mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 03:02:36 +01:00
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
93 lines
3.7 KiB
LLVM
93 lines
3.7 KiB
LLVM
; RUN: opt < %s -sroa -S | FileCheck %s
|
|
;
|
|
; Make sure that SROA doesn't lose nonnull metadata
|
|
; on loads from allocas that get optimized out.
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1)
|
|
|
|
; Check that we do basic propagation of nonnull when rewriting.
|
|
define i8* @propagate_nonnull(i32* %v) {
|
|
; CHECK-LABEL: define i8* @propagate_nonnull(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: %[[A:.*]] = alloca i8*
|
|
; CHECK-NEXT: %[[V_CAST:.*]] = bitcast i32* %v to i8*
|
|
; CHECK-NEXT: store i8* %[[V_CAST]], i8** %[[A]]
|
|
; CHECK-NEXT: %[[LOAD:.*]] = load volatile i8*, i8** %[[A]], !nonnull !0
|
|
; CHECK-NEXT: ret i8* %[[LOAD]]
|
|
entry:
|
|
%a = alloca [2 x i8*]
|
|
%a.gep0 = getelementptr [2 x i8*], [2 x i8*]* %a, i32 0, i32 0
|
|
%a.gep1 = getelementptr [2 x i8*], [2 x i8*]* %a, i32 0, i32 1
|
|
%a.gep0.cast = bitcast i8** %a.gep0 to i32**
|
|
%a.gep1.cast = bitcast i8** %a.gep1 to i32**
|
|
store i32* %v, i32** %a.gep1.cast
|
|
store i32* null, i32** %a.gep0.cast
|
|
%load = load volatile i8*, i8** %a.gep1, !nonnull !0
|
|
ret i8* %load
|
|
}
|
|
|
|
define float* @turn_nonnull_into_assume(float** %arg) {
|
|
; CHECK-LABEL: define float* @turn_nonnull_into_assume(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: %[[RETURN:.*]] = load float*, float** %arg, align 8
|
|
; CHECK-NEXT: %[[ASSUME:.*]] = icmp ne float* %[[RETURN]], null
|
|
; CHECK-NEXT: call void @llvm.assume(i1 %[[ASSUME]])
|
|
; CHECK-NEXT: ret float* %[[RETURN]]
|
|
entry:
|
|
%buf = alloca float*
|
|
%_arg_i8 = bitcast float** %arg to i8*
|
|
%_buf_i8 = bitcast float** %buf to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %_buf_i8, i8* align 8 %_arg_i8, i64 8, i1 false)
|
|
%ret = load float*, float** %buf, align 8, !nonnull !0
|
|
ret float* %ret
|
|
}
|
|
|
|
; Make sure we properly handle the !nonnull attribute when we convert
|
|
; a pointer load to an integer load.
|
|
; FIXME: While this doesn't do anythnig actively harmful today, it really
|
|
; should propagate the !nonnull metadata to range metadata. The irony is, it
|
|
; *does* initially, but then we lose that !range metadata before we finish
|
|
; SROA.
|
|
define i8* @propagate_nonnull_to_int() {
|
|
; CHECK-LABEL: define i8* @propagate_nonnull_to_int(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: %[[A:.*]] = alloca i64
|
|
; CHECK-NEXT: store i64 42, i64* %[[A]]
|
|
; CHECK-NEXT: %[[LOAD:.*]] = load volatile i64, i64* %[[A]]
|
|
; CHECK-NEXT: %[[CAST:.*]] = inttoptr i64 %[[LOAD]] to i8*
|
|
; CHECK-NEXT: ret i8* %[[CAST]]
|
|
entry:
|
|
%a = alloca [2 x i8*]
|
|
%a.gep0 = getelementptr [2 x i8*], [2 x i8*]* %a, i32 0, i32 0
|
|
%a.gep1 = getelementptr [2 x i8*], [2 x i8*]* %a, i32 0, i32 1
|
|
%a.gep0.cast = bitcast i8** %a.gep0 to i64*
|
|
%a.gep1.cast = bitcast i8** %a.gep1 to i64*
|
|
store i64 42, i64* %a.gep1.cast
|
|
store i64 0, i64* %a.gep0.cast
|
|
%load = load volatile i8*, i8** %a.gep1, !nonnull !0
|
|
ret i8* %load
|
|
}
|
|
|
|
; Make sure we properly handle the !nonnull attribute when we convert
|
|
; a pointer load to an integer load and immediately promote it to an SSA
|
|
; register. This can fail in interesting ways due to the rewrite iteration of
|
|
; SROA, resulting in PR32902.
|
|
define i8* @propagate_nonnull_to_int_and_promote() {
|
|
; CHECK-LABEL: define i8* @propagate_nonnull_to_int_and_promote(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: %[[PROMOTED_VALUE:.*]] = inttoptr i64 42 to i8*
|
|
; CHECK-NEXT: ret i8* %[[PROMOTED_VALUE]]
|
|
entry:
|
|
%a = alloca [2 x i8*], align 8
|
|
%a.gep0 = getelementptr [2 x i8*], [2 x i8*]* %a, i32 0, i32 0
|
|
%a.gep1 = getelementptr [2 x i8*], [2 x i8*]* %a, i32 0, i32 1
|
|
%a.gep0.cast = bitcast i8** %a.gep0 to i64*
|
|
%a.gep1.cast = bitcast i8** %a.gep1 to i64*
|
|
store i64 42, i64* %a.gep1.cast
|
|
store i64 0, i64* %a.gep0.cast
|
|
%load = load i8*, i8** %a.gep1, align 8, !nonnull !0
|
|
ret i8* %load
|
|
}
|
|
|
|
!0 = !{}
|