[DAG] Improve Aliasing of operations to static alloca

Memory accesses offset from frame indices may alias, e.g., we
may merge write from function arguments passed on the stack when they
are contiguous. As a result, when checking aliasing, we consider the
underlying frame index's offset from the stack pointer.

Static allocs are realized as stack objects in SelectionDAG, but its
offset is not set until post-DAG causing DAGCombiner's alias check to
consider access to static allocas to frequently alias. Modify isAlias
to consider access between static allocas and access from other frame
objects to be considered aliasing.

Many test changes are included here. Most are fixes for tests which
indirectly relied on our aliasing ability and needed to be modified to
preserve their original intent.

The remaining tests have minor improvements due to relaxed
ordering. The exception is CodeGen/X86/2011-10-19-widen_vselect.ll
which has a minor degradation dispite though the pre-legalized DAG is
improved.

Reviewers: rnk, mkuper, jonpa, hfinkel, uweigand

Reviewed By: rnk

Subscribers: sdardis, nemanjai, javed.absar, llvm-commits

Differential Revision: https://reviews.llvm.org/D33345

llvm-svn: 307546

6 files changed, 30 insertions, 33 deletions

diff --git a/llvm/test/CodeGen/AArch64/arm64-abi-varargs.ll b/llvm/test/CodeGen/AArch64/arm64-abi-varargs.ll
index 0a796557148..64a6b9b6b21 100644
--- a/llvm/test/CodeGen/AArch64/arm64-abi-varargs.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-abi-varargs.ll
@@ -11,9 +11,8 @@ define void @fn9(i32* %a1, i32 %a2, i32 %a3, i32 %a4, i32 %a5, i32 %a6, i32 %a7,
 ; CHECK: add {{x[0-9]+}}, [[ARGS]], #8
 ; First vararg
 ; CHECK: ldr {{w[0-9]+}}, [sp, #72]
-; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, #8
 ; Second vararg
-; CHECK: ldr {{w[0-9]+}}, [{{x[0-9]+}}]
+; CHECK: ldr {{w[0-9]+}}, [{{x[0-9]+}}], #8
 ; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, #8
 ; Third vararg
 ; CHECK: ldr {{w[0-9]+}}, [{{x[0-9]+}}]
diff --git a/llvm/test/CodeGen/AArch64/arm64-abi_align.ll b/llvm/test/CodeGen/AArch64/arm64-abi_align.ll
index b2ea9ad3b4a..b844aab5628 100644
--- a/llvm/test/CodeGen/AArch64/arm64-abi_align.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-abi_align.ll
@@ -280,10 +280,10 @@ entry:
 define i32 @caller42() #3 {
 entry:
 ; CHECK-LABEL: caller42
-; CHECK: str {{x[0-9]+}}, [sp, #48]
-; CHECK: str {{q[0-9]+}}, [sp, #32]
-; CHECK: str {{x[0-9]+}}, [sp, #16]
-; CHECK: str {{q[0-9]+}}, [sp]
+; CHECK-DAG: str {{x[0-9]+}}, [sp, #48]
+; CHECK-DAG: str {{q[0-9]+}}, [sp, #32]
+; CHECK-DAG: str {{x[0-9]+}}, [sp, #16]
+; CHECK-DAG: str {{q[0-9]+}}, [sp]
 ; CHECK: add x1, sp, #32
 ; CHECK: mov x2, sp
 ; Space for s1 is allocated at sp+32
@@ -318,10 +318,10 @@ entry:
 ; CHECK-LABEL: caller42_stack
 ; CHECK: sub sp, sp, #112
 ; CHECK: add x29, sp, #96
-; CHECK: stur {{x[0-9]+}}, [x29, #-16]
-; CHECK: stur {{q[0-9]+}}, [x29, #-32]
-; CHECK: str {{x[0-9]+}}, [sp, #48]
-; CHECK: str {{q[0-9]+}}, [sp, #32]
+; CHECK-DAG: stur {{x[0-9]+}}, [x29, #-16]
+; CHECK-DAG: stur {{q[0-9]+}}, [x29, #-32]
+; CHECK-DAG: str {{x[0-9]+}}, [sp, #48]
+; CHECK-DAG: str {{q[0-9]+}}, [sp, #32]
 ; Space for s1 is allocated at x29-32 = sp+64
 ; Space for s2 is allocated at sp+32
 ; CHECK: add x[[B:[0-9]+]], sp, #32
@@ -388,10 +388,10 @@ entry:
 define i32 @caller43() #3 {
 entry:
 ; CHECK-LABEL: caller43
-; CHECK: str {{q[0-9]+}}, [sp, #48]
-; CHECK: str {{q[0-9]+}}, [sp, #32]
-; CHECK: str {{q[0-9]+}}, [sp, #16]
-; CHECK: str {{q[0-9]+}}, [sp]
+; CHECK-DAG: str {{q[0-9]+}}, [sp, #48]
+; CHECK-DAG: str {{q[0-9]+}}, [sp, #32]
+; CHECK-DAG: str {{q[0-9]+}}, [sp, #16]
+; CHECK-DAG: str {{q[0-9]+}}, [sp]
 ; CHECK: add x1, sp, #32
 ; CHECK: mov x2, sp
 ; Space for s1 is allocated at sp+32
@@ -430,10 +430,10 @@ entry:
 ; CHECK-LABEL: caller43_stack
 ; CHECK: sub sp, sp, #112
 ; CHECK: add x29, sp, #96
-; CHECK: stur {{q[0-9]+}}, [x29, #-16]
-; CHECK: stur {{q[0-9]+}}, [x29, #-32]
-; CHECK: str {{q[0-9]+}}, [sp, #48]
-; CHECK: str {{q[0-9]+}}, [sp, #32]
+; CHECK-DAG: stur {{q[0-9]+}}, [x29, #-16]
+; CHECK-DAG: stur {{q[0-9]+}}, [x29, #-32]
+; CHECK-DAG: str {{q[0-9]+}}, [sp, #48]
+; CHECK-DAG: str {{q[0-9]+}}, [sp, #32]
 ; Space for s1 is allocated at x29-32 = sp+64
 ; Space for s2 is allocated at sp+32
 ; CHECK: add x[[B:[0-9]+]], sp, #32
diff --git a/llvm/test/CodeGen/AArch64/arm64-alloca-frame-pointer-offset.ll b/llvm/test/CodeGen/AArch64/arm64-alloca-frame-pointer-offset.ll
index a3b740df9b4..fdb37987104 100644
--- a/llvm/test/CodeGen/AArch64/arm64-alloca-frame-pointer-offset.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-alloca-frame-pointer-offset.ll
@@ -1,10 +1,8 @@
 ; RUN: llc -mtriple=arm64-eabi -mcpu=cyclone < %s | FileCheck %s
 
