Alastair Murray
Alastair Murray
In https://github.com/KhronosGroup/OpenCL-Headers/issues/142 @oddhack says > N.b. you might consider building a Docker image containing all the right components for this. Even just updating the apt database and installing components from...
There are some simple smoke tests in this repo, but only entry points up until OpenCL 1.2 are tested. OpenCL 2.0, 2.1, 2.2, and extensions added in that timeframe are...
Just pulling a small comment on a PR out to an issue so that it does not get lost now that the PR is merged: https://github.com/KhronosGroup/OpenCL-Docs/pull/1018#issuecomment-1841029912 > Related question, the...
Searching for an OpenCL API entry point on Google does not necessarily reach the OpenCL 3.0 reference pages (i.e. the most recent ones, and the ones written to be universal...
The printf testsuite tests the output of `printf("%.6a", 0.1)`: https://github.com/KhronosGroup/OpenCL-CTS/blob/dbd3e787fe4cf977c2da7c58f7505918eb293e6c/test_conformance/printf/util_printf.cpp#L188 This test expects the output from device `printf` to be identical to that of the host `printf`. However, for `%a`...
OpenCL C has a `size_t` type, but the OpenCL C printf [excludes the z format qualifier](https://www.khronos.org/registry/OpenCL/specs/3.0-unified/html/OpenCL_C.html#differences-between-opencl-c-and-c99-printf). This makes it slightly harder to use printf to print things such as `get_global_id(...)`...