mirror of
https://github.com/RPCS3/llvm.git
synced 2025-05-19 20:06:06 +00:00
d706d030af
Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
29 lines
909 B
LLVM
29 lines
909 B
LLVM
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=fiji -loop-vectorize < %s | FileCheck %s
|
|
|
|
|
|
; For AMDGPU, loop unroll in loop vectorizer is disabled when VF==1.
|
|
;
|
|
; CHECK-LABEL: @small_loop(
|
|
; CHECK: store i32
|
|
; CHECK-NOT: store i32
|
|
; CHECK: ret
|
|
define amdgpu_kernel void @small_loop(i32* nocapture %inArray, i32 %size) nounwind {
|
|
entry:
|
|
%0 = icmp sgt i32 %size, 0
|
|
br i1 %0, label %loop, label %exit
|
|
|
|
loop: ; preds = %entry, %loop
|
|
%iv = phi i32 [ %iv1, %loop ], [ 0, %entry ]
|
|
%1 = getelementptr inbounds i32, i32* %inArray, i32 %iv
|
|
%2 = load i32, i32* %1, align 4
|
|
%3 = add nsw i32 %2, 6
|
|
store i32 %3, i32* %1, align 4
|
|
%iv1 = add i32 %iv, 1
|
|
; %lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%cond = icmp eq i32 %iv1, %size
|
|
br i1 %cond, label %exit, label %loop
|
|
|
|
exit: ; preds = %loop, %entry
|
|
ret void
|
|
}
|