[PATCH] D36327: [OpenCL] Allow targets emit optimized pipe functions for power of 2 type sizes

[Yaxun Liu via Phabricator via cfe-commits]

yaxunl created this revision.
Herald added a subscriber: tpr.

Currently Clang emits call of __read_pipe_2 or __read_pipe_4 for OpenCL read_pipe builtin,
with appended type size and alignment arguments, where 2 or 4 indicates the original
number of arguments.

For certain targets (e.g. amdgpu), there are optimized version of __read_pipe_2/__read_pipe_4
when the type size and alignment has the same power of 2 value. It is desired that Clang
emits a different function for these cases.

This patch let Clang emits __read_pipe_2_N for such cases where N is the size in bytes of
the type. (N = 1,2,4,8,...,128), so that the target runtime can use an optimized version of
read_pipe.

The same with __read_pipe_4, __write_pipe_2 and __wirte_pipe_4.

This optimization is controlled by TargetCodeGenInfo::hasOptimizedPipeBuiltin, which returns
false by default. Each target can override this function to turn on this optimization.


https://reviews.llvm.org/D36327

Files:
  lib/CodeGen/CGBuiltin.cpp
  lib/CodeGen/TargetInfo.cpp
  lib/CodeGen/TargetInfo.h
  test/CodeGenOpenCL/pipe_builtin.cl

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D36327.109764.patch
Type: text/x-patch
Size: 15320 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20170804/c5473cb9/attachment-0001.bin>