maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/InstCombine/memcpy-from-global.ll

207 lines
10 KiB
LLVM
Raw Normal View History

Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
; RUN: opt < %s -instcombine -S | FileCheck %s
Make opt default to not adding a target data string and update tests that depend on target data to supply it within the test llvm-svn: 85900
2009-11-03 23:29:06 +08:00
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"
new testcase, should be able to eliminate the alloca and memcpy llvm-svn: 36428
2007-04-25 14:29:34 +08:00
@C.0.1248 = internal constant [128 x float] [ float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00 ], align 32 ; <[128 x float]*> [#uses=1]
filecheckize llvm-svn: 119681
2010-11-18 14:16:43 +08:00
define float @test1(i32 %hash, float %x, float %y, float %z, float %w) {
new testcase, should be able to eliminate the alloca and memcpy llvm-svn: 36428
2007-04-25 14:29:34 +08:00
entry:
%lookupTable = alloca [128 x float], align 16 ; <[128 x float]*> [#uses=5]
%lookupTable1 = bitcast [128 x float]* %lookupTable to i8* ; <i8*> [#uses=1]
Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %lookupTable1, i8* bitcast ([128 x float]* @C.0.1248 to i8*), i64 512, i32 16, i1 false)
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test1(
filecheckize llvm-svn: 119681
2010-11-18 14:16:43 +08:00
; CHECK-NOT: alloca
; CHECK-NOT: call{{.*}}@llvm.memcpy
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
new testcase, should be able to eliminate the alloca and memcpy llvm-svn: 36428
2007-04-25 14:29:34 +08:00
%tmp3 = shl i32 %hash, 2 ; <i32> [#uses=1]
%tmp5 = and i32 %tmp3, 124 ; <i32> [#uses=4]
%tmp753 = getelementptr [128 x float]* %lookupTable, i32 0, i32 %tmp5 ; <float*> [#uses=1]
%tmp9 = load float* %tmp753 ; <float> [#uses=1]
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
%tmp11 = fmul float %tmp9, %x ; <float> [#uses=1]
%tmp13 = fadd float %tmp11, 0.000000e+00 ; <float> [#uses=1]
new testcase, should be able to eliminate the alloca and memcpy llvm-svn: 36428
2007-04-25 14:29:34 +08:00
%tmp17.sum52 = or i32 %tmp5, 1 ; <i32> [#uses=1]
%tmp1851 = getelementptr [128 x float]* %lookupTable, i32 0, i32 %tmp17.sum52 ; <float*> [#uses=1]
%tmp19 = load float* %tmp1851 ; <float> [#uses=1]
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
%tmp21 = fmul float %tmp19, %y ; <float> [#uses=1]
%tmp23 = fadd float %tmp21, %tmp13 ; <float> [#uses=1]
new testcase, should be able to eliminate the alloca and memcpy llvm-svn: 36428
2007-04-25 14:29:34 +08:00
%tmp27.sum50 = or i32 %tmp5, 2 ; <i32> [#uses=1]
%tmp2849 = getelementptr [128 x float]* %lookupTable, i32 0, i32 %tmp27.sum50 ; <float*> [#uses=1]
%tmp29 = load float* %tmp2849 ; <float> [#uses=1]
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
%tmp31 = fmul float %tmp29, %z ; <float> [#uses=1]
%tmp33 = fadd float %tmp31, %tmp23 ; <float> [#uses=1]
new testcase, should be able to eliminate the alloca and memcpy llvm-svn: 36428
2007-04-25 14:29:34 +08:00
%tmp37.sum48 = or i32 %tmp5, 3 ; <i32> [#uses=1]
%tmp3847 = getelementptr [128 x float]* %lookupTable, i32 0, i32 %tmp37.sum48 ; <float*> [#uses=1]
%tmp39 = load float* %tmp3847 ; <float> [#uses=1]
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
%tmp41 = fmul float %tmp39, %w ; <float> [#uses=1]
%tmp43 = fadd float %tmp41, %tmp33 ; <float> [#uses=1]
new testcase, should be able to eliminate the alloca and memcpy llvm-svn: 36428
2007-04-25 14:29:34 +08:00
ret float %tmp43
}
