2fee8dd621
When enabling freeze-loop-unswitch-cond the inserted freeze instruction may block unswitching of parent loops if they get inserted in a block in the parent loop (as the llvm::Loop-based invariance check only checks whether an instruction is in a loop block or not). In the optimization pipeline, LICM is responsible to hoist out loop invariant instructions to enable further unswitching. Also run LICM for nested unswitching tests in preparation for flipping the default of freeze-loop-unswitch-cond. Reviewed By: nikic Differential Revision: https://reviews.llvm.org/D124251
161 lines
6.3 KiB
LLVM
161 lines
6.3 KiB
LLVM
;
|
|
; Here all the branches we unswitch are exiting from the inner loop.
|
|
; That means we should not be getting exponential behavior on inner-loop
|
|
; unswitch. In fact there should be just a single version of inner-loop,
|
|
; with possibly some outer loop copies.
|
|
;
|
|
; There should be just a single copy of each loop when strictest mutiplier
|
|
; candidates formula (unscaled candidates == 0) is enforced:
|
|
|
|
; RUN: opt < %s -enable-unswitch-cost-multiplier=true \
|
|
; RUN: -unswitch-num-initial-unscaled-candidates=0 -unswitch-siblings-toplevel-div=1 \
|
|
; RUN: -passes='loop(simple-loop-unswitch<nontrivial>),print<loops>' -disable-output 2>&1 | FileCheck %s --check-prefixes=LOOP1
|
|
;
|
|
; RUN: opt < %s -enable-unswitch-cost-multiplier=true \
|
|
; RUN: -unswitch-num-initial-unscaled-candidates=0 -unswitch-siblings-toplevel-div=16 \
|
|
; RUN: -passes='loop(simple-loop-unswitch<nontrivial>),print<loops>' -disable-output 2>&1 | FileCheck %s --check-prefixes=LOOP1
|
|
;
|
|
; RUN: opt < %s -enable-unswitch-cost-multiplier=true \
|
|
; RUN: -unswitch-num-initial-unscaled-candidates=0 -unswitch-siblings-toplevel-div=1 \
|
|
; RUN: -passes='loop-mssa(simple-loop-unswitch<nontrivial>),print<loops>' -disable-output 2>&1 | FileCheck %s --check-prefixes=LOOP1
|
|
;
|
|
; RUN: opt < %s -enable-unswitch-cost-multiplier=true \
|
|
; RUN: -unswitch-num-initial-unscaled-candidates=0 -unswitch-siblings-toplevel-div=16 \
|
|
; RUN: -passes='loop-mssa(simple-loop-unswitch<nontrivial>),print<loops>' -disable-output 2>&1 | FileCheck %s --check-prefixes=LOOP1
|
|
;
|
|
; When we relax the candidates part of a multiplier formula
|
|
; (unscaled candidates == 2) we start getting some unswitches in outer loops,
|
|
; which leads to siblings multiplier kicking in.
|
|
;
|
|
; The tests below also run licm, because it is needed to hoist out
|
|
; loop-invariant freeze instructions, which otherwise may block further
|
|
; unswitching.
|
|
;
|
|
; RUN: opt < %s -enable-unswitch-cost-multiplier=true \
|
|
; RUN: -unswitch-num-initial-unscaled-candidates=3 -unswitch-siblings-toplevel-div=1 \
|
|
; RUN: -passes='loop-mssa(licm,simple-loop-unswitch<nontrivial>),print<loops>' -disable-output 2>&1 | \
|
|
; RUN: sort -b -k 1 | FileCheck %s --check-prefixes=LOOP-UNSCALE3-DIV1
|
|
;
|
|
; NB: sort -b is essential here and below, otherwise blanks might lead to different
|
|
; order depending on locale.
|
|
;
|
|
; RUN: opt < %s -enable-unswitch-cost-multiplier=true \
|
|
; RUN: -unswitch-num-initial-unscaled-candidates=3 -unswitch-siblings-toplevel-div=2 \
|
|
; RUN: -passes='loop-mssa(licm,simple-loop-unswitch<nontrivial>),print<loops>' -disable-output 2>&1 | \
|
|
; RUN: sort -b -k 1 | FileCheck %s --check-prefixes=LOOP-UNSCALE3-DIV2
|
|
;
|
|
; With disabled cost-multiplier we get maximal possible amount of unswitches.
|
|
;
|
|
; RUN: opt < %s -enable-unswitch-cost-multiplier=false \
|
|
; RUN: -passes='loop-mssa(licm,simple-loop-unswitch<nontrivial>),print<loops>' -disable-output 2>&1 | \
|
|
; RUN: sort -b -k 1 | FileCheck %s --check-prefixes=LOOP-MAX
|
|
;
|
|
; Single loop nest, not unswitched
|
|
; LOOP1: Loop at depth 1 containing:
|
|
; LOOP1-NOT: Loop at depth 1 containing:
|
|
; LOOP1: Loop at depth 2 containing:
|
|
; LOOP1-NOT: Loop at depth 2 containing:
|
|
; LOOP1: Loop at depth 3 containing:
|
|
; LOOP1-NOT: Loop at depth 3 containing:
|
|
;
|
|
; Half unswitched loop nests, with unscaled3 and div1 it gets less depth1 loops unswitched
|
|
; since they have more cost.
