derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
28 lines
1.2 KiB
ReStructuredText
28 lines
1.2 KiB
ReStructuredText
.. meta::
|
|
:description: Learn about hipBLASLt provider operation support in hipDNN.
|
|
:keywords: hipDNN, ROCm, API, hipBLASLt
|
|
|
|
.. _hipblaslt:
|
|
|
|
************************************
|
|
hipBLASLt provider operation support
|
|
************************************
|
|
|
|
The hipBLASLt provider plugin integrates with the ROCm `hipBLASLt library <https://rocm.docs.amd.com/projects/hipBLASLt/en/latest/index.html>`_ that provides optimized GEMM operations.
|
|
|
|
Operation support
|
|
=================
|
|
|
|
The hipBLASLt provider plugin supports standalone Matmul (GEMM, general matrix multiplication) operations with these features and constraints:
|
|
|
|
- Input and output data types:
|
|
|
|
- ``FP32``: Single-precision floating point (32-bit)
|
|
- ``FP16``: Half-precision floating point (16-bit)
|
|
- ``BFP16``: Brain floating point (16-bit).
|
|
|
|
- Compute data type: ``FP32``.
|
|
- Transposed inputs: Supported.
|
|
- Batched matmuls: Only equal batch sizes are supported, along with broadcasting when one input has a single batch (batch=1).
|
|
- Fused operations: Matmul supports fused bias, forward activation (ReLU, clamp, GELU with tanh approximation, and Swish with unit beta), and fused bias + forward activation (same supported activations).
|