90ba33099c
This patch canonicalizes getelementptr instructions with constant indices to use the `i8` source element type. This makes it easier for optimizations to recognize that two GEPs are identical, because they don't need to see past many different ways to express the same offset. This is a first step towards https://discourse.llvm.org/t/rfc-replacing-getelementptr-with-ptradd/68699. This is limited to constant GEPs only for now, as they have a clear canonical form, while we're not yet sure how exactly to deal with variable indices. The test llvm/test/Transforms/PhaseOrdering/switch_with_geps.ll gives two representative examples of the kind of optimization improvement we expect from this change. In the first test SimplifyCFG can now realize that all switch branches are actually the same. In the second test it can convert it into simple arithmetic. These are representative of common optimization failures we see in Rust. Fixes https://github.com/llvm/llvm-project/issues/69841.
50 lines
2.0 KiB
LLVM
50 lines
2.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
|
|
|
|
target datalayout = "p:32:32"
|
|
|
|
%S = type { [2 x i32] }
|
|
|
|
define i1 @test(ptr %p, i32 %n) {
|
|
; CHECK-LABEL: @test(
|
|
; CHECK-NEXT: [[END:%.*]] = getelementptr inbounds [0 x %S], ptr [[P:%.*]], i32 0, i32 [[N:%.*]], i32 0, i32 0
|
|
; CHECK-NEXT: [[LAST:%.*]] = getelementptr inbounds i8, ptr [[END]], i32 -8
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp eq ptr [[LAST]], [[P]]
|
|
; CHECK-NEXT: ret i1 [[CMP]]
|
|
;
|
|
%end = getelementptr inbounds [0 x %S], ptr %p, i32 0, i32 %n, i32 0, i32 0
|
|
%last = getelementptr inbounds %S, ptr %end, i32 -1
|
|
%cmp = icmp eq ptr %last, %p
|
|
ret i1 %cmp
|
|
}
|
|
|
|
; Same test using 64-bit indices.
|
|
define i1 @test64(ptr %p, i64 %n) {
|
|
; CHECK-LABEL: @test64(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[N:%.*]] to i32
|
|
; CHECK-NEXT: [[END:%.*]] = getelementptr inbounds [0 x %S], ptr [[P:%.*]], i32 0, i32 [[TMP1]], i32 0, i32 0
|
|
; CHECK-NEXT: [[LAST:%.*]] = getelementptr inbounds i8, ptr [[END]], i32 -8
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp eq ptr [[LAST]], [[P]]
|
|
; CHECK-NEXT: ret i1 [[CMP]]
|
|
;
|
|
%end = getelementptr inbounds [0 x %S], ptr %p, i64 0, i64 %n, i32 0, i64 0
|
|
%last = getelementptr inbounds %S, ptr %end, i64 -1
|
|
%cmp = icmp eq ptr %last, %p
|
|
ret i1 %cmp
|
|
}
|
|
|
|
; Here the offset overflows and is treated modulo 2^32. This is UB.
|
|
define i1 @test64_overflow(ptr %p, i64 %n) {
|
|
; CHECK-LABEL: @test64_overflow(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[N:%.*]] to i32
|
|
; CHECK-NEXT: [[END:%.*]] = getelementptr inbounds [0 x %S], ptr [[P:%.*]], i32 0, i32 [[TMP1]], i32 0, i32 0
|
|
; CHECK-NEXT: [[LAST:%.*]] = getelementptr inbounds i8, ptr [[END]], i32 -8
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp eq ptr [[LAST]], [[P]]
|
|
; CHECK-NEXT: ret i1 [[CMP]]
|
|
;
|
|
%end = getelementptr inbounds [0 x %S], ptr %p, i64 0, i64 %n, i32 0, i64 8589934592
|
|
%last = getelementptr inbounds %S, ptr %end, i64 -1
|
|
%cmp = icmp eq ptr %last, %p
|
|
ret i1 %cmp
|
|
}
|