mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-14 11:32:34 +00:00
7c9c6ed761
Essentially the same as the GEP change in r230786.
A similar migration script can be used to update test cases, though a few more
test case improvements/changes were required this time around: (r229269-r229278)
import fileinput
import sys
import re
pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)")
for line in sys.stdin:
sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line))
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7649
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
49 lines
1.7 KiB
LLVM
49 lines
1.7 KiB
LLVM
; RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck -check-prefix=SI %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefix=SI %s
|
|
|
|
; SI-LABEL: {{^}}vector_umin:
|
|
; SI: v_min_u32_e32
|
|
define void @vector_umin(i32 %p0, i32 %p1, i32 addrspace(1)* %in) #0 {
|
|
main_body:
|
|
%load = load i32, i32 addrspace(1)* %in, align 4
|
|
%min = call i32 @llvm.AMDGPU.umin(i32 %p0, i32 %load)
|
|
%bc = bitcast i32 %min to float
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %bc, float %bc, float %bc, float %bc)
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}scalar_umin:
|
|
; SI: s_min_u32
|
|
define void @scalar_umin(i32 %p0, i32 %p1) #0 {
|
|
entry:
|
|
%min = call i32 @llvm.AMDGPU.umin(i32 %p0, i32 %p1)
|
|
%bc = bitcast i32 %min to float
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %bc, float %bc, float %bc, float %bc)
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}trunc_zext_umin:
|
|
; SI: buffer_load_ubyte [[VREG:v[0-9]+]],
|
|
; SI: v_min_u32_e32 [[RESULT:v[0-9]+]], 0, [[VREG]]
|
|
; SI-NOT: and
|
|
; SI: buffer_store_short [[RESULT]],
|
|
define void @trunc_zext_umin(i16 addrspace(1)* nocapture %out, i8 addrspace(1)* nocapture %src) nounwind {
|
|
%tmp5 = load i8, i8 addrspace(1)* %src, align 1
|
|
%tmp2 = zext i8 %tmp5 to i32
|
|
%tmp3 = tail call i32 @llvm.AMDGPU.umin(i32 %tmp2, i32 0) nounwind readnone
|
|
%tmp4 = trunc i32 %tmp3 to i8
|
|
%tmp6 = zext i8 %tmp4 to i16
|
|
store i16 %tmp6, i16 addrspace(1)* %out, align 2
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: readnone
|
|
declare i32 @llvm.AMDGPU.umin(i32, i32) #1
|
|
|
|
declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone }
|
|
|
|
!0 = !{!"const", null, i32 1}
|