aboutsummaryrefslogtreecommitdiff
path: root/test/Transforms/SROA
diff options
context:
space:
mode:
Diffstat (limited to 'test/Transforms/SROA')
-rw-r--r--test/Transforms/SROA/basictest.ll55
-rw-r--r--test/Transforms/SROA/big-endian.ll16
-rw-r--r--test/Transforms/SROA/vector-promotion.ll83
-rw-r--r--test/Transforms/SROA/vectors-of-pointers.ll25
4 files changed, 167 insertions, 12 deletions
diff --git a/test/Transforms/SROA/basictest.ll b/test/Transforms/SROA/basictest.ll
index 9fe926ee2c..efc01acd59 100644
--- a/test/Transforms/SROA/basictest.ll
+++ b/test/Transforms/SROA/basictest.ll
@@ -575,8 +575,8 @@ entry:
store i8 0, i8* %a2ptr
%aiptr = bitcast [3 x i8]* %a to i24*
%ai = load i24* %aiptr
-; CHCEK-NOT: store
-; CHCEK-NOT: load
+; CHECK-NOT: store
+; CHECK-NOT: load
; CHECK: %[[ext2:.*]] = zext i8 0 to i24
; CHECK-NEXT: %[[shift2:.*]] = shl i24 %[[ext2]], 16
; CHECK-NEXT: %[[mask2:.*]] = and i24 undef, 65535
@@ -597,8 +597,8 @@ entry:
%b1 = load i8* %b1ptr
%b2ptr = getelementptr [3 x i8]* %b, i64 0, i32 2
%b2 = load i8* %b2ptr
-; CHCEK-NOT: store
-; CHCEK-NOT: load
+; CHECK-NOT: store
+; CHECK-NOT: load
; CHECK: %[[trunc0:.*]] = trunc i24 %[[insert0]] to i8
; CHECK-NEXT: %[[shift1:.*]] = lshr i24 %[[insert0]], 8
; CHECK-NEXT: %[[trunc1:.*]] = trunc i24 %[[shift1]] to i8
@@ -1176,3 +1176,50 @@ entry:
%baz = load i1* %a.i1, align 1
ret void
}
+
+define <3 x i8> @PR14572.1(i32 %x) {
+; Ensure that a split integer store which is wider than the type size of the
+; alloca (relying on the alloc size padding) doesn't trigger an assert.
+; CHECK: @PR14572.1
+
+entry:
+ %a = alloca <3 x i8>, align 4
+; CHECK-NOT: alloca
+
+ %cast = bitcast <3 x i8>* %a to i32*
+ store i32 %x, i32* %cast, align 1
+ %y = load <3 x i8>* %a, align 4
+ ret <3 x i8> %y
+; CHECK: ret <3 x i8>
+}
+
+define i32 @PR14572.2(<3 x i8> %x) {
+; Ensure that a split integer load which is wider than the type size of the
+; alloca (relying on the alloc size padding) doesn't trigger an assert.
+; CHECK: @PR14572.2
+
+entry:
+ %a = alloca <3 x i8>, align 4
+; CHECK-NOT: alloca
+
+ store <3 x i8> %x, <3 x i8>* %a, align 1
+ %cast = bitcast <3 x i8>* %a to i32*
+ %y = load i32* %cast, align 4
+ ret i32 %y
+; CHECK: ret i32
+}
+
+define i32 @PR14601(i32 %x) {
+; Don't try to form a promotable integer alloca when there is a variable length
+; memory intrinsic.