fix a small oversight in the "eliminate memcpy from constant global" optimization. If the alloca that is "memcpy'd from constant" also has a memcpy from *it*, ignore it: it is a load. We now optimize the testcase to: define void @test2() { %B = alloca %T %a = bitcast %T* @G to i8* %b = bitcast %T* %B to i8* call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) call void @bar(i8* %b) ret void } previously we would generate: define void @test() { %B = alloca %T %b = bitcast %T* %B to i8* %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0 %tmp3 = load i8* %G.0, align 4 %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1 %G.15 = bitcast [123 x i8]* %G.1 to i8* %1 = bitcast [123 x i8]* %G.1 to i984* %srcval = load i984* %1, align 1 %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0 store i8 %tmp3, i8* %B.0, align 4 %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1 %B.12 = bitcast [123 x i8]* %B.1 to i8* %2 = bitcast [123 x i8]* %B.1 to i984* store i984 %srcval, i984* %2, align 1 call void @bar(i8* %b) ret void } llvm-svn: 119682
2010-11-18 14:20:47 +08:00
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture, i8* nocapture, i64, i32, i1) nounwind
declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind
declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind
fix a small oversight in the "eliminate memcpy from constant global" optimization. If the alloca that is "memcpy'd from constant" also has a memcpy from *it*, ignore it: it is a load. We now optimize the testcase to: define void @test2() { %B = alloca %T %a = bitcast %T* @G to i8* %b = bitcast %T* %B to i8* call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) call void @bar(i8* %b) ret void } previously we would generate: define void @test() { %B = alloca %T %b = bitcast %T* %B to i8* %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0 %tmp3 = load i8* %G.0, align 4 %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1 %G.15 = bitcast [123 x i8]* %G.1 to i8* %1 = bitcast [123 x i8]* %G.1 to i984* %srcval = load i984* %1, align 1 %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0 store i8 %tmp3, i8* %B.0, align 4 %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1 %B.12 = bitcast [123 x i8]* %B.1 to i8* %2 = bitcast [123 x i8]* %B.1 to i984* store i984 %srcval, i984* %2, align 1 call void @bar(i8* %b) ret void } llvm-svn: 119682
2010-11-18 14:20:47 +08:00
%T = type { i8, [123 x i8] }
Do not eliminate allocas whose alignment exceeds that of the copied-in constant, as a subsequent user may rely on over alignment. Fixes PR12885. llvm-svn: 157134
2012-05-20 06:52:10 +08:00
%U = type { i32, i32, i32, i32, i32 }
fix a small oversight in the "eliminate memcpy from constant global" optimization. If the alloca that is "memcpy'd from constant" also has a memcpy from *it*, ignore it: it is a load. We now optimize the testcase to: define void @test2() { %B = alloca %T %a = bitcast %T* @G to i8* %b = bitcast %T* %B to i8* call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) call void @bar(i8* %b) ret void } previously we would generate: define void @test() { %B = alloca %T %b = bitcast %T* %B to i8* %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0 %tmp3 = load i8* %G.0, align 4 %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1 %G.15 = bitcast [123 x i8]* %G.1 to i8* %1 = bitcast [123 x i8]* %G.1 to i984* %srcval = load i984* %1, align 1 %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0 store i8 %tmp3, i8* %B.0, align 4 %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1 %B.12 = bitcast [123 x i8]* %B.1 to i8* %2 = bitcast [123 x i8]* %B.1 to i984* store i984 %srcval, i984* %2, align 1 call void @bar(i8* %b) ret void } llvm-svn: 119682
2010-11-18 14:20:47 +08:00
@G = constant %T {i8 1, [123 x i8] zeroinitializer }
Do not eliminate allocas whose alignment exceeds that of the copied-in constant, as a subsequent user may rely on over alignment. Fixes PR12885. llvm-svn: 157134
2012-05-20 06:52:10 +08:00
@H = constant [2 x %U] zeroinitializer, align 16
