1e68724d24
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
152 lines
4.9 KiB
LLVM
152 lines
4.9 KiB
LLVM
; RUN: llc --march=mips64 -mcpu=mips64r2 < %s | FileCheck %s
|
|
|
|
; Generated from the C program:
|
|
;
|
|
; #include <stdio.h>
|
|
; #include <string.h>
|
|
;
|
|
; struct SmallStruct_1b1s {
|
|
; char x1;
|
|
; short x2;
|
|
; };
|
|
;
|
|
; struct SmallStruct_1b1i {
|
|
; char x1;
|
|
; int x2;
|
|
; };
|
|
;
|
|
; struct SmallStruct_1b1s1b {
|
|
; char x1;
|
|
; short x2;
|
|
; char x3;
|
|
; };
|
|
;
|
|
; struct SmallStruct_1s1i {
|
|
; short x1;
|
|
; int x2;
|
|
; };
|
|
;
|
|
; struct SmallStruct_3b1s {
|
|
; char x1;
|
|
; char x2;
|
|
; char x3;
|
|
; short x4;
|
|
; };
|
|
;
|
|
; void varArgF_SmallStruct(char* c, ...);
|
|
;
|
|
; void smallStruct_1b1s(struct SmallStruct_1b1s* ss)
|
|
; {
|
|
; varArgF_SmallStruct("", *ss);
|
|
; }
|
|
;
|
|
; void smallStruct_1b1i(struct SmallStruct_1b1i* ss)
|
|
; {
|
|
; varArgF_SmallStruct("", *ss);
|
|
; }
|
|
;
|
|
; void smallStruct_1b1s1b(struct SmallStruct_1b1s1b* ss)
|
|
; {
|
|
; varArgF_SmallStruct("", *ss);
|
|
; }
|
|
;
|
|
; void smallStruct_1s1i(struct SmallStruct_1s1i* ss)
|
|
; {
|
|
; varArgF_SmallStruct("", *ss);
|
|
; }
|
|
;
|
|
; void smallStruct_3b1s(struct SmallStruct_3b1s* ss)
|
|
; {
|
|
; varArgF_SmallStruct("", *ss);
|
|
; }
|
|
|
|
%struct.SmallStruct_1b1s = type { i8, i16 }
|
|
%struct.SmallStruct_1b1i = type { i8, i32 }
|
|
%struct.SmallStruct_1b1s1b = type { i8, i16, i8 }
|
|
%struct.SmallStruct_1s1i = type { i16, i32 }
|
|
%struct.SmallStruct_3b1s = type { i8, i8, i8, i16 }
|
|
|
|
@.str = private unnamed_addr constant [3 x i8] c"01\00", align 1
|
|
|
|
declare void @varArgF_SmallStruct(i8* %c, ...)
|
|
|
|
define void @smallStruct_1b1s(%struct.SmallStruct_1b1s* %ss) #0 {
|
|
entry:
|
|
%ss.addr = alloca %struct.SmallStruct_1b1s*, align 8
|
|
store %struct.SmallStruct_1b1s* %ss, %struct.SmallStruct_1b1s** %ss.addr, align 8
|
|
%0 = load %struct.SmallStruct_1b1s*, %struct.SmallStruct_1b1s** %ss.addr, align 8
|
|
%1 = bitcast %struct.SmallStruct_1b1s* %0 to { i32 }*
|
|
%2 = getelementptr { i32 }, { i32 }* %1, i32 0, i32 0
|
|
%3 = load i32, i32* %2, align 1
|
|
call void (i8*, ...) @varArgF_SmallStruct(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @.str, i32 0, i32 0), i32 inreg %3)
|
|
ret void
|
|
; CHECK-LABEL: smallStruct_1b1s:
|
|
; CHECK: dsll $[[R1:[0-9]+]], $[[R2:[0-9]+]], 32
|
|
}
|
|
|
|
define void @smallStruct_1b1i(%struct.SmallStruct_1b1i* %ss) #0 {
|
|
entry:
|
|
%ss.addr = alloca %struct.SmallStruct_1b1i*, align 8
|
|
store %struct.SmallStruct_1b1i* %ss, %struct.SmallStruct_1b1i** %ss.addr, align 8
|
|
%0 = load %struct.SmallStruct_1b1i*, %struct.SmallStruct_1b1i** %ss.addr, align 8
|
|
%1 = bitcast %struct.SmallStruct_1b1i* %0 to { i64 }*