+; CHECK: @PR14601
+
+entry:
+ %a = alloca i32
+; CHECK: alloca
+
+ %a.i8 = bitcast i32* %a to i8*
+ call void @llvm.memset.p0i8.i32(i8* %a.i8, i8 0, i32 %x, i32 1, i1 false)
+ %v = load i32* %a
+ ret i32 %v
+}
diff --git a/test/Transforms/SROA/big-endian.ll b/test/Transforms/SROA/big-endian.ll
index 1ac6d25d63..64a0cc7439 100644
--- a/test/Transforms/SROA/big-endian.ll
+++ b/test/Transforms/SROA/big-endian.ll
@@ -24,8 +24,8 @@ entry:
store i8 0, i8* %a2ptr
%aiptr = bitcast [3 x i8]* %a to i24*
%ai = load i24* %aiptr
-; CHCEK-NOT: store
-; CHCEK-NOT: load
+; CHECK-NOT: store
+; CHECK-NOT: load
; CHECK: %[[ext2:.*]] = zext i8 0 to i24
; CHECK-NEXT: %[[mask2:.*]] = and i24 undef, -256
; CHECK-NEXT: %[[insert2:.*]] = or i24 %[[mask2]], %[[ext2]]
@@ -46,8 +46,8 @@ entry:
%b1 = load i8* %b1ptr
%b2ptr = getelementptr [3 x i8]* %b, i64 0, i32 2
%b2 = load i8* %b2ptr
-; CHCEK-NOT: store
-; CHCEK-NOT: load
+; CHECK-NOT: store
+; CHECK-NOT: load
; CHECK: %[[shift0:.*]] = lshr i24 %[[insert0]], 16
; CHECK-NEXT: %[[trunc0:.*]] = trunc i24 %[[shift0]] to i8
; CHECK-NEXT: %[[shift1:.*]] = lshr i24 %[[insert0]], 8
@@ -77,8 +77,8 @@ entry:
%a2ptr = getelementptr [7 x i8]* %a, i64 0, i32 2
%a3ptr = getelementptr [7 x i8]* %a, i64 0, i32 3
-; CHCEK-NOT: store
-; CHCEK-NOT: load
+; CHECK-NOT: store
+; CHECK-NOT: load
%a0i16ptr = bitcast i8* %a0ptr to i16*
store i16 1, i16* %a0i16ptr
@@ -98,8 +98,8 @@ entry:
; CHECK-NEXT: %[[mask3:.*]] = and i56 undef, -1099511627776
; CHECK-NEXT: %[[insert3:.*]] = or i56 %[[mask3]], %[[ext3]]
-; CHCEK-NOT: store
-; CHCEK-NOT: load
+; CHECK-NOT: store
+; CHECK-NOT: load
%aiptr = bitcast [7 x i8]* %a to i56*
%ai = load i56* %aiptr
diff --git a/test/Transforms/SROA/vector-promotion.ll b/test/Transforms/SROA/vector-promotion.ll
index bb34e3f084..02f6d040cc 100644
--- a/test/Transforms/SROA/vector-promotion.ll
+++ b/test/Transforms/SROA/vector-promotion.ll
@@ -279,6 +279,89 @@ entry:
; CHECK-NEXT: ret <4 x i32> %[[ret]]
}
+declare void @llvm.memset.p0i32.i32(i32* nocapture, i32, i32, i32, i1) nounwind
+
+define <4 x float> @test_subvec_memset() {
+; CHECK: @test_subvec_memset
+entry:
+ %a = alloca <4 x float>
+; CHECK-NOT: alloca
+
+ %a.gep0 = getelementptr <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, i32 0, i1 false)
+; CHECK-NOT: store
+; CHECK: %[[insert1:.*]] = shufflevector <4 x float> <float 0.000000e+00, float 0.000000e+00, float undef, float undef>, <4 x float> undef, <4 x i32> <i32 0, i32 1, {{.*}}>
+
+ %a.gep1 = getelementptr <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, i32 0, i1 false)
+; CHECK-NEXT: %[[insert2:.*]] = shufflevector <4 x float> <float undef, float 0x3820202020000000, float 0x3820202020000000, float undef>, <4 x float> %[[insert1]], <4 x i32> <i32 4, i32 1, i32 2, {{.*}}>
+
+ %a.gep2 = getelementptr <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, i32 0, i1 false)
+; CHECK-NEXT: %[[insert3:.*]] = shufflevector <4 x float> <float undef, float undef, float 0x3860606060000000, float 0x3860606060000000>, <4 x float> %[[insert2]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
