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
626 lines
24 KiB
LLVM
626 lines
24 KiB
LLVM
; RUN: opt < %s -sroa -S | FileCheck %s
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64"
|
|
|
|
%S1 = type { i64, [42 x float] }
|
|
|
|
define i32 @test1(<4 x i32> %x, <4 x i32> %y) {
|
|
; CHECK-LABEL: @test1(
|
|
entry:
|
|
%a = alloca [2 x <4 x i32>]
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
|
|
store <4 x i32> %x, <4 x i32>* %a.x
|
|
%a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
|
|
store <4 x i32> %y, <4 x i32>* %a.y
|
|
; CHECK-NOT: store
|
|
|
|
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
|
|
%tmp1 = load i32, i32* %a.tmp1
|
|
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
|
|
%tmp2 = load i32, i32* %a.tmp2
|
|
%a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
|
|
%tmp3 = load i32, i32* %a.tmp3
|
|
; CHECK-NOT: load
|
|
; CHECK: extractelement <4 x i32> %x, i32 2
|
|
; CHECK-NEXT: extractelement <4 x i32> %y, i32 3
|
|
; CHECK-NEXT: extractelement <4 x i32> %y, i32 0
|
|
|
|
%tmp4 = add i32 %tmp1, %tmp2
|
|
%tmp5 = add i32 %tmp3, %tmp4
|
|
ret i32 %tmp5
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: ret
|
|
}
|
|
|
|
define i32 @test2(<4 x i32> %x, <4 x i32> %y) {
|
|
; CHECK-LABEL: @test2(
|
|
entry:
|
|
%a = alloca [2 x <4 x i32>]
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
|
|
store <4 x i32> %x, <4 x i32>* %a.x
|
|
%a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
|
|
store <4 x i32> %y, <4 x i32>* %a.y
|
|
; CHECK-NOT: store
|
|
|
|
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
|
|
%tmp1 = load i32, i32* %a.tmp1
|
|
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
|
|
%tmp2 = load i32, i32* %a.tmp2
|
|
%a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
|
|
%a.tmp3.cast = bitcast i32* %a.tmp3 to <2 x i32>*
|
|
%tmp3.vec = load <2 x i32>, <2 x i32>* %a.tmp3.cast
|
|
%tmp3 = extractelement <2 x i32> %tmp3.vec, i32 0
|
|
; CHECK-NOT: load
|
|
; CHECK: %[[extract1:.*]] = extractelement <4 x i32> %x, i32 2
|
|
; CHECK-NEXT: %[[extract2:.*]] = extractelement <4 x i32> %y, i32 3
|
|
; CHECK-NEXT: %[[extract3:.*]] = shufflevector <4 x i32> %y, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: %[[extract4:.*]] = extractelement <2 x i32> %[[extract3]], i32 0
|
|
|
|
%tmp4 = add i32 %tmp1, %tmp2
|
|
%tmp5 = add i32 %tmp3, %tmp4
|
|
ret i32 %tmp5
|
|
; CHECK-NEXT: %[[sum1:.*]] = add i32 %[[extract1]], %[[extract2]]
|
|
; CHECK-NEXT: %[[sum2:.*]] = add i32 %[[extract4]], %[[sum1]]
|
|
; CHECK-NEXT: ret i32 %[[sum2]]
|
|
}
|
|
|
|
define i32 @test3(<4 x i32> %x, <4 x i32> %y) {
|
|
; CHECK-LABEL: @test3(
|
|
entry:
|
|
%a = alloca [2 x <4 x i32>]
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
|
|
store <4 x i32> %x, <4 x i32>* %a.x
|
|
%a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
|
|
store <4 x i32> %y, <4 x i32>* %a.y
|
|
; CHECK-NOT: store
|
|
|
|
