8e8d2595da
This patch canonicalizes constant expression GEPs to use i8 source element type, aka ptradd. This is the ConstantFolding equivalent of the InstCombine canonicalization introduced in #68882. I believe all our optimizations working on constant expression GEPs (like GlobalOpt etc) have already been switched to work on offsets, so I don't expect any significant fallout from this change. This is part of: https://discourse.llvm.org/t/rfc-replacing-getelementptr-with-ptradd/68699
42 lines
1.6 KiB
LLVM
42 lines
1.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
|
|
target datalayout = "p:16:16"
|
|
|
|
@a = external global [21 x i16], align 1
|
|
@offsets = external global [4 x i16], align 1
|
|
|
|
; The "same gep" optimization should work with vector icmp.
|
|
define <4 x i1> @PR38984_1() {
|
|
; CHECK-LABEL: @PR38984_1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: ret <4 x i1> <i1 true, i1 true, i1 true, i1 true>
|
|
;
|
|
entry:
|
|
%0 = load i16, ptr @offsets, align 1
|
|
%1 = insertelement <4 x i16> undef, i16 %0, i32 3
|
|
%2 = getelementptr i32, ptr null, <4 x i16> %1
|
|
%3 = getelementptr i32, ptr null, <4 x i16> %1
|
|
%4 = icmp eq <4 x ptr> %2, %3
|
|
ret <4 x i1> %4
|
|
}
|
|
|
|
; The "compare base pointers" optimization should not kick in for vector icmp.
|
|
define <4 x i1> @PR38984_2() {
|
|
; CHECK-LABEL: @PR38984_2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load i16, ptr @offsets, align 2
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i16> <i16 undef, i16 undef, i16 undef, i16 poison>, i16 [[TMP0]], i64 3
|
|
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr i16, ptr getelementptr inbounds (i8, ptr @a, i16 42), <4 x i16> [[TMP1]]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i16, ptr null, <4 x i16> [[TMP1]]
|
|
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq <4 x ptr> [[TMP2]], [[TMP3]]
|
|
; CHECK-NEXT: ret <4 x i1> [[TMP4]]
|
|
;
|
|
entry:
|
|
%0 = load i16, ptr @offsets
|
|
%1 = insertelement <4 x i16> undef, i16 %0, i32 3
|
|
%2 = getelementptr i16, ptr getelementptr ([21 x i16], ptr @a, i64 1, i32 0), <4 x i16> %1
|
|
%3 = getelementptr i16, ptr null, <4 x i16> %1
|
|
%4 = icmp eq <4 x ptr> %2, %3
|
|
ret <4 x i1> %4
|
|
}
|