 ; CHECK: foo
-; CHECK: str w[[REG0:[0-9]+]], [x19, #264]
-; CHECK: mov w[[REG1:[0-9]+]], w[[REG0]]
-; CHECK: str w[[REG1]], [x19, #132]
-
+; CHECK-DAG: str w[[REG0:[0-9]+]], [x19, #132]
+; CHECK-DAG: str w[[REG0]], [x19, #264]
 define i32 @foo(i32 %a) nounwind {
   %retval = alloca i32, align 4
   %a.addr = alloca i32, align 4
diff --git a/llvm/test/CodeGen/AArch64/arm64-vext.ll b/llvm/test/CodeGen/AArch64/arm64-vext.ll
index b315e4c409b..c1edf1b2e9b 100644
--- a/llvm/test/CodeGen/AArch64/arm64-vext.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-vext.ll
@@ -116,7 +116,7 @@ define void @test_vext_p16() nounwind ssp {
 
 define void @test_vext_s32() nounwind ssp {
   ; CHECK-LABEL: test_vext_s32:
-  ; CHECK: {{ext.8.*#4}}
+  ; CHECK: {{rev64.2s.*}}
   %xS32x2 = alloca <2 x i32>, align 8
   %__a = alloca <2 x i32>, align 8
   %__b = alloca <2 x i32>, align 8
@@ -137,7 +137,7 @@ define void @test_vext_s32() nounwind ssp {
 
