maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/NVPTX/generic-to-nvvm.ll

27 lines
811 B
LLVM
Raw Normal View History

[NVPTX] Add support for selecting CUDA vs OCL mode based on triple IR for CUDA should use "nvptx[64]-nvidia-cuda", and IR for NV OpenCL should use "nvptx[64]-nvidia-nvcl" llvm-svn: 184579
2013-06-22 02:51:49 +08:00
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
[NVPTX] Add GenericToNVVM IR converter to better handle idiomatic LLVM IR inputs This converter currently only handles global variables in address space 0. For these variables, they are promoted to address space 1 (global memory), and all uses are updated to point to the result of a cvta.global instruction on the new variable. The motivation for this is address space 0 global variables are illegal since we cannot declare variables in the generic address space. Instead, we place the variables in address space 1 and explicitly convert the pointer to address space 0. This is primarily intended to help new users who expect to be able to place global variables in the default address space. llvm-svn: 182254
2013-05-20 20:13:32 +08:00
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
[NVPTX] Add support for selecting CUDA vs OCL mode based on triple IR for CUDA should use "nvptx[64]-nvidia-cuda", and IR for NV OpenCL should use "nvptx[64]-nvidia-nvcl" llvm-svn: 184579
2013-06-22 02:51:49 +08:00
target triple = "nvptx-nvidia-cuda"
[NVPTX] Add GenericToNVVM IR converter to better handle idiomatic LLVM IR inputs This converter currently only handles global variables in address space 0. For these variables, they are promoted to address space 1 (global memory), and all uses are updated to point to the result of a cvta.global instruction on the new variable. The motivation for this is address space 0 global variables are illegal since we cannot declare variables in the generic address space. Instead, we place the variables in address space 1 and explicitly convert the pointer to address space 0. This is primarily intended to help new users who expect to be able to place global variables in the default address space. llvm-svn: 182254
2013-05-20 20:13:32 +08:00
; Ensure global variables in address space 0 are promoted to address space 1
; CHECK: .global .align 4 .u32 myglobal = 42;
@myglobal = internal global i32 42, align 4
; CHECK: .global .align 4 .u32 myconst = 42;
@myconst = internal constant i32 42, align 4
define void @foo(i32* %a, i32* %b) {
; CHECK: cvta.global.u32
%ld1 = load i32* @myglobal
; CHECK: cvta.global.u32
%ld2 = load i32* @myconst
store i32 %ld1, i32* %a
store i32 %ld2, i32* %b
ret void
}
!nvvm.annotations = !{!0}
!0 = metadata !{void (i32*, i32*)* @foo, metadata !"kernel", i32 1}