mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-24 05:23:45 +02:00
dd9ab77318
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). llvm-svn: 298444
30 lines
797 B
LLVM
30 lines
797 B
LLVM
; RUN: opt -loop-unroll -unroll-threshold=2000 -S < %s | llc -march=r600 -mcpu=cypress | FileCheck %s
|
|
; REQUIRES: asserts
|
|
|
|
; CHECK: {{^}}alu_limits:
|
|
; CHECK: CF_END
|
|
|
|
%struct.foo = type {i32, i32, i32}
|
|
|
|
define amdgpu_kernel void @alu_limits(i32 addrspace(1)* %out, %struct.foo* %in, i32 %offset) {
|
|
entry:
|
|
%ptr = getelementptr inbounds %struct.foo, %struct.foo* %in, i32 1, i32 2
|
|
%x = load i32, i32 *%ptr, align 4
|
|
br label %loop
|
|
loop:
|
|
%i = phi i32 [ 100, %entry ], [ %nexti, %loop ]
|
|
%val = phi i32 [ 1, %entry ], [ %nextval, %loop ]
|
|
|
|
%nexti = sub i32 %i, 1
|
|
|
|
%y = xor i32 %x, %i
|
|
%nextval = mul i32 %val, %y
|
|
|
|
%cond = icmp ne i32 %nexti, 0
|
|
br i1 %cond, label %loop, label %end
|
|
end:
|
|
%out_val = add i32 %nextval, 4
|
|
store i32 %out_val, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|