Prior to this patch, computeKnownBits would only try to deduce trailing zeros bits for getelementptrs. This patch adds the logic to treat geps as a series of add * scaling factor. Thanks to this patch, using a gep or performing an address computation directly "by hand" (ptrtoint followed by adds and mul followed by inttoptr) offers the same computeKnownBits information. Previously, the "by hand" approach would have given more information. This is related to https://llvm.org/PR47241. Differential Revision: https://reviews.llvm.org/D86364
120 lines
7.5 KiB
LLVM
120 lines
7.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -instcombine -S | FileCheck %s
|
|
target datalayout = "E-p:64:64:64-p1:16:16:16-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"
|
|
|
|
; Constant folding should fix notionally out-of-bounds indices
|
|
; and add inbounds keywords.
|
|
|
|
%struct.X = type { [3 x i32], [3 x i32] }
|
|
|
|
@Y = internal global [3 x %struct.X] zeroinitializer
|
|
|
|
define void @frob() {
|
|
; CHECK-LABEL: @frob(
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 0), align 16
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 1), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 2), align 8
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 1, i64 0), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 1, i64 1), align 16
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 1, i64 2), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 1, i32 0, i64 0), align 8
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 1, i32 0, i64 1), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 1, i32 0, i64 2), align 16
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 1, i32 1, i64 0), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 1, i32 1, i64 1), align 8
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 1, i32 1, i64 2), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 2, i32 0, i64 0), align 16
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 2, i32 0, i64 1), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 2, i32 0, i64 2), align 8
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 2, i32 1, i64 0), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 2, i32 1, i64 1), align 16
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 2, i32 1, i64 2), align 4
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr inbounds ([3 x %struct.X], [3 x %struct.X]* @Y, i64 1, i64 0, i32 0, i64 0), align 8
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 2, i64 0, i32 0, i64 0), align 16
|
|
; CHECK-NEXT: store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 1, i64 0, i32 0, i64 1), align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 0), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 1), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 2), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 3), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 4), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 5), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 6), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 7), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 8), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 9), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 10), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 11), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 12), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 13), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 14), align 8
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 15), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 16), align 8
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 17), align 4
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 18), align 8
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 36), align 8
|
|
store i32 1, i32* getelementptr ([3 x %struct.X], [3 x %struct.X]* @Y, i64 0, i64 0, i32 0, i64 19), align 8
|
|
ret void
|
|
}
|
|
|
|
|
|
; PR8883 - Constant fold exotic gep subtract
|
|
@X = global [1000 x i8] zeroinitializer, align 16
|
|
|
|
define i64 @test2() {
|
|
; CHECK-LABEL: @test2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: ret i64 1000
|
|
;
|
|
entry:
|
|
%A = bitcast i8* getelementptr inbounds ([1000 x i8], [1000 x i8]* @X, i64 1, i64 0) to i8*
|
|
%B = bitcast i8* getelementptr inbounds ([1000 x i8], [1000 x i8]* @X, i64 0, i64 0) to i8*
|
|
|
|
%B2 = ptrtoint i8* %B to i64
|
|
%C = sub i64 0, %B2
|
|
%D = getelementptr i8, i8* %A, i64 %C
|
|
%E = ptrtoint i8* %D to i64
|
|
|
|
ret i64 %E
|
|
}
|
|
|
|
@X_as1 = addrspace(1) global [1000 x i8] zeroinitializer, align 16
|
|
|
|
define i16 @test2_as1() {
|
|
; CHECK-LABEL: @test2_as1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: ret i16 1000
|
|
;
|
|
|
|
entry:
|
|
%A = bitcast i8 addrspace(1)* getelementptr inbounds ([1000 x i8], [1000 x i8] addrspace(1)* @X_as1, i64 1, i64 0) to i8 addrspace(1)*
|
|
%B = bitcast i8 addrspace(1)* getelementptr inbounds ([1000 x i8], [1000 x i8] addrspace(1)* @X_as1, i64 0, i64 0) to i8 addrspace(1)*
|
|
|
|
%B2 = ptrtoint i8 addrspace(1)* %B to i16
|
|
%C = sub i16 0, %B2
|
|
%D = getelementptr i8, i8 addrspace(1)* %A, i16 %C
|
|
%E = ptrtoint i8 addrspace(1)* %D to i16
|
|
|
|
ret i16 %E
|
|
}
|
|
|
|
; Check that we improve the alignment information.
|
|
; The base pointer is 16-byte aligned and we access the field at
|
|
; an offset of 8-byte.
|
|
; Every element in the @CallerInfos array is 16-byte aligned so
|
|
; any access from the following gep is 8-byte aligned.
|
|
%struct.CallerInfo = type { i8*, i32 }
|
|
@CallerInfos = global [128 x %struct.CallerInfo] zeroinitializer, align 16
|
|
|
|
define i32 @test_gep_in_struct(i64 %idx) {
|
|
; CHECK-LABEL: @test_gep_in_struct(
|
|
; CHECK-NEXT: [[NS7:%.*]] = getelementptr inbounds [128 x %struct.CallerInfo], [128 x %struct.CallerInfo]* @CallerInfos, i64 0, i64 [[IDX:%.*]], i32 1
|
|
; CHECK-NEXT: [[RES:%.*]] = load i32, i32* [[NS7]], align 8
|
|
; CHECK-NEXT: ret i32 [[RES]]
|
|
;
|
|
%NS7 = getelementptr inbounds [128 x %struct.CallerInfo], [128 x %struct.CallerInfo]* @CallerInfos, i64 0, i64 %idx, i32 1
|
|
%res = load i32, i32* %NS7, align 1
|
|
ret i32 %res
|
|
}
|