[SYCL] Add prototype of atomic_ref<T*> #2177
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Enables partial specialization of atomic_ref for pointer types. Implementation assumes that both host and device pointers can be stored in a uintptr_t, but uses compare_exchange to implement pointer arithmetic rather than make assumptions about how pointers will be represented on different devices. Signed-off-by: John Pennycook <[email protected]>
Pennycook
added
enhancement
Triggers a pointer validity check that isn't required here. Signed-off-by: John Pennycook <[email protected]>
alexbatashev
previously approved these changes
Jul 29, 2020
sycl/doc/extensions/README.md
Outdated
| @@ -13,7 +13,7 @@ DPC++ extensions status: | |||
| | [SYCL_INTEL_deduction_guides](deduction_guides/SYCL_INTEL_deduction_guides.asciidoc) | Supported | | | |||
| | [SYCL_INTEL_device_specific_kernel_queries](DeviceSpecificKernelQueries/SYCL_INTEL_device_specific_kernel_queries.asciidoc) | Proposal | | | |||
| | [SYCL_INTEL_enqueue_barrier](EnqueueBarrier/enqueue_barrier.asciidoc) | Supported(OpenCL, Level Zero) | | | |||
| | [SYCL_INTEL_extended_atomics](ExtendedAtomics/SYCL_INTEL_extended_atomics.asciidoc) | Partially supported(OpenCL: CPU, GPU) | Not supported: pointer types | | |||
| | [SYCL_INTEL_extended_atomics](ExtendedAtomics/SYCL_INTEL_extended_atomics.asciidoc) | Supported(OpenCL) | | | |||
There was a problem hiding this comment.
Does it mean FPGAs also gain support for atomic_ref? Should we enable tests on FPGA emulator as well then?
There was a problem hiding this comment.
Ah, no. That's a mistake -- good catch. I should have changed it from "Partially supported" to "Supported", but left the set of supported platforms the same. Fixed in 0c19be3.
Should be fully supported, but only a subset of devices. Signed-off-by: John Pennycook <[email protected]>
Signed-off-by: John Pennycook <[email protected]>
jbrodman
approved these changes
Jul 29, 2020
alexbatashev
approved these changes
Jul 30, 2020
alexbatashev
pushed a commit
to alexbatashev/llvm
that referenced
this pull request
Jul 31, 2020
…rogram * upstream/sycl: [SYCL] Add barrier before leader guard in LowerWGSCope pass (intel#2208) [SYCL] Add prototype of atomic_ref<T*> (intel#2177) Revert "[SYCL] Disallow mutable lambdas (intel#1785)" (intel#2213)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Enables partial specialization of atomic_ref for pointer types.
Implementation assumes that both host and device pointers can be stored
in a uintptr_t, but uses compare_exchange to implement pointer arithmetic
rather than make assumptions about how pointers will be represented on
different devices.
Signed-off-by: John Pennycook [email protected]
There are a few changes in the tests that may not be obvious to reviewers, so capturing those here:
std::numeric_limits<T>::max()isn't defined forT*, but tests only ever required that the sentinel value was outside the range of the group.inttoT*, and the simplest fix was to usesize_tto store the work-item ID in those tests (since it's defined to be asize_tanyway).minandmaxtests mistakenly included comments referencing the pointer specialization, so I removed them -- not addingfetch_minandfetch_maxto the pointer specialization ofatomic_refis deliberate