|
|
; LOOP-UNSCALE3-DIV1-COUNT-4: Loop at depth 1 containing:
|
|
; LOOP-UNSCALE3-DIV1-NOT: Loop at depth 1 containing:
|
|
; LOOP-UNSCALE3-DIV1-COUNT-1: Loop at depth 2 containing:
|
|
; LOOP-UNSCALE3-DIV1-NOT: Loop at depth 2 containing:
|
|
; LOOP-UNSCALE3-DIV1-COUNT-1: Loop at depth 3 containing:
|
|
; LOOP-UNSCALE3-DIV1-NOT: Loop at depth 3 containing:
|
|
;
|
|
; Half unswitched loop nests, with unscaled3 and div2 it gets more depth1 loops unswitched
|
|
; as div2 kicks in.
|
|
; LOOP-UNSCALE3-DIV2-COUNT-6: Loop at depth 1 containing:
|
|
; LOOP-UNSCALE3-DIV2-NOT: Loop at depth 1 containing:
|
|
; LOOP-UNSCALE3-DIV2-COUNT-1: Loop at depth 2 containing:
|
|
; LOOP-UNSCALE3-DIV2-NOT: Loop at depth 2 containing:
|
|
; LOOP-UNSCALE3-DIV2-COUNT-1: Loop at depth 3 containing:
|
|
; LOOP-UNSCALE3-DIV2-NOT: Loop at depth 3 containing:
|
|
;
|
|
; Maximally unswitched (copy of the outer loop per each condition)
|
|
; LOOP-MAX-COUNT-6: Loop at depth 1 containing:
|
|
; LOOP-MAX-NOT: Loop at depth 1 containing:
|
|
; LOOP-MAX-COUNT-1: Loop at depth 2 containing:
|
|
; LOOP-MAX-NOT: Loop at depth 2 containing:
|
|
; LOOP-MAX-COUNT-1: Loop at depth 3 containing:
|
|
; LOOP-MAX-NOT: Loop at depth 3 containing:
|
|
|
|
declare void @bar()
|
|
|
|
define void @loop_nested3_conds5(i32* %addr, i1 %c1, i1 %c2, i1 %c3, i1 %c4, i1 %c5) {
|
|
entry:
|
|
%addr1 = getelementptr i32, i32* %addr, i64 0
|
|
%addr2 = getelementptr i32, i32* %addr, i64 1
|
|
%addr3 = getelementptr i32, i32* %addr, i64 2
|
|
br label %outer
|
|
outer:
|
|
%iv1 = phi i32 [0, %entry], [%iv1.next, %outer_latch]
|
|
%iv1.next = add i32 %iv1, 1
|
|
;; skip nontrivial unswitch
|
|
call void @bar()
|
|
br label %middle
|
|
middle:
|
|
%iv2 = phi i32 [0, %outer], [%iv2.next, %middle_latch]
|
|
%iv2.next = add i32 %iv2, 1
|
|
;; skip nontrivial unswitch
|
|
call void @bar()
|
|
br label %loop
|
|
loop:
|
|
%iv3 = phi i32 [0, %middle], [%iv3.next, %loop_latch]
|
|
%iv3.next = add i32 %iv3, 1
|
|
;; skip nontrivial unswitch
|
|
call void @bar()
|
|
br i1 %c1, label %loop_next1_left, label %outer_latch
|
|
loop_next1_left:
|
|
br label %loop_next1
|
|
loop_next1_right:
|
|
br label %loop_next1
|
|
|
|
loop_next1:
|
|
br i1 %c2, label %loop_next2_left, label %outer_latch
|
|
loop_next2_left:
|
|
br label %loop_next2
|
|
loop_next2_right:
|
|
br label %loop_next2
|
|
|
|
loop_next2:
|
|
br i1 %c3, label %loop_next3_left, label %outer_latch
|
|
loop_next3_left:
|
|
br label %loop_next3
|
|
loop_next3_right:
|
|
br label %loop_next3
|
|
|
|
loop_next3:
|
|
br i1 %c4, label %loop_next4_left, label %outer_latch
|
|
loop_next4_left:
|
|
br label %loop_next4
|
|
loop_next4_right:
|
|
br label %loop_next4
|
|
|
|
loop_next4:
|
|
br i1 %c5, label %loop_latch_left, label %outer_latch
|
|
loop_latch_left:
|
|
br label %loop_latch
|
|
loop_latch_right:
|
|
br label %loop_latch
|
|
|
|
loop_latch:
|
|
store volatile i32 0, i32* %addr1
|
|
%test_loop = icmp slt i32 %iv3, 50
|
|
br i1 %test_loop, label %loop, label %middle_latch
|
|
middle_latch:
|
|
store volatile i32 0, i32* %addr2
|
|
%test_middle = icmp slt i32 %iv2, 50
|
|
br i1 %test_middle, label %middle, label %outer_latch
|
|
outer_latch:
|
|
store volatile i32 0, i32* %addr3
|
|
%test_outer = icmp slt i32 %iv1, 50
|
|
br i1 %test_outer, label %outer, label %exit
|
|
exit:
|
|
ret void
|
|
}
|