[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-12 Thread Konstantin Zhuravlyov via cfe-commits
This revision was automatically updated to reflect the committed changes. Closed by commit rL286741: [AMDGPU] Add f16 builtin functions (VI+) (authored by kzhuravl). Changed prior to commit: https://reviews.llvm.org/D26476?vs=77654&id=77732#toc Repository: rL LLVM https://reviews.llvm.org/D

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-11 Thread Matt Arsenault via cfe-commits
arsenm accepted this revision. arsenm added a comment. This revision is now accepted and ready to land. LGTM https://reviews.llvm.org/D26476 ___ cfe-commits mailing list cfe-commits@lists.llvm.org http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-c

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-11 Thread Konstantin Zhuravlyov via cfe-commits
kzhuravl updated this revision to Diff 77654. kzhuravl added a comment. Leave the return type of `frexp_exph` unchanged https://reviews.llvm.org/D26476 Files: include/clang/Basic/BuiltinsAMDGPU.def lib/CodeGen/CGBuiltin.cpp test/CodeGenOpenCL/builtins-amdgcn-error.cl test/CodeGenOpenCL/

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-11 Thread Konstantin Zhuravlyov via cfe-commits
kzhuravl updated this revision to Diff 77634. kzhuravl added a comment. Also update run line to exclude `amdhsa` from another error file. https://reviews.llvm.org/D26476 Files: include/clang/Basic/BuiltinsAMDGPU.def lib/CodeGen/CGBuiltin.cpp test/CodeGenOpenCL/builtins-amdgcn-error.cl t

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-11 Thread Konstantin Zhuravlyov via cfe-commits
kzhuravl updated this revision to Diff 77633. kzhuravl marked 4 inline comments as done. kzhuravl added a comment. Address review feedback: put tests in the same file, update run line, move error tests to SemaOpenCL directory https://reviews.llvm.org/D26476 Files: include/clang/Basic/Builtin

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-11 Thread Yaxun Liu via cfe-commits
yaxunl added inline comments. Comment at: test/CodeGenOpenCL/builtins-amdgcn-error-f16-div-fixup.cl:8 +{ + *out = __builtin_amdgcn_div_fixuph(a, b, c); // expected-error {{'__builtin_amdgcn_div_fixuph' needs target feature 16-bit-insts}} +} The tests for checki

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-11 Thread Matt Arsenault via cfe-commits
arsenm added inline comments. Comment at: test/CodeGenOpenCL/builtins-amdgcn-error-f16-class.cl:1-9 +// REQUIRES: amdgpu-registered-target +// RUN: %clang_cc1 -triple amdgcn-unknown-amdhsa -target-cpu tahiti -verify -S -o - %s + +#pragma OPENCL EXTENSION cl_khr_fp16 : enable + +

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-11 Thread Konstantin Zhuravlyov via cfe-commits
kzhuravl added inline comments. Comment at: test/CodeGenOpenCL/builtins-amdgcn-error-f16-class.cl:1-9 +// REQUIRES: amdgpu-registered-target +// RUN: %clang_cc1 -triple amdgcn-unknown-amdhsa -target-cpu tahiti -verify -S -o - %s + +#pragma OPENCL EXTENSION cl_khr_fp16 : enable +

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-11 Thread Matt Arsenault via cfe-commits
arsenm added inline comments. Comment at: test/CodeGenOpenCL/builtins-amdgcn-error-f16-class.cl:1-9 +// REQUIRES: amdgpu-registered-target +// RUN: %clang_cc1 -triple amdgcn-unknown-amdhsa -target-cpu tahiti -verify -S -o - %s + +#pragma OPENCL EXTENSION cl_khr_fp16 : enable + +

[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+

2016-11-09 Thread Konstantin Zhuravlyov via cfe-commits
kzhuravl created this revision. kzhuravl added reviewers: tstellarAMD, arsenm. kzhuravl added a subscriber: cfe-commits. Herald added subscribers: tony-tye, yaxunl, nhaehnle, wdng. https://reviews.llvm.org/D26476 Files: include/clang/Basic/BuiltinsAMDGPU.def lib/CodeGen/CGBuiltin.cpp test/C