[llvm-dev] Missing TargetPrefix for NVVM intrinsics

[Justin Bogner via llvm-dev]

Justin Lebar <jlebar at google.com> writes:
>> @jlebar, any issues on your end with removing all of the non-nvvm intrinsics?
>
> I don't think so, if the functionality is all there from the nvvm
> intrinsics.  Some if it may involve clang changes, which I'm not
> exactly volunteering to do, but they should be simple.

Okay, so if I've understood you both correctly, the attached six patches
should do the trick, for both LLVM and clang. First, they rename the
shfl intrinsics from __builtin_ptx_shfl to __nvvm_shfl. Second,
they replace uses of cuda.syncthreads with nvvm.barrier0. Third, all of
the ptx intrinsics and builtins are removed. Finally, I wrap the nvvm
intrinsics with a TargetPrefix.

Let me know if you want me to break any of these out into specific
review threads on -commits.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: llvm-0001-NVPTX-Make-the-llvm.nvvm.shfl-intrinsics-and-builtin.patch
Type: text/x-patch
Size: 4915 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160705/6012c0af/attachment-0006.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: clang-0001-NVPTX-Rename-__builtin_ptx_shfl-__nvvm_shfl.patch
Type: text/x-patch
Size: 2754 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160705/6012c0af/attachment-0007.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: llvm-0002-NVPTX-Replace-uses-of-cuda.syncthreads-with-nvvm.bar.patch
Type: text/x-patch
Size: 10570 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160705/6012c0af/attachment-0008.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: llvm-0003-NVPTX-Remove-the-legacy-ptx-intrinsics.patch
Type: text/x-patch
Size: 27172 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160705/6012c0af/attachment-0009.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: clang-0002-NVPTX-Remove-the-legacy-ptx-builtins.patch
Type: text/x-patch
Size: 15544 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160705/6012c0af/attachment-0010.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: llvm-0004-IR-Set-a-TargetPrefix-for-nvvm-intrinsics.patch
Type: text/x-patch
Size: 1062 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160705/6012c0af/attachment-0011.bin>
-------------- next part --------------

> On Fri, Jul 1, 2016 at 2:35 PM, Justin Holewinski
> <jholewinski at nvidia.com> wrote:
>> It's all historical, unfortunately. Before NVIDIA open sourced
>> NVPTX, we had the PTX target. The NVPTX target continued to accept
>> the old PTX intrinsics to ease compatibility. That was ~3.2, we can
>> likely just get rid of the PTX intrinsics now. The llvm.cuda
>> intrinsic is an unfortunate naming quirk used internally. This
>> should be handled by llvm.nvvm.bar0, so it should be okay to remove
>> that intrinsic.
>>
>> @jlebar, any issues on your end with removing all of the non-nvvm intrinsics?
>>
>>> On Jul 1, 2016, at 3:01 PM, Justin Bogner <mail at justinbogner.com> wrote:
>>>
>>> Justins:
>>>
>>> I noticed that the intrinsics in IntrinsicsNVVM don't specify a
>>> TargetPrefix. This seems like a simple omission, so I was going to
>>> simply throw a `let TargetPrefix = "nvvm" ` block around them, but this
>>> doesn't quite work.
>>>
>>> There seem to be three prefixes that are used in this file. About 900
>>> are int_nvvm_*, 30 are int_ptx_*, and 1 is int_cuda. It isn't clear to
>>> me if this inconsistency is intentional or warranted - should these all
>>> be named int_nvvm_*? Is there a good reason to differentiate int_ptx_*?
>>> Why does __syncthreads map to int_cuda_syncthreads, rather than
>>> int_nvvm_syncthreads?
>>>
>>> I'm probably going to go ahead and add the TargetPrefix to the nvvm
>>> intrinsics, but I'm not familiar enough with NVPTX to know what to do
>>> with the others.
>>>
>>> Thanks,
>>> -- Justin
>> -----------------------------------------------------------------------------------
>> This email message is for the sole use of the intended recipient(s)
>> and may contain
>> confidential information.  Any unauthorized review, use, disclosure
>> or distribution
>> is prohibited.  If you are not the intended recipient, please
>> contact the sender by
>> reply email and destroy all copies of the original message.
>> -----------------------------------------------------------------------------------