%a.y.cast = bitcast <4 x i32>* %a.y to i8*
|
|
call void @llvm.memset.p0i8.i32(i8* %a.y.cast, i8 0, i32 16, i1 false)
|
|
; CHECK-NOT: memset
|
|
|
|
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
|
|
%a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
|
|
call void @llvm.memset.p0i8.i32(i8* %a.tmp1.cast, i8 -1, i32 4, i1 false)
|
|
%tmp1 = load i32, i32* %a.tmp1
|
|
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
|
|
%tmp2 = load i32, i32* %a.tmp2
|
|
%a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
|
|
%tmp3 = load i32, i32* %a.tmp3
|
|
; CHECK-NOT: load
|
|
; CHECK: %[[insert:.*]] = insertelement <4 x i32> %x, i32 -1, i32 2
|
|
; CHECK-NEXT: extractelement <4 x i32> %[[insert]], i32 2
|
|
; CHECK-NEXT: extractelement <4 x i32> zeroinitializer, i32 3
|
|
; CHECK-NEXT: extractelement <4 x i32> zeroinitializer, i32 0
|
|
|
|
%tmp4 = add i32 %tmp1, %tmp2
|
|
%tmp5 = add i32 %tmp3, %tmp4
|
|
ret i32 %tmp5
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: ret
|
|
}
|
|
|
|
define i32 @test4(<4 x i32> %x, <4 x i32> %y, <4 x i32>* %z) {
|
|
; CHECK-LABEL: @test4(
|
|
entry:
|
|
%a = alloca [2 x <4 x i32>]
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
|
|
store <4 x i32> %x, <4 x i32>* %a.x
|
|
%a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
|
|
store <4 x i32> %y, <4 x i32>* %a.y
|
|
; CHECK-NOT: store
|
|
|
|
%a.y.cast = bitcast <4 x i32>* %a.y to i8*
|
|
%z.cast = bitcast <4 x i32>* %z to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.y.cast, i8* %z.cast, i32 16, i1 false)
|
|
; CHECK-NOT: memcpy
|
|
|
|
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
|
|
%a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
|
|
%z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
|
|
%z.tmp1.cast = bitcast i32* %z.tmp1 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.tmp1.cast, i8* %z.tmp1.cast, i32 4, i1 false)
|
|
%tmp1 = load i32, i32* %a.tmp1
|
|
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
|
|
%tmp2 = load i32, i32* %a.tmp2
|
|
%a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
|
|
%tmp3 = load i32, i32* %a.tmp3
|
|
; CHECK-NOT: memcpy
|
|
; CHECK: %[[load:.*]] = load <4 x i32>, <4 x i32>* %z
|
|
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
|
|
; CHECK-NEXT: %[[element_load:.*]] = load i32, i32* %[[gep]]
|
|
; CHECK-NEXT: %[[insert:.*]] = insertelement <4 x i32> %x, i32 %[[element_load]], i32 2
|
|
; CHECK-NEXT: extractelement <4 x i32> %[[insert]], i32 2
|
|
; CHECK-NEXT: extractelement <4 x i32> %[[load]], i32 3
|
|
; CHECK-NEXT: extractelement <4 x i32> %[[load]], i32 0
|
|
|
|
%tmp4 = add i32 %tmp1, %tmp2
|
|
%tmp5 = add i32 %tmp3, %tmp4
|
|
ret i32 %tmp5
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: ret
|
|
}
|
|
|
|
declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture, i32, i1) nounwind
|
|
|
|
; Same as test4 with a different sized address space pointer source.