fix a small oversight in the "eliminate memcpy from constant global" optimization. If the alloca that is "memcpy'd from constant" also has a memcpy from *it*, ignore it: it is a load. We now optimize the testcase to: define void @test2() { %B = alloca %T %a = bitcast %T* @G to i8* %b = bitcast %T* %B to i8* call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) call void @bar(i8* %b) ret void } previously we would generate: define void @test() { %B = alloca %T %b = bitcast %T* %B to i8* %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0 %tmp3 = load i8* %G.0, align 4 %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1 %G.15 = bitcast [123 x i8]* %G.1 to i8* %1 = bitcast [123 x i8]* %G.1 to i984* %srcval = load i984* %1, align 1 %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0 store i8 %tmp3, i8* %B.0, align 4 %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1 %B.12 = bitcast [123 x i8]* %B.1 to i8* %2 = bitcast [123 x i8]* %B.1 to i984* store i984 %srcval, i984* %2, align 1 call void @bar(i8* %b) ret void } llvm-svn: 119682
2010-11-18 14:20:47 +08:00
define void @test2() {
%A = alloca %T
%B = alloca %T
%a = bitcast %T* %A to i8*
%b = bitcast %T* %B to i8*
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test2(
fix a small oversight in the "eliminate memcpy from constant global" optimization. If the alloca that is "memcpy'd from constant" also has a memcpy from *it*, ignore it: it is a load. We now optimize the testcase to: define void @test2() { %B = alloca %T %a = bitcast %T* @G to i8* %b = bitcast %T* %B to i8* call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) call void @bar(i8* %b) ret void } previously we would generate: define void @test() { %B = alloca %T %b = bitcast %T* %B to i8* %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0 %tmp3 = load i8* %G.0, align 4 %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1 %G.15 = bitcast [123 x i8]* %G.1 to i8* %1 = bitcast [123 x i8]* %G.1 to i984* %srcval = load i984* %1, align 1 %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0 store i8 %tmp3, i8* %B.0, align 4 %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1 %B.12 = bitcast [123 x i8]* %B.1 to i8* %2 = bitcast [123 x i8]* %B.1 to i984* store i984 %srcval, i984* %2, align 1 call void @bar(i8* %b) ret void } llvm-svn: 119682
2010-11-18 14:20:47 +08:00
; %A alloca is deleted
Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
; CHECK-NEXT: alloca [124 x i8]
; CHECK-NEXT: getelementptr inbounds [124 x i8]*
fix a small oversight in the "eliminate memcpy from constant global" optimization. If the alloca that is "memcpy'd from constant" also has a memcpy from *it*, ignore it: it is a load. We now optimize the testcase to: define void @test2() { %B = alloca %T %a = bitcast %T* @G to i8* %b = bitcast %T* %B to i8* call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) call void @bar(i8* %b) ret void } previously we would generate: define void @test() { %B = alloca %T %b = bitcast %T* %B to i8* %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0 %tmp3 = load i8* %G.0, align 4 %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1 %G.15 = bitcast [123 x i8]* %G.1 to i8* %1 = bitcast [123 x i8]* %G.1 to i984* %srcval = load i984* %1, align 1 %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0 store i8 %tmp3, i8* %B.0, align 4 %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1 %B.12 = bitcast [123 x i8]* %B.1 to i8* %2 = bitcast [123 x i8]* %B.1 to i984* store i984 %srcval, i984* %2, align 1 call void @bar(i8* %b) ret void } llvm-svn: 119682
2010-11-18 14:20:47 +08:00
; use @G instead of %A
Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %{{.*}}, i8* getelementptr inbounds (%T* @G, i64 0, i32 0)
