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
99 lines
4.0 KiB
LLVM
99 lines
4.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -S -passes=loop-unroll -unroll-allow-partial | FileCheck %s
|
|
|
|
; The phi which acts as input to func should not be undef. It should
|
|
; have its loop-carried value (the load in for.cond) replaced accordingly
|
|
; after unrolling the loop.
|
|
|
|
define i16 @full_unroll(ptr %A) {
|
|
; CHECK-LABEL: @full_unroll(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[FOR_COND:%.*]]
|
|
; CHECK: for.cond:
|
|
; CHECK-NEXT: br label [[FOR_COND_CLEANUP3:%.*]]
|
|
; CHECK: for.cond.cleanup:
|
|
; CHECK-NEXT: [[DOTLCSSA10_LCSSA:%.*]] = phi i16 [ [[TMP2_2:%.*]], [[FOR_COND_CLEANUP3_2:%.*]] ]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = call i16 @func(i16 [[DOTLCSSA10_LCSSA]])
|
|
; CHECK-NEXT: ret i16 0
|
|
; CHECK: for.cond.cleanup3:
|
|
; CHECK-NEXT: br label [[FOR_COND_CLEANUP3_1:%.*]]
|
|
; CHECK: for.cond.cleanup3.1:
|
|
; CHECK-NEXT: [[PTR_2:%.*]] = getelementptr inbounds i16, ptr [[A:%.*]], i64 2
|
|
; CHECK-NEXT: [[TMP2_2]] = load i16, ptr [[PTR_2]], align 2
|
|
; CHECK-NEXT: br label [[FOR_COND_CLEANUP3_2]]
|
|
; CHECK: for.cond.cleanup3.2:
|
|
; CHECK-NEXT: br i1 false, label [[FOR_COND_CLEANUP3_3:%.*]], label [[FOR_COND_CLEANUP:%.*]]
|
|
; CHECK: for.cond.cleanup3.3:
|
|
; CHECK-NEXT: unreachable
|
|
;
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.cond.cleanup3, %entry
|
|
%.lcssa10 = phi i16 [ 123, %entry ], [ %.lcssa, %for.cond.cleanup3 ]
|
|
%i.0 = phi i64 [ 0, %entry ], [ %inc9, %for.cond.cleanup3 ]
|
|
%ptr = getelementptr inbounds i16, ptr %A, i64 %i.0
|
|
%tmp2 = load i16, ptr %ptr
|
|
%cmp = icmp ult i64 %i.0, 3
|
|
br i1 %cmp, label %for.cond.cleanup3, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup: ; preds = %for.cond
|
|
%.lcssa10.lcssa = phi i16 [ %.lcssa10, %for.cond ]
|
|
%tmp3 = call i16 (i16) @func(i16 %.lcssa10.lcssa)
|
|
ret i16 0
|
|
|
|
for.cond.cleanup3: ; preds = %for.cond
|
|
%.lcssa = phi i16 [ %tmp2, %for.cond ]
|
|
%inc9 = add i64 %i.0, 1
|
|
br label %for.cond
|
|
}
|
|
|
|
define i16 @partial_unroll(ptr %A) {
|
|
; CHECK-LABEL: @partial_unroll(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[FOR_COND:%.*]]
|
|
; CHECK: for.cond:
|
|
; CHECK-NEXT: [[I_0:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC9_2:%.*]], [[FOR_COND_CLEANUP3_2:%.*]] ]
|
|
; CHECK-NEXT: br label [[FOR_COND_CLEANUP3:%.*]]
|
|
; CHECK: for.cond.cleanup:
|
|
; CHECK-NEXT: [[DOTLCSSA10_LCSSA:%.*]] = phi i16 [ [[TMP2_1:%.*]], [[FOR_COND_CLEANUP3_1:%.*]] ]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = call i16 @func(i16 [[DOTLCSSA10_LCSSA]])
|
|
; CHECK-NEXT: ret i16 0
|
|
; CHECK: for.cond.cleanup3:
|
|
; CHECK-NEXT: [[INC9:%.*]] = add nuw nsw i64 [[I_0]], 1
|
|
; CHECK-NEXT: [[PTR_1:%.*]] = getelementptr inbounds i16, ptr [[A:%.*]], i64 [[INC9]]
|
|
; CHECK-NEXT: [[TMP2_1]] = load i16, ptr [[PTR_1]], align 2
|
|
; CHECK-NEXT: br label [[FOR_COND_CLEANUP3_1]]
|
|
; CHECK: for.cond.cleanup3.1:
|
|
; CHECK-NEXT: [[INC9_1:%.*]] = add nuw nsw i64 [[I_0]], 2
|
|
; CHECK-NEXT: [[CMP_2:%.*]] = icmp ult i64 [[INC9_1]], 200
|
|
; CHECK-NEXT: br i1 [[CMP_2]], label [[FOR_COND_CLEANUP3_2]], label [[FOR_COND_CLEANUP:%.*]]
|
|
; CHECK: for.cond.cleanup3.2:
|
|
; CHECK-NEXT: [[INC9_2]] = add nuw nsw i64 [[I_0]], 3
|
|
; CHECK-NEXT: br label [[FOR_COND]]
|
|
;
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.cond.cleanup3, %entry
|
|
%.lcssa10 = phi i16 [ 123, %entry ], [ %.lcssa, %for.cond.cleanup3 ]
|
|
%i.0 = phi i64 [ 0, %entry ], [ %inc9, %for.cond.cleanup3 ]
|
|
%ptr = getelementptr inbounds i16, ptr %A, i64 %i.0
|
|
%tmp2 = load i16, ptr %ptr
|
|
%cmp = icmp ult i64 %i.0, 200
|
|
br i1 %cmp, label %for.cond.cleanup3, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup: ; preds = %for.cond
|
|
%.lcssa10.lcssa = phi i16 [ %.lcssa10, %for.cond ]
|
|
%tmp3 = call i16 (i16) @func(i16 %.lcssa10.lcssa)
|
|
ret i16 0
|
|
|
|
for.cond.cleanup3: ; preds = %for.cond
|
|
%.lcssa = phi i16 [ %tmp2, %for.cond ]
|
|
%inc9 = add i64 %i.0, 1
|
|
br label %for.cond
|
|
}
|
|
|
|
declare i16 @func(i16)
|
|
|