mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-12-11 13:37:07 +00:00
f59acc15ad
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
81 lines
2.0 KiB
LLVM
81 lines
2.0 KiB
LLVM
; RUN: llc < %s -march=mips64 -target-abi n64 -mcpu=mips64r2 | FileCheck %s -check-prefixes=ALL,MIPSEB
|
|
; RUN: llc < %s -march=mips64el -target-abi n64 -mcpu=mips64r2 | FileCheck %s -check-prefixes=ALL,MIPSEL
|
|
; RUN: llc < %s -march=mips64 -target-abi n32 -mcpu=mips64r2 | FileCheck %s -check-prefixes=ALL,MIPSEB
|
|
; RUN: llc < %s -march=mips64el -target-abi n32 -mcpu=mips64r2 | FileCheck %s -check-prefixes=ALL,MIPSEL
|
|
|
|
; #include <stdio.h>
|
|
;
|
|
; struct S1 {
|
|
; char x1;
|
|
; short x2;
|
|
; char x3;
|
|
; };
|
|
;
|
|
; struct S2 {
|
|
; char x1;
|
|
; char x2;
|
|
; char x3;
|
|
; char x4;
|
|
; char x5;
|
|
; };
|
|
;
|
|
; void fS1(struct S1 s);
|
|
; void fS2(struct S2 s);
|
|
;
|
|
; void f1() {
|
|
; struct S1 s1_1;
|
|
; fS1(s1_1);
|
|
; }
|
|
;
|
|
; void f2() {
|
|
; struct S2 s2_1;
|
|
; fS2(s2_1);
|
|
; }
|
|
;
|
|
; int main() {
|
|
; f1();
|
|
; f2();
|
|
; }
|
|
|
|
%struct.S1 = type { i8, i16, i8 }
|
|
%struct.S2 = type { i8, i8, i8, i8, i8 }
|
|
|
|
declare void @fS1(i48 inreg) #1
|
|
declare void @fS2(i40 inreg) #1
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) #2
|
|
|
|
define void @f1() #0 {
|
|
entry:
|
|
%s1_1 = alloca %struct.S1, align 2
|
|
%s1_1.coerce = alloca { i48 }
|
|
%0 = bitcast { i48 }* %s1_1.coerce to i8*
|
|
%1 = bitcast %struct.S1* %s1_1 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 6, i1 false)
|
|
%2 = getelementptr { i48 }, { i48 }* %s1_1.coerce, i32 0, i32 0
|
|
%3 = load i48, i48* %2, align 1
|
|
call void @fS1(i48 inreg %3)
|
|
ret void
|
|
; ALL-LABEL: f1:
|
|
|
|
; MIPSEB: dsll $[[R1:[0-9]+]], $[[R2:[0-9]+]], 16
|
|
; MIPSEL-NOT: dsll $[[R1:[0-9]+]], $[[R2:[0-9]+]], 16
|
|
}
|
|
|
|
define void @f2() #0 {
|
|
entry:
|
|
%s2_1 = alloca %struct.S2, align 1
|
|
%s2_1.coerce = alloca { i40 }
|
|
%0 = bitcast { i40 }* %s2_1.coerce to i8*
|
|
%1 = bitcast %struct.S2* %s2_1 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 5, i1 false)
|
|
%2 = getelementptr { i40 }, { i40 }* %s2_1.coerce, i32 0, i32 0
|
|
%3 = load i40, i40* %2, align 1
|
|
call void @fS2(i40 inreg %3)
|
|
ret void
|
|
; ALL-LABEL: f2:
|
|
|
|
; MIPSEB: dsll $[[R1:[0-9]+]], $[[R2:[0-9]+]], 24
|
|
; MIPSEL-NOT: dsll $[[R1:[0-9]+]], $[[R2:[0-9]+]], 24
|
|
}
|