|
|
define i32 @test4_as1(<4 x i32> %x, <4 x i32> %y, <4 x i32> addrspace(1)* %z) {
|
|
; CHECK-LABEL: @test4_as1(
|
|
entry:
|
|
%a = alloca [2 x <4 x i32>]
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
|
|
store <4 x i32> %x, <4 x i32>* %a.x
|
|
%a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
|
|
store <4 x i32> %y, <4 x i32>* %a.y
|
|
; CHECK-NOT: store
|
|
|
|
%a.y.cast = bitcast <4 x i32>* %a.y to i8*
|
|
%z.cast = bitcast <4 x i32> addrspace(1)* %z to i8 addrspace(1)*
|
|
call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.y.cast, i8 addrspace(1)* %z.cast, i32 16, i1 false)
|
|
; CHECK-NOT: memcpy
|
|
|
|
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
|
|
%a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
|
|
%z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %z, i16 0, i16 2
|
|
%z.tmp1.cast = bitcast i32 addrspace(1)* %z.tmp1 to i8 addrspace(1)*
|
|
call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.tmp1.cast, i8 addrspace(1)* %z.tmp1.cast, i32 4, i1 false)
|
|
%tmp1 = load i32, i32* %a.tmp1
|
|
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
|
|
%tmp2 = load i32, i32* %a.tmp2
|
|
%a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
|
|
%tmp3 = load i32, i32* %a.tmp3
|
|
; CHECK-NOT: memcpy
|
|
; CHECK: %[[load:.*]] = load <4 x i32>, <4 x i32> addrspace(1)* %z
|
|
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %z, i64 0, i64 2
|
|
; CHECK-NEXT: %[[element_load:.*]] = load i32, i32 addrspace(1)* %[[gep]]
|
|
; CHECK-NEXT: %[[insert:.*]] = insertelement <4 x i32> %x, i32 %[[element_load]], i32 2
|
|
; CHECK-NEXT: extractelement <4 x i32> %[[insert]], i32 2
|
|
; CHECK-NEXT: extractelement <4 x i32> %[[load]], i32 3
|
|
; CHECK-NEXT: extractelement <4 x i32> %[[load]], i32 0
|
|
|
|
%tmp4 = add i32 %tmp1, %tmp2
|
|
%tmp5 = add i32 %tmp3, %tmp4
|
|
ret i32 %tmp5
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: ret
|
|
}
|
|
|
|
define i32 @test5(<4 x i32> %x, <4 x i32> %y, <4 x i32>* %z) {
|
|
; CHECK-LABEL: @test5(
|
|
; The same as the above, but with reversed source and destination for the
|
|
; element memcpy, and a self copy.
|
|
entry:
|
|
%a = alloca [2 x <4 x i32>]
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
|
|
store <4 x i32> %x, <4 x i32>* %a.x
|
|
%a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
|
|
store <4 x i32> %y, <4 x i32>* %a.y
|
|
; CHECK-NOT: store
|
|
|
|
%a.y.cast = bitcast <4 x i32>* %a.y to i8*
|
|
%a.x.cast = bitcast <4 x i32>* %a.x to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.x.cast, i8* %a.y.cast, i32 16, i1 false)
|
|
; CHECK-NOT: memcpy
|
|
|
|
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
|
|
%a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
|
|
%z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
|
|
%z.tmp1.cast = bitcast i32* %z.tmp1 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %z.tmp1.cast, i8* %a.tmp1.cast, i32 4, i1 false)
|
|
%tmp1 = load i32, i32* %a.tmp1
|
|
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
|
|
%tmp2 = load i32, i32* %a.tmp2
|
|
%a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
|
|
%tmp3 = load i32, i32* %a.tmp3
|
|
; CHECK-NOT: memcpy
|
|
; CHECK: %[[gep:.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
|
|
; CHECK-NEXT: %[[extract:.*]] = extractelement <4 x i32> %y, i32 2
|
|
; CHECK-NEXT: store i32 %[[extract]], i32* %[[gep]]
|
|
; CHECK-NEXT: extractelement <4 x i32> %y, i32 2
|
|
; CHECK-NEXT: extractelement <4 x i32> %y, i32 3
|
|
; CHECK-NEXT: extractelement <4 x i32> %y, i32 0
|
|
|
|
%tmp4 = add i32 %tmp1, %tmp2
|
|
%tmp5 = add i32 %tmp3, %tmp4
|
|
ret i32 %tmp5
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: ret
|
|
}
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
|
|
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
|
|
|
|
define i64 @test6(<4 x i64> %x, <4 x i64> %y, i64 %n) {
|
|
; CHECK-LABEL: @test6(
|
|
; The old scalarrepl pass would wrongly drop the store to the second alloca.
