diff options
author | Che-Liang Chiou <clchiou@gmail.com> | 2011-03-02 03:20:28 +0000 |
---|---|---|
committer | Che-Liang Chiou <clchiou@gmail.com> | 2011-03-02 03:20:28 +0000 |
commit | fd8978b021dbb0b9b09084dcc707c2054ff76280 (patch) | |
tree | cdbd6a22e3787047cdb1edcaa79065a2231b6a9c /test/CodeGen/PTX/add.ll | |
parent | 9ff5de99df4820a128e525e077333047cfe50661 (diff) | |
download | external_llvm-fd8978b021dbb0b9b09084dcc707c2054ff76280.zip external_llvm-fd8978b021dbb0b9b09084dcc707c2054ff76280.tar.gz external_llvm-fd8978b021dbb0b9b09084dcc707c2054ff76280.tar.bz2 |
Extend initial support for primitive types in PTX backend
- Allow i16, i32, i64, float, and double types, using the native .u16,
.u32, .u64, .f32, and .f64 PTX types.
- Allow loading/storing of all primitive types.
- Allow primitive types to be passed as parameters.
- Allow selection of PTX Version and Shader Model as sub-target attributes.
- Merge integer/floating-point test cases for load/store.
- Use .u32 instead of .s32 to conform to output from NVidia nvcc compiler.
Patch by Justin Holewinski
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126824 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/PTX/add.ll')
-rw-r--r-- | test/CodeGen/PTX/add.ll | 62 |
1 files changed, 52 insertions, 10 deletions
diff --git a/test/CodeGen/PTX/add.ll b/test/CodeGen/PTX/add.ll index 9e777ae..598591c 100644 --- a/test/CodeGen/PTX/add.ll +++ b/test/CodeGen/PTX/add.ll @@ -1,29 +1,71 @@ ; RUN: llc < %s -march=ptx | FileCheck %s -define ptx_device i32 @t1(i32 %x, i32 %y) { -; CHECK: add.s32 r0, r1, r2; +define ptx_device i16 @t1_u16(i16 %x, i16 %y) { +; CHECK: add.u16 rh0, rh1, rh2; +; CHECK-NEXT: ret; + %z = add i16 %x, %y + ret i16 %z +} + +define ptx_device i32 @t1_u32(i32 %x, i32 %y) { +; CHECK: add.u32 r0, r1, r2; +; CHECK-NEXT: ret; %z = add i32 %x, %y -; CHECK: ret; ret i32 %z } -define ptx_device i32 @t2(i32 %x) { -; CHECK: add.s32 r0, r1, 1; - %z = add i32 %x, 1 -; CHECK: ret; - ret i32 %z +define ptx_device i64 @t1_u64(i64 %x, i64 %y) { +; CHECK: add.u64 rd0, rd1, rd2; +; CHECK-NEXT: ret; + %z = add i64 %x, %y + ret i64 %z } -define ptx_device float @t3(float %x, float %y) { +define ptx_device float @t1_f32(float %x, float %y) { ; CHECK: add.f32 f0, f1, f2 ; CHECK-NEXT: ret; %z = fadd float %x, %y ret float %z } -define ptx_device float @t4(float %x) { +define ptx_device double @t1_f64(double %x, double %y) { +; CHECK: add.f64 fd0, fd1, fd2 +; CHECK-NEXT: ret; + %z = fadd double %x, %y + ret double %z +} + +define ptx_device i16 @t2_u16(i16 %x) { +; CHECK: add.u16 rh0, rh1, 1; +; CHECK-NEXT: ret; + %z = add i16 %x, 1 + ret i16 %z +} + +define ptx_device i32 @t2_u32(i32 %x) { +; CHECK: add.u32 r0, r1, 1; +; CHECK-NEXT: ret; + %z = add i32 %x, 1 + ret i32 %z +} + +define ptx_device i64 @t2_u64(i64 %x) { +; CHECK: add.u64 rd0, rd1, 1; +; CHECK-NEXT: ret; + %z = add i64 %x, 1 + ret i64 %z +} + +define ptx_device float @t2_f32(float %x) { ; CHECK: add.f32 f0, f1, 0F3F800000; ; CHECK-NEXT: ret; %z = fadd float %x, 1.0 ret float %z } + +define ptx_device double @t2_f64(double %x) { +; CHECK: add.f64 fd0, fd1, 0D3FF0000000000000; +; CHECK-NEXT: ret; + %z = fadd double %x, 1.0 + ret double %z +} |