This is an archive of the discontinued LLVM Phabricator instance.

[AMDGPU] Define code object identification string used in AMDHSA runtimes.
ClosedPublic

Authored by t-tye on Mar 20 2018, 4:16 PM.

Download Raw Diff

Details

Reviewers

kzhuravl
b-sumner

Commits

rG01bfd6c4e5c4: [AMDGPU] Define code object identification string used in AMDHSA runtimes.
rL328669: [AMDGPU] Define code object identification string used in AMDHSA runtimes.

Diff Detail

Event Timeline

t-tye created this revision.Mar 20 2018, 4:16 PM

Herald added subscribers: tpr, dstuttard, yaxunl and 2 others. · View Herald TranscriptMar 20 2018, 4:16 PM

LGTM

This revision is now accepted and ready to land.Mar 21 2018, 3:48 PM

Change target feature element of the target identification string to be comma separated so hyphens only delimit the elements.

LGTM.

LGTM, but I'd rather use '+' instead of ',' for the features.

Change syntax for target features to be concatenated to Processor using a plus prefix for each target feature.

In D44718#1047028, @b-sumner wrote:

LGTM, but I'd rather use '+' instead of ',' for the features.

Changed to use + prefix as suggested by Laurent.

LGTM

kzhuravl added inline comments.Mar 23 2018, 1:24 PM

docs/AMDGPUUsage.rst
941	I'd rather have a '-' separator, as it would be easier to tokenize.

Closed by commit rL328669: [AMDGPU] Define code object identification string used in AMDHSA runtimes. (authored by t-tye). · Explain WhyMar 27 2018, 2:25 PM

This revision was automatically updated to reflect the committed changes.

Revision Contents

Path

Size

docs/

AMDGPUUsage.rst

22 lines

Diff 139220

docs/AMDGPUUsage.rst

	Show First 20 Lines • Show All 906 Lines • ▼ Show 20 Lines
	AMDHSA			AMDHSA
	------			------

	This section provides code conventions used when the target triple OS is			This section provides code conventions used when the target triple OS is
	``amdhsa`` (see :ref:`amdgpu-target-triples`).			``amdhsa`` (see :ref:`amdgpu-target-triples`).

	.. _amdgpu-amdhsa-hsa-code-object-metadata:			.. _amdgpu-amdhsa-hsa-code-object-metadata:

				Code Object Target Identification
				~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

				The AMDHSA OS uses the following syntax to specify the code object
				target as a single string:

				``<Architecture>-<Vendor>-<OS>-<Environment>-<Processor>-<Target Features>``

				Where the first four components are the same as the Target Triple
				(see :ref:`amdgpu-target-triples`), the next component is the same as
				the Processor (see :ref:`amdgpu-processors`) and the last component
				is a hyphen separated list of the enabled Target Features that apply
				to Processor in the same order as listed in the table
				:ref:`amdgpu-target-feature-table` (see
				:ref:`amdgpu-target-features`). Note that Target Features must be
				included in the list if they are enabled even if that is the default for
				Processor.

				For example:

				``"amdgcn-amd-amdhsa--gfx902-xnack"``

	Code Object Metadata			Code Object Metadata
	~~~~~~~~~~~~~~~~~~~~			~~~~~~~~~~~~~~~~~~~~

	The code object metadata specifies extensible metadata associated with the code			The code object metadata specifies extensible metadata associated with the code
	objects executed on HSA [HSA]_ compatible runtimes such as AMD's ROCm			objects executed on HSA [HSA]_ compatible runtimes such as AMD's ROCm
				kzhuravlUnsubmitted Not Done Reply Inline Actions I'd rather have a '-' separator, as it would be easier to tokenize. kzhuravl: I'd rather have a '-' separator, as it would be easier to tokenize.
	[AMD-ROCm]_. It is specified by the ``NT_AMD_AMDGPU_HSA_METADATA`` note record			[AMD-ROCm]_. It is specified by the ``NT_AMD_AMDGPU_HSA_METADATA`` note record
	(see :ref:`amdgpu-note-records`) and is required when the target triple OS is			(see :ref:`amdgpu-note-records`) and is required when the target triple OS is
	``amdhsa`` (see :ref:`amdgpu-target-triples`). It must contain the minimum			``amdhsa`` (see :ref:`amdgpu-target-triples`). It must contain the minimum
	information necessary to support the ROCM kernel queries. For example, the			information necessary to support the ROCM kernel queries. For example, the
	segment sizes needed in a dispatch packet. In addition, a high level language			segment sizes needed in a dispatch packet. In addition, a high level language
	runtime may require other information to be included. For example, the AMD			runtime may require other information to be included. For example, the AMD
	OpenCL runtime records kernel argument information.			OpenCL runtime records kernel argument information.

	▲ Show 20 Lines • Show All 3,234 Lines • Show Last 20 Lines