|
|
; PR13254
|
|
%tmp = alloca { <4 x i64>, <4 x i64> }
|
|
%p0 = getelementptr inbounds { <4 x i64>, <4 x i64> }, { <4 x i64>, <4 x i64> }* %tmp, i32 0, i32 0
|
|
store <4 x i64> %x, <4 x i64>* %p0
|
|
; CHECK: store <4 x i64> %x,
|
|
%p1 = getelementptr inbounds { <4 x i64>, <4 x i64> }, { <4 x i64>, <4 x i64> }* %tmp, i32 0, i32 1
|
|
store <4 x i64> %y, <4 x i64>* %p1
|
|
; CHECK: store <4 x i64> %y,
|
|
%addr = getelementptr inbounds { <4 x i64>, <4 x i64> }, { <4 x i64>, <4 x i64> }* %tmp, i32 0, i32 0, i64 %n
|
|
%res = load i64, i64* %addr, align 4
|
|
ret i64 %res
|
|
}
|
|
|
|
define <4 x i32> @test_subvec_store() {
|
|
; CHECK-LABEL: @test_subvec_store(
|
|
entry:
|
|
%a = alloca <4 x i32>
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.gep0 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 0
|
|
%a.cast0 = bitcast i32* %a.gep0 to <2 x i32>*
|
|
store <2 x i32> <i32 0, i32 0>, <2 x i32>* %a.cast0
|
|
; CHECK-NOT: store
|
|
; CHECK: select <4 x i1> <i1 true, i1 true, i1 false, i1 false>
|
|
|
|
%a.gep1 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 1
|
|
%a.cast1 = bitcast i32* %a.gep1 to <2 x i32>*
|
|
store <2 x i32> <i32 1, i32 1>, <2 x i32>* %a.cast1
|
|
; CHECK-NEXT: select <4 x i1> <i1 false, i1 true, i1 true, i1 false>
|
|
|
|
%a.gep2 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 2
|
|
%a.cast2 = bitcast i32* %a.gep2 to <2 x i32>*
|
|
store <2 x i32> <i32 2, i32 2>, <2 x i32>* %a.cast2
|
|
; CHECK-NEXT: select <4 x i1> <i1 false, i1 false, i1 true, i1 true>
|
|
|
|
%a.gep3 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 3
|
|
store i32 3, i32* %a.gep3
|
|
; CHECK-NEXT: insertelement <4 x i32>
|
|
|
|
%ret = load <4 x i32>, <4 x i32>* %a
|
|
|
|
ret <4 x i32> %ret
|
|
; CHECK-NEXT: ret <4 x i32>
|
|
}
|
|
|
|
define <4 x i32> @test_subvec_load() {
|
|
; CHECK-LABEL: @test_subvec_load(
|
|
entry:
|
|
%a = alloca <4 x i32>
|
|
; CHECK-NOT: alloca
|
|
store <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32>* %a
|
|
; CHECK-NOT: store
|
|
|
|
%a.gep0 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 0
|
|
%a.cast0 = bitcast i32* %a.gep0 to <2 x i32>*
|
|
%first = load <2 x i32>, <2 x i32>* %a.cast0
|
|
; CHECK-NOT: load
|
|
; CHECK: %[[extract1:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
|
|
|
|
%a.gep1 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 1
|
|
%a.cast1 = bitcast i32* %a.gep1 to <2 x i32>*
|
|
%second = load <2 x i32>, <2 x i32>* %a.cast1
|
|
; CHECK-NEXT: %[[extract2:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 1, i32 2>
|
|
|
|
%a.gep2 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 2
|
|
%a.cast2 = bitcast i32* %a.gep2 to <2 x i32>*
|
|
%third = load <2 x i32>, <2 x i32>* %a.cast2
|
|
; CHECK-NEXT: %[[extract3:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
|
|
|
|
%tmp = shufflevector <2 x i32> %first, <2 x i32> %second, <2 x i32> <i32 0, i32 2>
|
|
%ret = shufflevector <2 x i32> %tmp, <2 x i32> %third, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: %[[tmp:.*]] = shufflevector <2 x i32> %[[extract1]], <2 x i32> %[[extract2]], <2 x i32> <i32 0, i32 2>
|
|
