OpenCL-Docs

OpenCL-Docs copied to clipboard

Command buffers and thread safety

2

Creating a sub-issue based on https://github.com/KhronosGroup/OpenCL-Docs/issues/1309: @joshqti asked: > clUpdateMutableCommandsKHR seems to be defined in a similar manner as clSetKernelArg. Is it not thread safe like clSetKernelArg? Clarification on how...

bashbaug

Does cl_khr_integer_dot_product require OpenCL C 3.0?

7

I'm not sure if this is a Clang issue or an OpenCL spec issue, but I figure I'll start here. It looks like Clang compiles OpenCL kernels that use the...

bashbaug

Change-Id: Id2bc90ca7d9a3c1523080f30f5d6b60cd01d54f2

kpet

From a discussion in the March 18th memory subgroup: Regardless whether we decide to allow any SVM pointer to be set as a kernel argument as part of the unified...

bashbaug

add cl_khr_unified_svm extension

3

This PR contains the draft specification for `cl_khr_unified_svm`. It is intended to provide early access for review and community feedback, and it is not a ratified specification. `cl_khr_unified_svm` adds additional...

bashbaug

Contradictory wording of cl_image_desc specification

1

[Description](https://registry.khronos.org/OpenCL/specs/3.0-unified/html/OpenCL_API.html#image-descriptor) of `image_row_pitch` (the same refers to `image_slice_pitch`) seems mutually contradictory. First spec says: `The image_row_pitch must be zero if ... . If image_row_pitch is zero and the image is...

shajder

setting kernel arguments before recording it in command buffer

2

Currently, the specification for `clCommandNDRangeKernelKHR` says: > _kernel_ is a valid kernel object which **must** have its arguments set. This is indeed true if `cl_khr_command_buffer_mutable_dispatch` is not supported. However, our...

aharon-abramson

printf format string

2

I want to clarify something about `printf`'s `format` argument. The spec says: > The format is in the constant address space and must be resolvable at compile time, i.e. cannot...

aharon-abramson

Confirm clUpdateMutableCommandsKHR error behavior

3

Opening this issue to confirm with implementers that the currently specified error behavior of [clUpdateMutableCommandsKHR](https://registry.khronos.org/OpenCL/specs/3.0-unified/html/OpenCL_API.html#clUpdateMutableCommandsKHR) is what we want. In particular that none of the updates to a command-buffer are...

EwanC

Clarification on importing opaque_fd and dma buf

1

In 5.5.2.1 "File descriptor handle types" it is stated: "For these extensions, importing memory from a file descriptor transfers ownership of the file descriptor from the application to the OpenCL...

joshqti