|
|
%2 = getelementptr { i64 }, { i64 }* %1, i32 0, i32 0
|
|
%3 = load i64, i64* %2, align 1
|
|
call void (i8*, ...) @varArgF_SmallStruct(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @.str, i32 0, i32 0), i64 inreg %3)
|
|
ret void
|
|
; CHECK-LABEL: smallStruct_1b1i:
|
|
; CHECK-NOT: dsll
|
|
; CHECK: lui
|
|
}
|
|
|
|
define void @smallStruct_1b1s1b(%struct.SmallStruct_1b1s1b* %ss) #0 {
|
|
entry:
|
|
%ss.addr = alloca %struct.SmallStruct_1b1s1b*, align 8
|
|
%.coerce = alloca { i48 }
|
|
store %struct.SmallStruct_1b1s1b* %ss, %struct.SmallStruct_1b1s1b** %ss.addr, align 8
|
|
%0 = load %struct.SmallStruct_1b1s1b*, %struct.SmallStruct_1b1s1b** %ss.addr, align 8
|
|
%1 = bitcast { i48 }* %.coerce to i8*
|
|
%2 = bitcast %struct.SmallStruct_1b1s1b* %0 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 6, i1 false)
|
|
%3 = getelementptr { i48 }, { i48 }* %.coerce, i32 0, i32 0
|
|
%4 = load i48, i48* %3, align 1
|
|
call void (i8*, ...) @varArgF_SmallStruct(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @.str, i32 0, i32 0), i48 inreg %4)
|
|
ret void
|
|
; CHECK-LABEL: smallStruct_1b1s1b:
|
|
; CHECK: dsll $[[R1:[0-9]+]], $[[R2:[0-9]+]], 16
|
|
}
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) #1
|
|
|
|
define void @smallStruct_1s1i(%struct.SmallStruct_1s1i* %ss) #0 {
|
|
entry:
|
|
%ss.addr = alloca %struct.SmallStruct_1s1i*, align 8
|
|
store %struct.SmallStruct_1s1i* %ss, %struct.SmallStruct_1s1i** %ss.addr, align 8
|
|
%0 = load %struct.SmallStruct_1s1i*, %struct.SmallStruct_1s1i** %ss.addr, align 8
|
|
%1 = bitcast %struct.SmallStruct_1s1i* %0 to { i64 }*
|
|
%2 = getelementptr { i64 }, { i64 }* %1, i32 0, i32 0
|
|
%3 = load i64, i64* %2, align 1
|
|
call void (i8*, ...) @varArgF_SmallStruct(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @.str, i32 0, i32 0), i64 inreg %3)
|
|
ret void
|
|
; CHECK-LABEL: smallStruct_1s1i:
|
|
; CHECK-NOT: dsll
|
|
; CHECK: lui
|
|
}
|
|
|
|
define void @smallStruct_3b1s(%struct.SmallStruct_3b1s* %ss) #0 {
|
|
entry:
|
|
%ss.addr = alloca %struct.SmallStruct_3b1s*, align 8
|
|
%.coerce = alloca { i48 }
|
|
store %struct.SmallStruct_3b1s* %ss, %struct.SmallStruct_3b1s** %ss.addr, align 8
|
|
%0 = load %struct.SmallStruct_3b1s*, %struct.SmallStruct_3b1s** %ss.addr, align 8
|
|
%1 = bitcast { i48 }* %.coerce to i8*
|
|
%2 = bitcast %struct.SmallStruct_3b1s* %0 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 6, i1 false)
|
|
%3 = getelementptr { i48 }, { i48 }* %.coerce, i32 0, i32 0
|
|
%4 = load i48, i48* %3, align 1
|
|
call void (i8*, ...) @varArgF_SmallStruct(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @.str, i32 0, i32 0), i48 inreg %4)
|
|
ret void
|
|
; CHECK-LABEL: smallStruct_3b1s:
|
|
; CHECK: dsll $[[R1:[0-9]+]], $[[R2:[0-9]+]], 16
|
|
}
|