; CHECK-NEXT: %[[ret:.*]] = shufflevector <2 x i32> %[[tmp]], <2 x i32> %[[extract3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
|
|
ret <4 x i32> %ret
|
|
; CHECK-NEXT: ret <4 x i32> %[[ret]]
|
|
}
|
|
|
|
declare void @llvm.memset.p0i32.i32(i32* nocapture, i32, i32, i1) nounwind
|
|
|
|
define <4 x float> @test_subvec_memset() {
|
|
; CHECK-LABEL: @test_subvec_memset(
|
|
entry:
|
|
%a = alloca <4 x float>
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.gep0 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 0
|
|
%a.cast0 = bitcast float* %a.gep0 to i8*
|
|
call void @llvm.memset.p0i8.i32(i8* %a.cast0, i8 0, i32 8, i1 false)
|
|
; CHECK-NOT: store
|
|
; CHECK: select <4 x i1> <i1 true, i1 true, i1 false, i1 false>
|
|
|
|
%a.gep1 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 1
|
|
%a.cast1 = bitcast float* %a.gep1 to i8*
|
|
call void @llvm.memset.p0i8.i32(i8* %a.cast1, i8 1, i32 8, i1 false)
|
|
; CHECK-NEXT: select <4 x i1> <i1 false, i1 true, i1 true, i1 false>
|
|
|
|
%a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2
|
|
%a.cast2 = bitcast float* %a.gep2 to i8*
|
|
call void @llvm.memset.p0i8.i32(i8* %a.cast2, i8 3, i32 8, i1 false)
|
|
; CHECK-NEXT: select <4 x i1> <i1 false, i1 false, i1 true, i1 true>
|
|
|
|
%a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3
|
|
%a.cast3 = bitcast float* %a.gep3 to i8*
|
|
call void @llvm.memset.p0i8.i32(i8* %a.cast3, i8 7, i32 4, i1 false)
|
|
; CHECK-NEXT: insertelement <4 x float>
|
|
|
|
%ret = load <4 x float>, <4 x float>* %a
|
|
|
|
ret <4 x float> %ret
|
|
; CHECK-NEXT: ret <4 x float>
|
|
}
|
|
|
|
define <4 x float> @test_subvec_memcpy(i8* %x, i8* %y, i8* %z, i8* %f, i8* %out) {
|
|
; CHECK-LABEL: @test_subvec_memcpy(
|
|
entry:
|
|
%a = alloca <4 x float>
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.gep0 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 0
|
|
%a.cast0 = bitcast float* %a.gep0 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast0, i8* %x, i32 8, i1 false)
|
|
; CHECK: %[[xptr:.*]] = bitcast i8* %x to <2 x float>*
|
|
; CHECK-NEXT: %[[x:.*]] = load <2 x float>, <2 x float>* %[[xptr]]
|
|
; CHECK-NEXT: %[[expand_x:.*]] = shufflevector <2 x float> %[[x]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
|
|
; CHECK-NEXT: select <4 x i1> <i1 true, i1 true, i1 false, i1 false>
|
|
|
|
%a.gep1 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 1
|
|
%a.cast1 = bitcast float* %a.gep1 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast1, i8* %y, i32 8, i1 false)
|
|
; CHECK-NEXT: %[[yptr:.*]] = bitcast i8* %y to <2 x float>*
|
|
; CHECK-NEXT: %[[y:.*]] = load <2 x float>, <2 x float>* %[[yptr]]
|
|
; CHECK-NEXT: %[[expand_y:.*]] = shufflevector <2 x float> %[[y]], <2 x float> undef, <4 x i32> <i32 undef, i32 0, i32 1, i32 undef>
|
|
; CHECK-NEXT: select <4 x i1> <i1 false, i1 true, i1 true, i1 false>
|
|
|
|
%a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2
|
|
%a.cast2 = bitcast float* %a.gep2 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast2, i8* %z, i32 8, i1 false)
|
|
; CHECK-NEXT: %[[zptr:.*]] = bitcast i8* %z to <2 x float>*
|
|
; CHECK-NEXT: %[[z:.*]] = load <2 x float>, <2 x float>* %[[zptr]]
