1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
llvm-mirror/test/Transforms/SimplifyCFG/unprofitable-pr.ll
Max Kazantsev c1e656184f [SimplifyCFG] Fix inconsistency in block size assessment for threading
Sometimes SimplifyCFG may decide to perform jump threading. In order
to do it, it follows the following algorithm:

1. Checks if the block is small enough for threading;
2. If yes, inserts a PR Phi relying that the next iteration will remove it
   by performing jump threading;
3. The next iteration checks the block again and performs the threading.

This logic has a corner case: inserting the PR Phi increases block's size
by 1. If the block size at first check was max possible, one more Phi will
exceed this size, and we will neither perform threading nor remove the
created Phi node. As result, we will end up with worse IR than before.

This patch fixes this situation by excluding Phis from block size computation.
Excluding Phis from size computation for threading also makes sense by
itself because in case of threadign all those Phis will be removed.

Differential Revision: https://reviews.llvm.org/D81835
Reviewed By: asbirlea, nikic
2020-06-30 12:40:07 +07:00

168 lines
7.0 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -simplifycfg -simplifycfg-max-small-block-size=10 -S < %s | FileCheck %s
; RUN: opt -passes=simplify-cfg -simplifycfg-max-small-block-size=10 -S < %s | FileCheck %s
target datalayout = "e-p:64:64-p5:32:32-A5"
declare void @llvm.assume(i1)
define void @test_01(i1 %c, i64* align 1 %ptr) local_unnamed_addr #0 {
; CHECK-LABEL: @test_01(
; CHECK-NEXT: br i1 [[C:%.*]], label [[TRUE2_CRITEDGE:%.*]], label [[FALSE1:%.*]]
; CHECK: false1:
; CHECK-NEXT: store volatile i64 1, i64* [[PTR:%.*]], align 4
; CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i64* [[PTR]] to i64
; CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 7
; CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
; CHECK-NEXT: tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT: store volatile i64 0, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 3, i64* [[PTR]], align 8
; CHECK-NEXT: ret void
; CHECK: true2.critedge:
; CHECK-NEXT: [[PTRINT_C:%.*]] = ptrtoint i64* [[PTR]] to i64
; CHECK-NEXT: [[MASKEDPTR_C:%.*]] = and i64 [[PTRINT_C]], 7
; CHECK-NEXT: [[MASKCOND_C:%.*]] = icmp eq i64 [[MASKEDPTR_C]], 0
; CHECK-NEXT: tail call void @llvm.assume(i1 [[MASKCOND_C]])
; CHECK-NEXT: store volatile i64 0, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 2, i64* [[PTR]], align 8
; CHECK-NEXT: ret void
;
br i1 %c, label %true1, label %false1
true1: ; preds = %false1, %0
%ptrint = ptrtoint i64* %ptr to i64
%maskedptr = and i64 %ptrint, 7
%maskcond = icmp eq i64 %maskedptr, 0
tail call void @llvm.assume(i1 %maskcond)
store volatile i64 0, i64* %ptr, align 8
br i1 %c, label %true2, label %false2
false1: ; preds = %0
store volatile i64 1, i64* %ptr, align 4
br label %true1
true2: ; preds = %true1
store volatile i64 2, i64* %ptr, align 8
ret void
false2: ; preds = %true1
store volatile i64 3, i64* %ptr, align 8
ret void
}
; Corner case: the block has max possible size for which we still do PRE.
define void @test_02(i1 %c, i64* align 1 %ptr) local_unnamed_addr #0 {
; CHECK-LABEL: @test_02(
; CHECK-NEXT: br i1 [[C:%.*]], label [[TRUE2_CRITEDGE:%.*]], label [[FALSE1:%.*]]
; CHECK: false1:
; CHECK-NEXT: store volatile i64 1, i64* [[PTR:%.*]], align 4
; CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i64* [[PTR]] to i64
; CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 7
; CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
; CHECK-NEXT: tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT: store volatile i64 0, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 3, i64* [[PTR]], align 8
; CHECK-NEXT: ret void
; CHECK: true2.critedge:
; CHECK-NEXT: [[PTRINT_C:%.*]] = ptrtoint i64* [[PTR]] to i64
; CHECK-NEXT: [[MASKEDPTR_C:%.*]] = and i64 [[PTRINT_C]], 7
; CHECK-NEXT: [[MASKCOND_C:%.*]] = icmp eq i64 [[MASKEDPTR_C]], 0
; CHECK-NEXT: tail call void @llvm.assume(i1 [[MASKCOND_C]])
; CHECK-NEXT: store volatile i64 0, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 2, i64* [[PTR]], align 8
; CHECK-NEXT: ret void
;
br i1 %c, label %true1, label %false1
true1: ; preds = %false1, %0
%ptrint = ptrtoint i64* %ptr to i64
%maskedptr = and i64 %ptrint, 7
%maskcond = icmp eq i64 %maskedptr, 0
tail call void @llvm.assume(i1 %maskcond)
store volatile i64 0, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
br i1 %c, label %true2, label %false2
false1: ; preds = %0
store volatile i64 1, i64* %ptr, align 4
br label %true1
true2: ; preds = %true1
store volatile i64 2, i64* %ptr, align 8
ret void
false2: ; preds = %true1
store volatile i64 3, i64* %ptr, align 8
ret void
}
; This block is too huge for PRE.
define void @test_03(i1 %c, i64* align 1 %ptr) local_unnamed_addr #0 {
; CHECK-LABEL: @test_03(
; CHECK-NEXT: br i1 [[C:%.*]], label [[TRUE1:%.*]], label [[FALSE1:%.*]]
; CHECK: true1:
; CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i64* [[PTR:%.*]] to i64
; CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 7
; CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
; CHECK-NEXT: tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT: store volatile i64 0, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: store volatile i64 -1, i64* [[PTR]], align 8
; CHECK-NEXT: br i1 [[C]], label [[TRUE2:%.*]], label [[FALSE2:%.*]]
; CHECK: false1:
; CHECK-NEXT: store volatile i64 1, i64* [[PTR]], align 4
; CHECK-NEXT: br label [[TRUE1]]
; CHECK: true2:
; CHECK-NEXT: store volatile i64 2, i64* [[PTR]], align 8
; CHECK-NEXT: ret void
; CHECK: false2:
; CHECK-NEXT: store volatile i64 3, i64* [[PTR]], align 8
; CHECK-NEXT: ret void
;
br i1 %c, label %true1, label %false1
true1: ; preds = %false1, %0
%ptrint = ptrtoint i64* %ptr to i64
%maskedptr = and i64 %ptrint, 7
%maskcond = icmp eq i64 %maskedptr, 0
tail call void @llvm.assume(i1 %maskcond)
store volatile i64 0, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
store volatile i64 -1, i64* %ptr, align 8
br i1 %c, label %true2, label %false2
false1: ; preds = %0
store volatile i64 1, i64* %ptr, align 4
br label %true1
true2: ; preds = %true1
store volatile i64 2, i64* %ptr, align 8
ret void
false2: ; preds = %true1
store volatile i64 3, i64* %ptr, align 8
ret void
}