RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity
llvm-mirror/test/CodeGen/WebAssembly/mem-intrinsics.ll
Daniel Neilson f59acc15ad Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) 
Summary:
 This is a resurrection of work first proposed and discussed in Aug 2015:
   http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
   http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html

 The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.

 This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.

 In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
   require that the alignments for source & dest be equal.

 For example, code which used to read:
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)

 Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.

s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g

 The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
   source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
        and those that use use MemIntrinsicInst::[get|set]Alignment() to use
        getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
        MemIntrinsicInst::[get|set]Alignment() methods.

Reviewers: pete, hfinkel, lhames, reames, bollu

Reviewed By: reames

Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits

Differential Revision: https://reviews.llvm.org/D41675

llvm-svn: 322965
2018-01-19 17:13:12 +00:00

141 lines
4.3 KiB
LLVM
Raw Blame History

; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -disable-wasm-explicit-locals -tail-dup-placement=0 | 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-wasm"
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1)
declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1)
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, 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, i1 false)
ret i8* %dst
}
; CHECK-LABEL: copy_no:
; CHECK: i32.call $drop=, 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, 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, i1 false)
ret i8* %dst
}
; CHECK-LABEL: move_no:
; CHECK: i32.call $drop=, 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, 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, i1 false)
ret i8* %dst
}
; CHECK-LABEL: set_no:
; CHECK: i32.call $drop=, 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, i1 false)
ret void
}
; CHECK-LABEL: frame_index:
; CHECK: i32.call $drop=, memset@FUNCTION, $pop{{[0-9]+}}, $pop{{[0-9]+}}, $pop{{[0-9]+}}{{$}}
; CHECK: i32.call $push{{[0-9]+}}=, memset@FUNCTION, ${{[0-9]+}}, $pop{{[0-9]+}}, $pop{{[0-9]+}}{{$}}
; CHECK: return{{$}}
define void @frame_index() {
entry:
%a = alloca [2048 x i8], align 16
%b = alloca [2048 x i8], align 16
%0 = getelementptr inbounds [2048 x i8], [2048 x i8]* %a, i32 0, i32 0
%1 = getelementptr inbounds [2048 x i8], [2048 x i8]* %b, i32 0, i32 0
call void @llvm.memset.p0i8.i32(i8* align 16 %0, i8 256, i32 1024, i1 false)
call void @llvm.memset.p0i8.i32(i8* align 16 %1, i8 256, i32 1024, i1 false)
ret void
}
; If the result value of memset doesn't get stackified, it should be marked
; $drop. Note that we use a call to prevent tail dup so that we can test
; this specific functionality.
; CHECK-LABEL: drop_result:
; CHECK: i32.call $drop=, memset@FUNCTION, $0, $1, $2
declare i8* @def()
declare void @block_tail_dup()
define i8* @drop_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, 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 ]
call void @block_tail_dup()
ret i8* %tmp12
}
; This is the same as drop_result, except we let tail dup happen, so the
; result of the memset *is* stackified.
; CHECK-LABEL: tail_dup_to_reuse_result:
; CHECK: i32.call $push{{[0-9]+}}=, memset@FUNCTION, $0, $1, $2
define i8* @tail_dup_to_reuse_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, 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
}
Reference in New Issue View Git Blame Copy Permalink