|
|
; CHECK-NEXT: %[[expand_z:.*]] = shufflevector <2 x float> %[[z]], <2 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1>
|
|
; CHECK-NEXT: select <4 x i1> <i1 false, i1 false, i1 true, i1 true>
|
|
|
|
%a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3
|
|
%a.cast3 = bitcast float* %a.gep3 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast3, i8* %f, i32 4, i1 false)
|
|
; CHECK-NEXT: %[[fptr:.*]] = bitcast i8* %f to float*
|
|
; CHECK-NEXT: %[[f:.*]] = load float, float* %[[fptr]]
|
|
; CHECK-NEXT: %[[insert_f:.*]] = insertelement <4 x float>
|
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %a.cast2, i32 8, i1 false)
|
|
; CHECK-NEXT: %[[outptr:.*]] = bitcast i8* %out to <2 x float>*
|
|
; CHECK-NEXT: %[[extract_out:.*]] = shufflevector <4 x float> %[[insert_f]], <4 x float> undef, <2 x i32> <i32 2, i32 3>
|
|
; CHECK-NEXT: store <2 x float> %[[extract_out]], <2 x float>* %[[outptr]]
|
|
|
|
%ret = load <4 x float>, <4 x float>* %a
|
|
|
|
ret <4 x float> %ret
|
|
; CHECK-NEXT: ret <4 x float> %[[insert_f]]
|
|
}
|
|
|
|
define i32 @PR14212() {
|
|
; CHECK-LABEL: @PR14212(
|
|
; This caused a crash when "splitting" the load of the i32 in order to promote
|
|
; the store of <3 x i8> properly. Heavily reduced from an OpenCL test case.
|
|
entry:
|
|
%retval = alloca <3 x i8>, align 4
|
|
; CHECK-NOT: alloca
|
|
|
|
store <3 x i8> undef, <3 x i8>* %retval, align 4
|
|
%cast = bitcast <3 x i8>* %retval to i32*
|
|
%load = load i32, i32* %cast, align 4
|
|
ret i32 %load
|
|
; CHECK: ret i32
|
|
}
|
|
|
|
define <2 x i8> @PR14349.1(i32 %x) {
|
|
; CHECK: @PR14349.1
|
|
; The first testcase for broken SROA rewriting of split integer loads and
|
|
; stores due to smaller vector loads and stores. This particular test ensures
|
|
; that we can rewrite a split store of an integer to a store of a vector.
|
|
entry:
|
|
%a = alloca i32
|
|
; CHECK-NOT: alloca
|
|
|
|
store i32 %x, i32* %a
|
|
; CHECK-NOT: store
|
|
|
|
%cast = bitcast i32* %a to <2 x i8>*
|
|
%vec = load <2 x i8>, <2 x i8>* %cast
|
|
; CHECK-NOT: load
|
|
|
|
ret <2 x i8> %vec
|
|
; CHECK: %[[trunc:.*]] = trunc i32 %x to i16
|
|
; CHECK: %[[cast:.*]] = bitcast i16 %[[trunc]] to <2 x i8>
|
|
; CHECK: ret <2 x i8> %[[cast]]
|
|
}
|
|
|
|
define i32 @PR14349.2(<2 x i8> %x) {
|
|
; CHECK: @PR14349.2
|
|
; The first testcase for broken SROA rewriting of split integer loads and
|
|
; stores due to smaller vector loads and stores. This particular test ensures
|
|
; that we can rewrite a split load of an integer to a load of a vector.
|
|
entry:
|
|
%a = alloca i32
|
|
; CHECK-NOT: alloca
|
|
|
|
%cast = bitcast i32* %a to <2 x i8>*
|
|
store <2 x i8> %x, <2 x i8>* %cast
|
|
; CHECK-NOT: store
|
|
|
|
%int = load i32, i32* %a
|
|
; CHECK-NOT: load
|
|
|
|
ret i32 %int
|
|
; CHECK: %[[cast:.*]] = bitcast <2 x i8> %x to i16
|
|
; CHECK: %[[trunc:.*]] = zext i16 %[[cast]] to i32
|
|
; CHECK: %[[insert:.*]] = or i32 %{{.*}}, %[[trunc]]
|
|
; CHECK: ret i32 %[[insert]]
|
|
}
|
|
|
|
define i32 @test7(<2 x i32> %x, <2 x i32> %y) {
|
|
; Test that we can promote to vectors when the alloca doesn't mention any vector types.
