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
49 lines
1.6 KiB
LLVM
49 lines
1.6 KiB
LLVM
; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-target-num-scalar-regs=16 -force-target-max-scalar-interleave=8 -force-target-instruction-cost=1 -small-loop-cost=40 -dce -instcombine -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
@a = common global [2048 x i32] zeroinitializer, align 16
|
|
|
|
; This is the loop.
|
|
; for (i=0; i<n; i++){
|
|
; a[i] += i;
|
|
; }
|
|
;CHECK-LABEL: @inc(
|
|
;CHECK: load i32, i32*
|
|
;CHECK: load i32, i32*
|
|
;CHECK: load i32, i32*
|
|
;CHECK: load i32, i32*
|
|
;CHECK-NOT: load i32, i32*
|
|
;CHECK: add nsw i32
|
|
;CHECK: add nsw i32
|
|
;CHECK: add nsw i32
|
|
;CHECK: add nsw i32
|
|
;CHECK-NOT: add nsw i32
|
|
;CHECK: store i32
|
|
;CHECK: store i32
|
|
;CHECK: store i32
|
|
;CHECK: store i32
|
|
;CHECK-NOT: store i32
|
|
;CHECK: add nuw i64 %{{.*}}, 4
|
|
;CHECK: ret void
|
|
define void @inc(i32 %n) nounwind uwtable noinline ssp {
|
|
%1 = icmp sgt i32 %n, 0
|
|
br i1 %1, label %.lr.ph, label %._crit_edge
|
|
|
|
.lr.ph: ; preds = %0, %.lr.ph
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
|
|
%2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %indvars.iv
|
|
%3 = load i32, i32* %2, align 4
|
|
%4 = trunc i64 %indvars.iv to i32
|
|
%5 = add nsw i32 %3, %4
|
|
store i32 %5, i32* %2, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %n
|
|
br i1 %exitcond, label %._crit_edge, label %.lr.ph
|
|
|
|
._crit_edge: ; preds = %.lr.ph, %0
|
|
ret void
|
|
}
|
|
|