b9808e5660
Loop unrolling tends to produce chains of `%x1 = add %x0, 1; %x2 = add %x1, 1; ...` with one add per unrolled iteration. This patch simplifies these adds to `%xN = add %x0, N` directly during unrolling, rather than waiting for InstCombine to do so. The motivation for this is that having a single add (rather than an add chain) on the induction variable makes it a simple recurrence, which we specially recognize in a number of places. This allows InstCombine to directly perform folds with that knowledge, instead of first folding the add chains, and then doing other folds in another InstCombine iteration. Due to the reduced number of InstCombine iterations, this also results in a small compile-time improvement. Differential Revision: https://reviews.llvm.org/D153540
36 lines
1.3 KiB
LLVM
36 lines
1.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: opt < %s -S -passes=loop-unroll | FileCheck %s
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
define x86_mmx @f() #0 {
|
|
; CHECK-LABEL: define x86_mmx @f
|
|
; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[PHI:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[ADD_7:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[ADD_6:%.*]] = add i32 [[PHI]], 7
|
|
; CHECK-NEXT: [[ADD_7]] = add i32 [[PHI]], 8
|
|
; CHECK-NEXT: [[CMP_7:%.*]] = icmp eq i32 [[ADD_6]], 0
|
|
; CHECK-NEXT: br i1 [[CMP_7]], label [[EXIT:%.*]], label [[FOR_BODY]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: [[RET:%.*]] = phi x86_mmx [ undef, [[FOR_BODY]] ]
|
|
; CHECK-NEXT: ret x86_mmx [[RET]]
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%phi = phi i32 [ 1, %entry ], [ %add, %for.body ]
|
|
%add = add i32 %phi, 1
|
|
%cmp = icmp eq i32 %phi, 0
|
|
br i1 %cmp, label %exit, label %for.body
|
|
|
|
exit: ; preds = %for.body
|
|
%ret = phi x86_mmx [ undef, %for.body ]
|
|
ret x86_mmx %ret
|
|
}
|
|
|
|
attributes #0 = { "target-cpu"="x86-64" }
|