 define void @test_vext_u32() nounwind ssp {
   ; CHECK-LABEL: test_vext_u32:
-  ; CHECK: {{ext.8.*#4}}
+  ; CHECK: {{rev64.2s.*}}
   %xU32x2 = alloca <2 x i32>, align 8
   %__a = alloca <2 x i32>, align 8
   %__b = alloca <2 x i32>, align 8
@@ -158,7 +158,7 @@ define void @test_vext_u32() nounwind ssp {
 
 define void @test_vext_f32() nounwind ssp {
   ; CHECK-LABEL: test_vext_f32:
-  ; CHECK: {{ext.8.*#4}}
+  ; CHECK: {{rev64.2s.*}}
   %xF32x2 = alloca <2 x float>, align 8
   %__a = alloca <2 x float>, align 8
   %__b = alloca <2 x float>, align 8
@@ -179,7 +179,7 @@ define void @test_vext_f32() nounwind ssp {
 
 define void @test_vext_s64() nounwind ssp {
   ; CHECK-LABEL: test_vext_s64:
-  ; CHECK_FIXME: {{ext.8.*#1}}
+  ; CHECK_FIXME: {{rev64.2s.*}}
   ; this just turns into a load of the second element
   %xS64x1 = alloca <1 x i64>, align 8
   %__a = alloca <1 x i64>, align 8
diff --git a/llvm/test/CodeGen/AArch64/dag-combine-invaraints.ll b/llvm/test/CodeGen/AArch64/dag-combine-invaraints.ll
index 20ba3fea837..a2fa1db8a8a 100644
--- a/llvm/test/CodeGen/AArch64/dag-combine-invaraints.ll
+++ b/llvm/test/CodeGen/AArch64/dag-combine-invaraints.ll
@@ -9,7 +9,7 @@ main_:
   %i32T = alloca i32, align 4
   %i32F = alloca i32, align 4
   %i32X = alloca i32, align 4
-  store i32 0, i32* %tmp
+  store i32 %argc, i32* %tmp
   store i32 15, i32* %i32T, align 4
   store i32 5, i32* %i32F, align 4
   %tmp6 = load i32, i32* %tmp, align 4
diff --git a/llvm/test/CodeGen/AArch64/swifterror.ll b/llvm/test/CodeGen/AArch64/swifterror.ll
index bc28f477c81..bcad19e391d 100644
--- a/llvm/test/CodeGen/AArch64/swifterror.ll
+++ b/llvm/test/CodeGen/AArch64/swifterror.ll
@@ -309,17 +309,17 @@ define float @foo_vararg(%swift_error** swifterror %error_ptr_ref, ...) {
 ; CHECK-APPLE-LABEL: foo_vararg:
 ; CHECK-APPLE: orr w0, wzr, #0x10
 ; CHECK-APPLE: malloc
-; CHECK-APPLE: orr [[ID:w[0-9]+]], wzr, #0x1
-; CHECK-APPLE: add [[ARGS:x[0-9]+]], [[TMP:x[0-9]+]], #16
-; CHECK-APPLE: strb [[ID]], [x0, #8]
+; CHECK-APPLE-DAG: orr [[ID:w[0-9]+]], wzr, #0x1
+; CHECK-APPLE-DAG: add [[ARGS:x[0-9]+]], [[TMP:x[0-9]+]], #16
+; CHECK-APPLE-DAG: strb [[ID]], [x0, #8]
 
 ; First vararg
 ; CHECK-APPLE-DAG: orr {{x[0-9]+}}, [[ARGS]], #0x8
 ; CHECK-APPLE-DAG: ldr {{w[0-9]+}}, [{{.*}}[[TMP]], #16]
-; CHECK-APPLE: add {{x[0-9]+}}, {{x[0-9]+}}, #8
+; CHECK-APPLE-DAG: add {{x[0-9]+}}, {{x[0-9]+}}, #8
 ; Second vararg
-; CHECK-APPLE: ldr {{w[0-9]+}}, [{{x[0-9]+}}]
-; CHECK-APPLE: add {{x[0-9]+}}, {{x[0-9]+}}, #8
+; CHECK-APPLE-DAG: ldr {{w[0-9]+}}, [{{x[0-9]+}}], #8
+; CHECK-APPLE-DAG: add {{x[0-9]+}}, {{x[0-9]+}}, #16
 ; Third vararg
 ; CHECK-APPLE: ldr {{w[0-9]+}}, [{{x[0-9]+}}]