fix a small oversight in the "eliminate memcpy from constant global" optimization. If the alloca that is "memcpy'd from constant" also has a memcpy from *it*, ignore it: it is a load. We now optimize the testcase to: define void @test2() { %B = alloca %T %a = bitcast %T* @G to i8* %b = bitcast %T* %B to i8* call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) call void @bar(i8* %b) ret void } previously we would generate: define void @test() { %B = alloca %T %b = bitcast %T* %B to i8* %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0 %tmp3 = load i8* %G.0, align 4 %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1 %G.15 = bitcast [123 x i8]* %G.1 to i8* %1 = bitcast [123 x i8]* %G.1 to i984* %srcval = load i984* %1, align 1 %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0 store i8 %tmp3, i8* %B.0, align 4 %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1 %B.12 = bitcast [123 x i8]* %B.1 to i8* %2 = bitcast [123 x i8]* %B.1 to i984* store i984 %srcval, i984* %2, align 1 call void @bar(i8* %b) ret void } llvm-svn: 119682
2010-11-18 14:20:47 +08:00
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false)
call void @bar(i8* %b)
ret void
}
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
define void @test2_addrspacecast() {
%A = alloca %T
%B = alloca %T
%a = addrspacecast %T* %A to i8 addrspace(1)*
%b = addrspacecast %T* %B to i8 addrspace(1)*
; CHECK-LABEL: @test2_addrspacecast(
; %A alloca is deleted
; This doesn't exactly match what test2 does, because folding the type
; cast into the alloca doesn't work for the addrspacecast yet.
InstCombine: Canonicalize addrspacecast between different element types addrspacecast X addrspace(M)* to Y addrspace(N)* --> bitcast X addrspace(M)* to Y addrspace(M)* addrspacecast Y addrspace(M)* to Y addrspace(N)* Updat all affected tests and add several new tests in addrspacecast.ll. This patch is based on http://reviews.llvm.org/D2186 (authored by Matt Arsenault) with fixes and more tests. llvm-svn: 210375
2014-06-07 05:52:55 +08:00
; CHECK-NEXT: alloca [124 x i8]
; CHECK-NEXT: getelementptr
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
; CHECK-NEXT: addrspacecast
; use @G instead of %A
; CHECK-NEXT: call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %{{.*}},
call void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false)
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %b, i8 addrspace(1)* %a, i64 124, i32 4, i1 false)
call void @bar_as1(i8 addrspace(1)* %b)
ret void
}
fix a small oversight in the "eliminate memcpy from constant global" optimization. If the alloca that is "memcpy'd from constant" also has a memcpy from *it*, ignore it: it is a load. We now optimize the testcase to: define void @test2() { %B = alloca %T %a = bitcast %T* @G to i8* %b = bitcast %T* %B to i8* call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) call void @bar(i8* %b) ret void } previously we would generate: define void @test() { %B = alloca %T %b = bitcast %T* %B to i8* %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0 %tmp3 = load i8* %G.0, align 4 %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1 %G.15 = bitcast [123 x i8]* %G.1 to i8* %1 = bitcast [123 x i8]* %G.1 to i984* %srcval = load i984* %1, align 1 %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0 store i8 %tmp3, i8* %B.0, align 4 %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1 %B.12 = bitcast [123 x i8]* %B.1 to i8* %2 = bitcast [123 x i8]* %B.1 to i984* store i984 %srcval, i984* %2, align 1 call void @bar(i8* %b) ret void } llvm-svn: 119682
2010-11-18 14:20:47 +08:00
declare void @bar(i8*)
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
declare void @bar_as1(i8 addrspace(1)*)
enhance the "alloca is just a memcpy from constant global" to ignore calls that obviously can't modify the alloca because they are readonly/readnone. llvm-svn: 119683
2010-11-18 14:26:49 +08:00
;; Should be able to eliminate the alloca.