+
+ %a.gep3 = getelementptr <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, i32 0, i1 false)
+; CHECK-NEXT: %[[insert4:.*]] = insertelement <4 x float> %[[insert3]], float 0x38E0E0E0E0000000, i32 3
+
+ %ret = load <4 x float>* %a
+
+ ret <4 x float> %ret
+; CHECK-NEXT: ret <4 x float> %[[insert4]]
+}
+
+define <4 x float> @test_subvec_memcpy(i8* %x, i8* %y, i8* %z, i8* %f, i8* %out) {
+; CHECK: @test_subvec_memcpy
+entry:
+ %a = alloca <4 x float>
+; CHECK-NOT: alloca
+
+ %a.gep0 = getelementptr <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, i32 0, i1 false)
+; CHECK: %[[xptr:.*]] = bitcast i8* %x to <2 x float>*
+; CHECK-NEXT: %[[x:.*]] = load <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: %[[insert_x:.*]] = shufflevector <4 x float> %[[expand_x]], <4 x float> undef, <4 x i32> <i32 0, i32 1, {{.*}}>
+
+ %a.gep1 = getelementptr <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, i32 0, i1 false)
+; CHECK-NEXT: %[[yptr:.*]] = bitcast i8* %y to <2 x float>*
+; CHECK-NEXT: %[[y:.*]] = load <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: %[[insert_y:.*]] = shufflevector <4 x float> %[[expand_y]], <4 x float> %[[insert_x]], <4 x i32> <i32 4, i32 1, i32 2, {{.*}}>
+
+ %a.gep2 = getelementptr <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, i32 0, i1 false)
+; CHECK-NEXT: %[[zptr:.*]] = bitcast i8* %z to <2 x float>*
+; CHECK-NEXT: %[[z:.*]] = load <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: %[[insert_z:.*]] = shufflevector <4 x float> %[[expand_z]], <4 x float> %[[insert_y]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
+
+ %a.gep3 = getelementptr <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, i32 0, i1 false)
+; CHECK-NEXT: %[[fptr:.*]] = bitcast i8* %f to float*
+; CHECK-NEXT: %[[f:.*]] = load float* %[[fptr]]
+; CHECK-NEXT: %[[insert_f:.*]] = insertelement <4 x float> %[[insert_z]], float %[[f]], i32 3
+
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %a.cast2, i32 8, i32 0, 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>* %a
+
+ ret <4 x float> %ret
+; CHECK-NEXT: ret <4 x float> %[[insert_f]]
+}
+
define i32 @PR14212() {
; CHECK: @PR14212
; This caused a crash when "splitting" the load of the i32 in order to promote
diff --git a/test/Transforms/SROA/vectors-of-pointers.ll b/test/Transforms/SROA/vectors-of-pointers.ll
new file mode 100644
index 0000000000..7e995b9e44
--- /dev/null
+++ b/test/Transforms/SROA/vectors-of-pointers.ll
@@ -0,0 +1,25 @@
+; RUN: opt < %s -sroa
+
+; Make sure we don't crash on this one.
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+define void @foo() {
+entry:
+ %Args.i = alloca <2 x i32*>, align 16
+ br i1 undef, label %bb0.exit158, label %if.then.i.i.i.i.i138
+
+if.then.i.i.i.i.i138:
+ unreachable
+
+bb0.exit158:
+ br i1 undef, label %bb0.exit257, label %if.then.i.i.i.i.i237
+
+if.then.i.i.i.i.i237:
+ unreachable
+
+bb0.exit257:
+ %0 = load <2 x i32*>* %Args.i, align 16
+ unreachable
+}
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2024-11-24 13:12:01 +0000