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/WebAssembly/mem-intrinsics.ll

108 lines
3.4 KiB
LLVM
Raw Normal View History

[WebAssembly] Optimize memcpy/memmove/memcpy calls. These calls return their first argument, but because LLVM uses an intrinsic with a void return type, they can't use the returned attribute. Generalize the store results pass to optimize these calls too. llvm-svn: 258781
2016-01-26 12:01:11 +08:00
; RUN: llc < %s -asm-verbose=false | FileCheck %s
; Test memcpy, memmove, and memset intrinsics.
target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
target triple = "wasm32-unknown-unknown"
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1)
declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1)
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1)
; Test that return values are optimized.
; CHECK-LABEL: copy_yes:
; CHECK: i32.call $push0=, memcpy@FUNCTION, $0, $1, $2{{$}}
; CHECK-NEXT: return $pop0{{$}}
define i8* @copy_yes(i8* %dst, i8* %src, i32 %len) {
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %len, i32 1, i1 false)
ret i8* %dst
}
; CHECK-LABEL: copy_no:
; CHECK: i32.call $discard=, memcpy@FUNCTION, $0, $1, $2{{$}}
; CHECK-NEXT: return{{$}}
define void @copy_no(i8* %dst, i8* %src, i32 %len) {
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %len, i32 1, i1 false)
ret void
}
; CHECK-LABEL: move_yes:
; CHECK: i32.call $push0=, memmove@FUNCTION, $0, $1, $2{{$}}
; CHECK-NEXT: return $pop0{{$}}
define i8* @move_yes(i8* %dst, i8* %src, i32 %len) {
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %len, i32 1, i1 false)
ret i8* %dst
}
; CHECK-LABEL: move_no:
; CHECK: i32.call $discard=, memmove@FUNCTION, $0, $1, $2{{$}}
; CHECK-NEXT: return{{$}}
define void @move_no(i8* %dst, i8* %src, i32 %len) {
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %len, i32 1, i1 false)
ret void
}
; CHECK-LABEL: set_yes:
; CHECK: i32.call $push0=, memset@FUNCTION, $0, $1, $2{{$}}
; CHECK-NEXT: return $pop0{{$}}
define i8* @set_yes(i8* %dst, i8 %src, i32 %len) {
call void @llvm.memset.p0i8.i32(i8* %dst, i8 %src, i32 %len, i32 1, i1 false)
ret i8* %dst
}
; CHECK-LABEL: set_no:
; CHECK: i32.call $discard=, memset@FUNCTION, $0, $1, $2{{$}}
; CHECK-NEXT: return{{$}}
define void @set_no(i8* %dst, i8 %src, i32 %len) {
call void @llvm.memset.p0i8.i32(i8* %dst, i8 %src, i32 %len, i32 1, i1 false)
ret void
}
WebAssembly: don't optimize memcpy/memmove/memcpy to frame index r258781 optimized memcpy/memmove/memcpy so the intrinsic call can return its first argument, but missed the frame index case. Teach it to ignore that case so C code doesn't assert out in these cases. llvm-svn: 258851
2016-01-27 04:22:42 +08:00
[WebAssembly] Omit no-op adds for non-mem uses of FrameIndex Differential Revision: http://reviews.llvm.org/D16554 llvm-svn: 258872
2016-01-27 06:47:43 +08:00
WebAssembly: don't optimize memcpy/memmove/memcpy to frame index r258781 optimized memcpy/memmove/memcpy so the intrinsic call can return its first argument, but missed the frame index case. Teach it to ignore that case so C code doesn't assert out in these cases. llvm-svn: 258851
2016-01-27 04:22:42 +08:00
; CHECK-LABEL: frame_index:
[WebAssembly] Stackify code emitted by eliminateFrameIndex and SP writeback Summary: MRI::eliminateFrameIndex can emit several instructions to do address calculations; these can usually be stackified. Because instructions with FI operands can have subsequent operands which may be expression trees, find the top of the leftmost tree and insert the code before it, to keep the LIFO property. Also use stackified registers when writing back the SP value to memory in the epilog; it's unnecessary because SP will not be used after the epilog, and it results in better code. Differential Revision: http://reviews.llvm.org/D18234 llvm-svn: 263725
2016-03-18 01:00:29 +08:00
; CHECK: i32.call $discard=, memset@FUNCTION, $pop12, $pop1, $pop0{{$}}
; CHECK: i32.call $discard=, memset@FUNCTION, $0, $pop3, $pop2{{$}}
WebAssembly: don't optimize memcpy/memmove/memcpy to frame index r258781 optimized memcpy/memmove/memcpy so the intrinsic call can return its first argument, but missed the frame index case. Teach it to ignore that case so C code doesn't assert out in these cases. llvm-svn: 258851
2016-01-27 04:22:42 +08:00
; CHECK: return{{$}}
define void @frame_index() {
entry:
%a = alloca [2048 x i8], align 16
[WebAssembly] Omit no-op adds for non-mem uses of FrameIndex Differential Revision: http://reviews.llvm.org/D16554 llvm-svn: 258872
2016-01-27 06:47:43 +08:00
%b = alloca [2048 x i8], align 16
WebAssembly: don't optimize memcpy/memmove/memcpy to frame index r258781 optimized memcpy/memmove/memcpy so the intrinsic call can return its first argument, but missed the frame index case. Teach it to ignore that case so C code doesn't assert out in these cases. llvm-svn: 258851
2016-01-27 04:22:42 +08:00
%0 = getelementptr inbounds [2048 x i8], [2048 x i8]* %a, i32 0, i32 0
[WebAssembly] Omit no-op adds for non-mem uses of FrameIndex Differential Revision: http://reviews.llvm.org/D16554 llvm-svn: 258872
2016-01-27 06:47:43 +08:00
%1 = getelementptr inbounds [2048 x i8], [2048 x i8]* %b, i32 0, i32 0
WebAssembly: don't optimize memcpy/memmove/memcpy to frame index r258781 optimized memcpy/memmove/memcpy so the intrinsic call can return its first argument, but missed the frame index case. Teach it to ignore that case so C code doesn't assert out in these cases. llvm-svn: 258851
2016-01-27 04:22:42 +08:00
call void @llvm.memset.p0i8.i32(i8* %0, i8 256, i32 1024, i32 16, i1 false)
[WebAssembly] Omit no-op adds for non-mem uses of FrameIndex Differential Revision: http://reviews.llvm.org/D16554 llvm-svn: 258872
2016-01-27 06:47:43 +08:00
call void @llvm.memset.p0i8.i32(i8* %1, i8 256, i32 1024, i32 16, i1 false)
WebAssembly: don't optimize memcpy/memmove/memcpy to frame index r258781 optimized memcpy/memmove/memcpy so the intrinsic call can return its first argument, but missed the frame index case. Teach it to ignore that case so C code doesn't assert out in these cases. llvm-svn: 258851
2016-01-27 04:22:42 +08:00
ret void
}
[WebAssembly] Add a test for the mem-intrinsic code in WebAssemblyPeephole.cpp llvm-svn: 258895
2016-01-27 09:37:52 +08:00
; If the result value of memset doesn't get stackified, it should be marked
; $discard.
; CHECK-LABEL: discard_result:
; CHECK: i32.call $discard=, memset@FUNCTION, $0, $1, $2
declare i8* @def()
define i8* @discard_result(i8* %arg, i8 %arg1, i32 %arg2, i32 %arg3, i32 %arg4) {
bb:
%tmp = icmp eq i32 %arg3, 0
br i1 %tmp, label %bb5, label %bb9
bb5:
%tmp6 = icmp eq i32 %arg4, 0
br i1 %tmp6, label %bb7, label %bb8
bb7:
call void @llvm.memset.p0i8.i32(i8* %arg, i8 %arg1, i32 %arg2, i32 1, i1 false)
br label %bb11
bb8:
br label %bb11
bb9:
%tmp10 = call i8* @def()
br label %bb11
bb11:
%tmp12 = phi i8* [ %arg, %bb7 ], [ %arg, %bb8 ], [ %tmp10, %bb9 ]
ret i8* %tmp12
}