diff options
author | Justin Holewinski <jholewinski@nvidia.com> | 2013-03-30 14:29:25 +0000 |
---|---|---|
committer | Justin Holewinski <jholewinski@nvidia.com> | 2013-03-30 14:29:25 +0000 |
commit | 21fdcb02716f5eae097abfd2f44e40563e90180a (patch) | |
tree | a22b3d6bd88893175984ae4e699c41b9ccad8b55 /test/CodeGen/NVPTX/nvvm-reflect.ll | |
parent | 3639ce2575660a0e6938d2e84e8bd9a738fd7051 (diff) | |
download | external_llvm-21fdcb02716f5eae097abfd2f44e40563e90180a.zip external_llvm-21fdcb02716f5eae097abfd2f44e40563e90180a.tar.gz external_llvm-21fdcb02716f5eae097abfd2f44e40563e90180a.tar.bz2 |
[NVPTX] Add NVVMReflect pass to allow compile-time selection of
specific code paths.
This allows us to write code like:
if (__nvvm_reflect("FOO"))
// Do something
else
// Do something else
and compile into a library, then give "FOO" a value at kernel
compile-time so the check becomes a no-op.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178416 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/NVPTX/nvvm-reflect.ll')
-rw-r--r-- | test/CodeGen/NVPTX/nvvm-reflect.ll | 34 |
1 files changed, 34 insertions, 0 deletions
diff --git a/test/CodeGen/NVPTX/nvvm-reflect.ll b/test/CodeGen/NVPTX/nvvm-reflect.ll new file mode 100644 index 0000000..0d02194 --- /dev/null +++ b/test/CodeGen/NVPTX/nvvm-reflect.ll @@ -0,0 +1,34 @@ +; RUN: opt < %s -S -nvvm-reflect -nvvm-reflect-list USE_MUL=0 -O2 | FileCheck %s --check-prefix=USE_MUL_0 +; RUN: opt < %s -S -nvvm-reflect -nvvm-reflect-list USE_MUL=1 -O2 | FileCheck %s --check-prefix=USE_MUL_1 + +@str = private addrspace(4) unnamed_addr constant [8 x i8] c"USE_MUL\00" + +declare i32 @__nvvm_reflect(i8*) +declare i8* @llvm.nvvm.ptr.constant.to.gen.p0i8.p4i8(i8 addrspace(4)*) + +define float @foo(float %a, float %b) { +; USE_MUL_0: define float @foo +; USE_MUL_0-NOT: call i32 @__nvvm_reflect +; USE_MUL_1: define float @foo +; USE_MUL_1-NOT: call i32 @__nvvm_reflect + %ptr = tail call i8* @llvm.nvvm.ptr.constant.to.gen.p0i8.p4i8(i8 addrspace(4)* getelementptr inbounds ([8 x i8] addrspace(4)* @str, i32 0, i32 0)) + %reflect = tail call i32 @__nvvm_reflect(i8* %ptr) + %cmp = icmp ugt i32 %reflect, 0 + br i1 %cmp, label %use_mul, label %use_add + +use_mul: +; USE_MUL_1: fmul float %a, %b +; USE_MUL_0-NOT: fadd float %a, %b + %ret1 = fmul float %a, %b + br label %exit + +use_add: +; USE_MUL_0: fadd float %a, %b +; USE_MUL_1-NOT: fmul float %a, %b + %ret2 = fadd float %a, %b + br label %exit + +exit: + %ret = phi float [%ret1, %use_mul], [%ret2, %use_add] + ret float %ret +} |