Files
clang-p2996/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll
Max Kazantsev b07369651e [LV] Do not create SCEVs on broken IR in emitTransformedIndex. PR39160
At the point when we perform `emitTransformedIndex`, we have a broken IR (in
particular, we have Phis for which not every incoming value is properly set). On
such IR, it is illegal to create SCEV expressions, because their internal
simplification process may try to prove some predicates and break when it
stumbles across some broken IR.

The only purpose of using SCEV in this particular place is attempt to simplify
the generated code slightly. It seems that the result isn't worth it, because
some trivial cases (like addition of zero and multiplication by 1) can be
handled separately if needed, but more generally InstCombine is able to achieve
the goals we want to achieve by using SCEV.

This patch fixes a functional crash described in PR39160, and as side-effect it
also generates a bit smarter code in some simple cases. It also may cause some
optimality loss (i.e. we will now generate `mul` by power of `2` instead of
shift etc), but there is nothing what InstCombine could not handle later. In
case of dire need, we can support more trivial cases just in place.

Note that this patch only fixes one particular case of the general problem that
LV misuses SCEV, attempting to create SCEVs or prove predicates on invalid IR.
The general solution, however, seems complex enough.

Differential Revision: https://reviews.llvm.org/D52881
Reviewed By: fhahn, hsaito

llvm-svn: 343954
2018-10-08 05:46:29 +00:00

54 lines
2.6 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -S -mtriple=x86_64-- -o - %s | FileCheck %s
; Testcase that verify that we don't get a faulty bitcast that cast between
; different sizes.
%rec8 = type { i16 }
@a = global [1 x %rec8] zeroinitializer
@b = global [2 x i16*] zeroinitializer
define void @f1() {
; CHECK-LABEL: @f1(
; CHECK-NEXT: bb1:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX]] to i16
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i16> undef, i16 [[OFFSET_IDX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i16> [[BROADCAST_SPLATINSERT]], <2 x i16> undef, <2 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <2 x i16> [[BROADCAST_SPLAT]], <i16 0, i16 1>
; CHECK-NEXT: [[TMP0:%.*]] = add i16 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = sext i16 [[TMP0]] to i64
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr [2 x i16*], [2 x i16*]* @b, i16 0, i64 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i16*, i16** [[TMP2]], i32 0
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i16** [[TMP3]] to <2 x i16*>*
; CHECK-NEXT: store <2 x i16*> <i16* getelementptr inbounds (%rec8, %rec8* extractelement (<2 x %rec8*> getelementptr ([1 x %rec8], [1 x %rec8]* @a, <2 x i16> zeroinitializer, <2 x i64> zeroinitializer), i32 0), i32 0, i32 0), i16* getelementptr inbounds (%rec8, %rec8* extractelement (<2 x %rec8*> getelementptr ([1 x %rec8], [1 x %rec8]* @a, <2 x i16> zeroinitializer, <2 x i64> zeroinitializer), i32 1), i32 0, i32 0)>, <2 x i16*>* [[TMP4]], align 8
; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 2
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 2
; CHECK-NEXT: br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
; CHECK: middle.block:
bb1:
br label %bb2
bb2:
%c.1.0 = phi i16 [ 0, %bb1 ], [ %_tmp9, %bb2 ]
%_tmp1 = zext i16 0 to i64
%_tmp2 = getelementptr [1 x %rec8], [1 x %rec8]* @a, i16 0, i64 %_tmp1
%_tmp4 = bitcast %rec8* %_tmp2 to i16*
%_tmp6 = sext i16 %c.1.0 to i64
%_tmp7 = getelementptr [2 x i16*], [2 x i16*]* @b, i16 0, i64 %_tmp6
store i16* %_tmp4, i16** %_tmp7
%_tmp9 = add nsw i16 %c.1.0, 1
%_tmp11 = icmp slt i16 %_tmp9, 2
br i1 %_tmp11, label %bb2, label %bb3
bb3:
ret void
}