|
|
; CHECK-LABEL: @test7(
|
|
entry:
|
|
%a = alloca [2 x i64]
|
|
%a.cast = bitcast [2 x i64]* %a to [2 x <2 x i32>]*
|
|
; CHECK-NOT: alloca
|
|
|
|
%a.x = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 0
|
|
store <2 x i32> %x, <2 x i32>* %a.x
|
|
%a.y = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 1
|
|
store <2 x i32> %y, <2 x i32>* %a.y
|
|
; CHECK-NOT: store
|
|
|
|
%a.tmp1 = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 0, i64 1
|
|
%tmp1 = load i32, i32* %a.tmp1
|
|
%a.tmp2 = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 1, i64 1
|
|
%tmp2 = load i32, i32* %a.tmp2
|
|
%a.tmp3 = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 1, i64 0
|
|
%tmp3 = load i32, i32* %a.tmp3
|
|
; CHECK-NOT: load
|
|
; CHECK: extractelement <2 x i32> %x, i32 1
|
|
; CHECK-NEXT: extractelement <2 x i32> %y, i32 1
|
|
; CHECK-NEXT: extractelement <2 x i32> %y, i32 0
|
|
|
|
%tmp4 = add i32 %tmp1, %tmp2
|
|
%tmp5 = add i32 %tmp3, %tmp4
|
|
ret i32 %tmp5
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: ret
|
|
}
|
|
|
|
define i32 @test8(<2 x i32> %x) {
|
|
; Ensure that we can promote an alloca that doesn't mention a vector type based
|
|
; on a single store with a vector type.
|
|
; CHECK-LABEL: @test8(
|
|
entry:
|
|
%a = alloca i64
|
|
%a.vec = bitcast i64* %a to <2 x i32>*
|
|
%a.i32 = bitcast i64* %a to i32*
|
|
; CHECK-NOT: alloca
|
|
|
|
store <2 x i32> %x, <2 x i32>* %a.vec
|
|
; CHECK-NOT: store
|
|
|
|
%tmp1 = load i32, i32* %a.i32
|
|
%a.tmp2 = getelementptr inbounds i32, i32* %a.i32, i64 1
|
|
%tmp2 = load i32, i32* %a.tmp2
|
|
; CHECK-NOT: load
|
|
; CHECK: extractelement <2 x i32> %x, i32 0
|
|
; CHECK-NEXT: extractelement <2 x i32> %x, i32 1
|
|
|
|
%tmp4 = add i32 %tmp1, %tmp2
|
|
ret i32 %tmp4
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: ret
|
|
}
|
|
|
|
define <2 x i32> @test9(i32 %x, i32 %y) {
|
|
; Ensure that we can promote an alloca that doesn't mention a vector type based
|
|
; on a single load with a vector type.
|
|
; CHECK-LABEL: @test9(
|
|
entry:
|
|
%a = alloca i64
|
|
%a.vec = bitcast i64* %a to <2 x i32>*
|
|
%a.i32 = bitcast i64* %a to i32*
|
|
; CHECK-NOT: alloca
|
|
|
|
store i32 %x, i32* %a.i32
|
|
%a.tmp2 = getelementptr inbounds i32, i32* %a.i32, i64 1
|
|
store i32 %y, i32* %a.tmp2
|
|
; CHECK-NOT: store
|
|
; CHECK: %[[V1:.*]] = insertelement <2 x i32> undef, i32 %x, i32 0
|
|
; CHECK-NEXT: %[[V2:.*]] = insertelement <2 x i32> %[[V1]], i32 %y, i32 1
|
|
|
|
%result = load <2 x i32>, <2 x i32>* %a.vec
|
|
; CHECK-NOT: load
|
|
|
|
ret <2 x i32> %result
|
|
; CHECK-NEXT: ret <2 x i32> %[[V2]]
|
|
}
|
|
|
|
define <2 x i32> @test10(<4 x i16> %x, i32 %y) {
|
|
; If there are multiple different vector types used, we should select the one
|
|
; with the widest elements.