define void @test3() {
%A = alloca %T
%a = bitcast %T* %A to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false)
call void @bar(i8* %a) readonly
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test3(
Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
; CHECK-NEXT: call void @bar(i8* getelementptr inbounds (%T* @G, i64 0, i32 0))
enhance the "alloca is just a memcpy from constant global" to ignore calls that obviously can't modify the alloca because they are readonly/readnone. llvm-svn: 119683
2010-11-18 14:26:49 +08:00
ret void
}
allow eliminating an alloca that is just copied from an constant global if it is passed as a byval argument. The byval argument will just be a read, so it is safe to read from the original global instead. This allows us to promote away the %agg.tmp alloca in PR8582 llvm-svn: 119686
2010-11-18 14:41:51 +08:00
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
define void @test3_addrspacecast() {
%A = alloca %T
%a = bitcast %T* %A to i8*
call void @llvm.memcpy.p0i8.p1i8.i64(i8* %a, i8 addrspace(1)* addrspacecast (%T* @G to i8 addrspace(1)*), i64 124, i32 4, i1 false)
call void @bar(i8* %a) readonly
; CHECK-LABEL: @test3_addrspacecast(
; CHECK-NEXT: call void @bar(i8* getelementptr inbounds (%T* @G, i64 0, i32 0))
ret void
}
allow eliminating an alloca that is just copied from an constant global if it is passed as a byval argument. The byval argument will just be a read, so it is safe to read from the original global instead. This allows us to promote away the %agg.tmp alloca in PR8582 llvm-svn: 119686
2010-11-18 14:41:51 +08:00
define void @test4() {
%A = alloca %T
%a = bitcast %T* %A to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false)
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
call void @baz(i8* byval %a)
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test4(
Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
; CHECK-NEXT: call void @baz(i8* byval getelementptr inbounds (%T* @G, i64 0, i32 0))
allow eliminating an alloca that is just copied from an constant global if it is passed as a byval argument. The byval argument will just be a read, so it is safe to read from the original global instead. This allows us to promote away the %agg.tmp alloca in PR8582 llvm-svn: 119686
2010-11-18 14:41:51 +08:00
ret void
}
Teach one piece of scalarrepl to handle lifetime markers. When transforming an alloca that only holds a copy of a global and we're going to replace the users of the alloca with that global, just nuke the lifetime intrinsics. Part of PR10121. llvm-svn: 133905
2011-06-27 13:40:02 +08:00
declare void @llvm.lifetime.start(i64, i8*)
define void @test5() {
%A = alloca %T
%a = bitcast %T* %A to i8*
call void @llvm.lifetime.start(i64 -1, i8* %a)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false)
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
call void @baz(i8* byval %a)
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test5(
Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
; CHECK-NEXT: call void @baz(i8* byval getelementptr inbounds (%T* @G, i64 0, i32 0))
Teach one piece of scalarrepl to handle lifetime markers. When transforming an alloca that only holds a copy of a global and we're going to replace the users of the alloca with that global, just nuke the lifetime intrinsics. Part of PR10121. llvm-svn: 133905
2011-06-27 13:40:02 +08:00
ret void
}
allow eliminating an alloca that is just copied from an constant global if it is passed as a byval argument. The byval argument will just be a read, so it is safe to read from the original global instead. This allows us to promote away the %agg.tmp alloca in PR8582 llvm-svn: 119686
2010-11-18 14:41:51 +08:00
declare void @baz(i8* byval)
Do not eliminate allocas whose alignment exceeds that of the copied-in constant, as a subsequent user may rely on over alignment. Fixes PR12885. llvm-svn: 157134
2012-05-20 06:52:10 +08:00
define void @test6() {
%A = alloca %U, align 16
%a = bitcast %U* %A to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast ([2 x %U]* @H to i8*), i64 20, i32 16, i1 false)
