23c2f2e6b2
This patch marks the induction increment of the main induction variable of the vector loop as NUW when not folding the tail. If the tail is not folded, we know that End - Start >= Step (either statically or through the minimum iteration checks). We also know that both Start % Step == 0 and End % Step == 0. We exit the vector loop if %IV + %Step == %End. Hence we must exit the loop before %IV + %Step unsigned overflows and we can mark the induction increment as NUW. This should make SCEV return more precise bounds for the created vector loops, used by later optimizations, like late unrolling. At the moment quite a few tests still need to be updated, but before doing so I'd like to get initial feedback to make sure I am not missing anything. Note that this could probably be further improved by using information from the original IV. Attempt of modeling of the assumption in Alive2: https://alive2.llvm.org/ce/z/H_DL_g Part of a set of fixes required for PR50412. Reviewed By: mkazantsev Differential Revision: https://reviews.llvm.org/D103255
51 lines
2.1 KiB
LLVM
51 lines
2.1 KiB
LLVM
; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s 2>&1 | FileCheck %s
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
@a = common local_unnamed_addr global i32 0, align 4
|
|
@b = common local_unnamed_addr global i8 0, align 1
|
|
|
|
; Function Attrs: norecurse nounwind uwtable
|
|
define void @doit1() local_unnamed_addr{
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%main.iv = phi i32 [ 0, %entry ], [ %inc, %for.body ]
|
|
|
|
%i8.iv = phi i8 [ 0, %entry ], [ %i8.add, %for.body ]
|
|
%i32.iv = phi i32 [ 0, %entry ], [ %i32.add, %for.body ]
|
|
|
|
%trunc.to.be.converted.to.new.iv = trunc i32 %i32.iv to i8
|
|
%i8.add = add i8 %i8.iv, %trunc.to.be.converted.to.new.iv
|
|
|
|
%noop.conv.under.pse = and i32 %i32.iv, 255
|
|
%i32.add = add nuw nsw i32 %noop.conv.under.pse, 9
|
|
|
|
%inc = add i32 %main.iv, 1
|
|
%tobool = icmp eq i32 %inc, 16
|
|
br i1 %tobool, label %for.cond.for.end_crit_edge, label %for.body
|
|
|
|
; CHECK-LABEL: @doit1(
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[MAIN_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[MAIN_IV_NEXT:%.*]], [[VECTOR_BODY:%.*]] ]
|
|
; CHECK-NEXT: [[I8_IV:%.*]] = phi <4 x i8> [ zeroinitializer, [[VECTOR_PH]] ], [ [[I8_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[I32_IV:%.*]] = phi <4 x i32> [ <i32 0, i32 9, i32 18, i32 27>, [[VECTOR_PH]] ], [ [[I32_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[IV_FROM_TRUNC:%.*]] = phi <4 x i8> [ <i8 0, i8 9, i8 18, i8 27>, [[VECTOR_PH]] ], [ [[IV_FROM_TRUNC_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
|
|
; CHECK-NEXT: [[TMP7:%.*]] = add i32 [[MAIN_IV]], 0
|
|
|
|
; CHECK-NEXT: [[I8_IV_NEXT]] = add <4 x i8> [[I8_IV]], [[IV_FROM_TRUNC]]
|
|
|
|
; CHECK-NEXT: [[MAIN_IV_NEXT]] = add nuw i32 [[MAIN_IV]], 4
|
|
; CHECK-NEXT: [[I32_IV_NEXT]] = add <4 x i32> [[I32_IV]], <i32 36, i32 36, i32 36, i32 36>
|
|
; CHECK-NEXT: [[IV_FROM_TRUNC_NEXT]] = add <4 x i8> [[IV_FROM_TRUNC]], <i8 36, i8 36, i8 36, i8 36>
|
|
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[MAIN_IV_NEXT]], 16
|
|
; CHECK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
|
|
|
|
for.cond.for.end_crit_edge:
|
|
store i8 %i8.add, i8* @b, align 1
|
|
br label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|