixed: https://github.com/llvm/llvm-project/pull/98931 - Implement lowering llvm.lrint intrinsic https://github.com/llvm/llvm-project/pull/98970 - Implement lowering of llvm.lround

[MI300A] Understanding hipmemcpy() within the framework of unified memory

Hi @vitduck, an internal ticket has been created to assist with your issue. Thanks!

[Issue]: Tensorflow documentation needs improvments

@briansp2020 Internal ticket has been created to fix the documentation. Thanks!

[Issue]: Memory copy started by dependency signal for pinned memory exhibits race condition

Hi @nstomlinson. Internal ticket has been created to investigate your issue. Thanks!