maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Add tests for the NVPTXLowerAggrCopies pass. 

Note: not testing memmove lowering for now, as it's broken
[see https://llvm.org/bugs/show_bug.cgi?id=24056]

llvm-svn: 241736
This commit is contained in:
Eli Bendersky 2015-07-08 21:29:28 +00:00
parent 495ad87919
commit 5c27308a8f
1 changed files with 34 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
llvm/test/CodeGen/NVPTX/lower-aggr-copies.ll Normal file
View File

@ -0,0 +1,34 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_35 | FileCheck %s
; Verify that the NVPTXLowerAggrCopies pass works as expected - calls to
; llvm.mem* intrinsics get lowered to loops.
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) #1
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) #1
define i8* @memcpy_caller(i8* %dst, i8* %src, i64 %n) #0 {
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %n, i32 1, i1 false)
ret i8* %dst
; CHECK-LABEL: .visible .func (.param .b32 func_retval0) memcpy_caller
; CHECK: LBB[[LABEL:[_0-9]+]]:
; CHECK: ld.u8 %rs[[REG:[0-9]+]]
; CHECK: st.u8 [%r{{[0-9]+}}], %rs[[REG]]
; CHECK: add.s64 %rd[[COUNTER:[0-9]+]], %rd[[COUNTER]], 1
; CHECK-NEXT: setp.lt.u64 %p[[PRED:[0-9]+]], %rd[[COUNTER]], %rd
; CHECK-NEXT: @%p[[PRED]] bra LBB[[LABEL]]
}
define i8* @memset_caller(i8* %dst, i32 %c, i64 %n) #0 {
entry:
%0 = trunc i32 %c to i8
tail call void @llvm.memset.p0i8.i64(i8* %dst, i8 %0, i64 %n, i32 1, i1 false)
ret i8* %dst
; CHECK-LABEL: .visible .func (.param .b32 func_retval0) memset_caller(
; CHECK: ld.param.u8 %rs[[REG:[0-9]+]]
; CHECK: LBB[[LABEL:[_0-9]+]]:
; CHECK: st.u8 [%r{{[0-9]+}}], %rs[[REG]]
; CHECK: add.s64 %rd[[COUNTER:[0-9]+]], %rd[[COUNTER]], 1
; CHECK-NEXT: setp.lt.u64 %p[[PRED:[0-9]+]], %rd[[COUNTER]], %rd
; CHECK-NEXT: @%p[[PRED]] bra LBB[[LABEL]]
}