|
|
; CHECK-LABEL: @test10(
|
|
entry:
|
|
%a = alloca i64
|
|
%a.vec1 = bitcast i64* %a to <2 x i32>*
|
|
%a.vec2 = bitcast i64* %a to <4 x i16>*
|
|
%a.i32 = bitcast i64* %a to i32*
|
|
; CHECK-NOT: alloca
|
|
|
|
store <4 x i16> %x, <4 x i16>* %a.vec2
|
|
%a.tmp2 = getelementptr inbounds i32, i32* %a.i32, i64 1
|
|
store i32 %y, i32* %a.tmp2
|
|
; CHECK-NOT: store
|
|
; CHECK: %[[V1:.*]] = bitcast <4 x i16> %x to <2 x i32>
|
|
; CHECK-NEXT: %[[V2:.*]] = insertelement <2 x i32> %[[V1]], i32 %y, i32 1
|
|
|
|
%result = load <2 x i32>, <2 x i32>* %a.vec1
|
|
; CHECK-NOT: load
|
|
|
|
ret <2 x i32> %result
|
|
; CHECK-NEXT: ret <2 x i32> %[[V2]]
|
|
}
|
|
|
|
define <2 x float> @test11(<4 x i16> %x, i32 %y) {
|
|
; If there are multiple different element types for different vector types,
|
|
; pick the integer types. This isn't really important, but seems like the best
|
|
; heuristic for making a deterministic decision.
|
|
; CHECK-LABEL: @test11(
|
|
entry:
|
|
%a = alloca i64
|
|
%a.vec1 = bitcast i64* %a to <2 x float>*
|
|
%a.vec2 = bitcast i64* %a to <4 x i16>*
|
|
%a.i32 = bitcast i64* %a to i32*
|
|
; CHECK-NOT: alloca
|
|
|
|
store <4 x i16> %x, <4 x i16>* %a.vec2
|
|
%a.tmp2 = getelementptr inbounds i32, i32* %a.i32, i64 1
|
|
store i32 %y, i32* %a.tmp2
|
|
; CHECK-NOT: store
|
|
; CHECK: %[[V1:.*]] = bitcast i32 %y to <2 x i16>
|
|
; CHECK-NEXT: %[[V2:.*]] = shufflevector <2 x i16> %[[V1]], <2 x i16> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1>
|
|
; CHECK-NEXT: %[[V3:.*]] = select <4 x i1> <i1 false, i1 false, i1 true, i1 true>, <4 x i16> %[[V2]], <4 x i16> %x
|
|
; CHECK-NEXT: %[[V4:.*]] = bitcast <4 x i16> %[[V3]] to <2 x float>
|
|
|
|
%result = load <2 x float>, <2 x float>* %a.vec1
|
|
; CHECK-NOT: load
|
|
|
|
ret <2 x float> %result
|
|
; CHECK-NEXT: ret <2 x float> %[[V4]]
|
|
}
|
|
|
|
define <4 x float> @test12() {
|
|
; CHECK-LABEL: @test12(
|
|
%a = alloca <3 x i32>, align 16
|
|
; CHECK-NOT: alloca
|
|
|
|
%cast1 = bitcast <3 x i32>* %a to <4 x i32>*
|
|
store <4 x i32> undef, <4 x i32>* %cast1, align 16
|
|
; CHECK-NOT: store
|
|
|
|
%cast2 = bitcast <3 x i32>* %a to <3 x float>*
|
|
%cast3 = bitcast <3 x float>* %cast2 to <4 x float>*
|
|
%vec = load <4 x float>, <4 x float>* %cast3
|
|
; CHECK-NOT: load
|
|
|
|
; CHECK: %[[ret:.*]] = bitcast <4 x i32> undef to <4 x float>
|
|
; CHECK-NEXT: ret <4 x float> %[[ret]]
|
|
ret <4 x float> %vec
|
|
}
|