mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 04:02:41 +01:00
2211738092
Proposed alternative to D105338. This is ugly, but short-term I think it's the best way forward: first, let's formalize the hacks into a coherent model. Then we can consider extensions of that model (we could have different flavors of volatile with different rules). Differential Revision: https://reviews.llvm.org/D106309
92 lines
3.6 KiB
LLVM
92 lines
3.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -O2 -preserve-alignment-assumptions-during-inlining=0 < %s | FileCheck %s --check-prefixes=CHECK,ASSUMPTIONS-OFF
|
|
; RUN: opt -S -O2 -preserve-alignment-assumptions-during-inlining=1 < %s | FileCheck %s --check-prefixes=CHECK,ASSUMPTIONS-ON
|
|
; RUN: opt -S -O2 < %s | FileCheck %s --check-prefixes=CHECK,ASSUMPTIONS-OFF
|
|
|
|
target datalayout = "e-p:64:64-p5:32:32-A5"
|
|
|
|
; This illustrates an optimization difference caused by instruction counting
|
|
; heuristics, which are affected by the additional instructions of the
|
|
; alignment assumption.
|
|
|
|
define internal i1 @callee1(i1 %c, i64* align 8 %ptr) {
|
|
store volatile i64 0, i64* %ptr
|
|
ret i1 %c
|
|
}
|
|
|
|
define void @caller1(i1 %c, i64* align 1 %ptr) {
|
|
; ASSUMPTIONS-OFF-LABEL: @caller1(
|
|
; ASSUMPTIONS-OFF-NEXT: br i1 [[C:%.*]], label [[COMMON_RET:%.*]], label [[FALSE2:%.*]]
|
|
; ASSUMPTIONS-OFF: common.ret:
|
|
; ASSUMPTIONS-OFF-NEXT: [[DOTSINK:%.*]] = phi i64 [ 3, [[FALSE2]] ], [ 2, [[TMP0:%.*]] ]
|
|
; ASSUMPTIONS-OFF-NEXT: store volatile i64 0, i64* [[PTR:%.*]], align 8
|
|
; ASSUMPTIONS-OFF-NEXT: store volatile i64 -1, i64* [[PTR]], align 4
|
|
; ASSUMPTIONS-OFF-NEXT: store volatile i64 -1, i64* [[PTR]], align 4
|
|
; ASSUMPTIONS-OFF-NEXT: store volatile i64 -1, i64* [[PTR]], align 4
|
|
; ASSUMPTIONS-OFF-NEXT: store volatile i64 -1, i64* [[PTR]], align 4
|
|
; ASSUMPTIONS-OFF-NEXT: store volatile i64 -1, i64* [[PTR]], align 4
|
|
; ASSUMPTIONS-OFF-NEXT: store volatile i64 [[DOTSINK]], i64* [[PTR]], align 4
|
|
; ASSUMPTIONS-OFF-NEXT: ret void
|
|
; ASSUMPTIONS-OFF: false2:
|
|
; ASSUMPTIONS-OFF-NEXT: store volatile i64 1, i64* [[PTR]], align 4
|
|
; ASSUMPTIONS-OFF-NEXT: br label [[COMMON_RET]]
|
|
;
|
|
; ASSUMPTIONS-ON-LABEL: @caller1(
|
|
; ASSUMPTIONS-ON-NEXT: br i1 [[C:%.*]], label [[COMMON_RET:%.*]], label [[FALSE1:%.*]]
|
|
; ASSUMPTIONS-ON: false1:
|
|
; ASSUMPTIONS-ON-NEXT: store volatile i64 1, i64* [[PTR:%.*]], align 4
|
|
; ASSUMPTIONS-ON-NEXT: br label [[COMMON_RET]]
|
|
; ASSUMPTIONS-ON: common.ret:
|
|
; ASSUMPTIONS-ON-NEXT: [[DOTSINK:%.*]] = phi i64 [ 3, [[FALSE1]] ], [ 2, [[TMP0:%.*]] ]
|
|
; ASSUMPTIONS-ON-NEXT: call void @llvm.assume(i1 true) [ "align"(i64* [[PTR]], i64 8) ]
|
|
; ASSUMPTIONS-ON-NEXT: store volatile i64 0, i64* [[PTR]], align 8
|
|
; ASSUMPTIONS-ON-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
|
|
; ASSUMPTIONS-ON-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
|
|
; ASSUMPTIONS-ON-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
|
|
; ASSUMPTIONS-ON-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
|
|
; ASSUMPTIONS-ON-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
|
|
; ASSUMPTIONS-ON-NEXT: store volatile i64 [[DOTSINK]], i64* [[PTR]], align 8
|
|
; ASSUMPTIONS-ON-NEXT: ret void
|
|
;
|
|
br i1 %c, label %true1, label %false1
|
|
|
|
true1:
|
|
%c2 = call i1 @callee1(i1 %c, i64* %ptr)
|
|
store volatile i64 -1, i64* %ptr
|
|
store volatile i64 -1, i64* %ptr
|
|
store volatile i64 -1, i64* %ptr
|
|
store volatile i64 -1, i64* %ptr
|
|
store volatile i64 -1, i64* %ptr
|
|
br i1 %c2, label %true2, label %false2
|
|
|
|
false1:
|
|
store volatile i64 1, i64* %ptr
|
|
br label %true1
|
|
|
|
true2:
|
|
store volatile i64 2, i64* %ptr
|
|
ret void
|
|
|
|
false2:
|
|
store volatile i64 3, i64* %ptr
|
|
ret void
|
|
}
|
|
|
|
; This test checks that alignment assumptions do not prevent SROA.
|
|
; See PR45763.
|
|
|
|
define internal void @callee2(i64* noalias sret(i64) align 32 %arg) {
|
|
store i64 0, i64* %arg, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @caller2() {
|
|
; CHECK-LABEL: @caller2(
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%alloca = alloca i64, align 8, addrspace(5)
|
|
%cast = addrspacecast i64 addrspace(5)* %alloca to i64*
|
|
call void @callee2(i64* sret(i64) align 32 %cast)
|
|
ret void
|
|
}
|