call void @bar(i8* %a) readonly
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test6(
Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
; CHECK-NEXT: call void @bar(i8* bitcast ([2 x %U]* @H to i8*))
Do not eliminate allocas whose alignment exceeds that of the copied-in constant, as a subsequent user may rely on over alignment. Fixes PR12885. llvm-svn: 157134
2012-05-20 06:52:10 +08:00
ret void
}
define void @test7() {
%A = alloca %U, align 16
%a = bitcast %U* %A to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%U* getelementptr ([2 x %U]* @H, i64 0, i32 0) to i8*), i64 20, i32 4, i1 false)
call void @bar(i8* %a) readonly
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test7(
Port the global copy optimization from the SROA pass to InstCombine. This optimization is really just replacing allocas wholesale with globals, there is no scalarization. The underlying motivation for this patch is to simplify the SROA pass and focus it on splitting and promoting allocas. llvm-svn: 162271
2012-08-21 16:39:44 +08:00
; CHECK-NEXT: call void @bar(i8* bitcast ([2 x %U]* @H to i8*))
Do not eliminate allocas whose alignment exceeds that of the copied-in constant, as a subsequent user may rely on over alignment. Fixes PR12885. llvm-svn: 157134
2012-05-20 06:52:10 +08:00
ret void
}
define void @test8() {
%A = alloca %U, align 16
%a = bitcast %U* %A to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%U* getelementptr ([2 x %U]* @H, i64 0, i32 1) to i8*), i64 20, i32 4, i1 false)
call void @bar(i8* %a) readonly
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test8(
Do not eliminate allocas whose alignment exceeds that of the copied-in constant, as a subsequent user may rely on over alignment. Fixes PR12885. llvm-svn: 157134
2012-05-20 06:52:10 +08:00
; CHECK: llvm.memcpy
; CHECK: bar
ret void
}
Get rid of the getPointeeAlignment helper function from InstCombineLoadStoreAlloca.cpp, which had many issues. (At least two bugs were noted on llvm-commits, and it was overly conservative.) Instead, use getOrEnforceKnownAlignment. llvm-svn: 168629
2012-11-27 07:04:53 +08:00
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
define void @test8_addrspacecast() {
%A = alloca %U, align 16
%a = bitcast %U* %A to i8*
call void @llvm.memcpy.p0i8.p1i8.i64(i8* %a, i8 addrspace(1)* addrspacecast (%U* getelementptr ([2 x %U]* @H, i64 0, i32 1) to i8 addrspace(1)*), i64 20, i32 4, i1 false)
call void @bar(i8* %a) readonly
; CHECK-LABEL: @test8_addrspacecast(
; CHECK: llvm.memcpy
; CHECK: bar
ret void
}
Get rid of the getPointeeAlignment helper function from InstCombineLoadStoreAlloca.cpp, which had many issues. (At least two bugs were noted on llvm-commits, and it was overly conservative.) Instead, use getOrEnforceKnownAlignment. llvm-svn: 168629
2012-11-27 07:04:53 +08:00
define void @test9() {
%A = alloca %U, align 4
%a = bitcast %U* %A to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%U* getelementptr ([2 x %U]* @H, i64 0, i32 1) to i8*), i64 20, i32 4, i1 false)
call void @bar(i8* %a) readonly
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test9(
Get rid of the getPointeeAlignment helper function from InstCombineLoadStoreAlloca.cpp, which had many issues. (At least two bugs were noted on llvm-commits, and it was overly conservative.) Instead, use getOrEnforceKnownAlignment. llvm-svn: 168629
2012-11-27 07:04:53 +08:00
; CHECK-NEXT: call void @bar(i8* bitcast (%U* getelementptr inbounds ([2 x %U]* @H, i64 0, i64 1) to i8*))
ret void
}
Handle addrspacecast when looking at memcpys from globals llvm-svn: 207054
2014-04-24 08:01:09 +08:00
define void @test9_addrspacecast() {
%A = alloca %U, align 4
%a = bitcast %U* %A to i8*
call void @llvm.memcpy.p0i8.p1i8.i64(i8* %a, i8 addrspace(1)* addrspacecast (%U* getelementptr ([2 x %U]* @H, i64 0, i32 1) to i8 addrspace(1)*), i64 20, i32 4, i1 false)
call void @bar(i8* %a) readonly
; CHECK-LABEL: @test9_addrspacecast(
; CHECK-NEXT: call void @bar(i8* bitcast (%U* getelementptr inbounds ([2 x %U]* @H, i64 0, i64 1) to i8*))
ret void
}