de2fed6152
The unrolling code was previously inserting new cloned blocks at the end of the function. The result of this with typical loop structures is that the new iterations are placed far from the initial iteration. With unrolling, the general assumption is that the a) the loop is reasonable hot, and b) the first Count-1 copies of the loop are rarely (if ever) loop exiting. As such, placing Count-1 copies out of line is a fairly poor code placement choice. We'd much rather fall through into the hot (non-exiting) path. For code with branch profiles, later layout would fix this, but this may have a positive impact on non-PGO compiled code. However, the real motivation for this change isn't performance. Its readability and human understanding. Having to jump around long distances in an IR file to trace an unrolled loop structure is error prone and tedious.
89 lines
4.5 KiB
LLVM
89 lines
4.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -loop-unroll -unroll-allow-partial %s | FileCheck %s
|
|
|
|
; This is a variant on full-unroll-non-latch-exit.ll for partial unrolling.
|
|
; This test is primarily interested in making sure that latches are not
|
|
; folded incorrectly, not that a transform occurs.
|
|
|
|
define i1 @test(i64* %a1, i64* %a2) {
|
|
; CHECK-LABEL: @test(
|
|
; CHECK-NEXT: start:
|
|
; CHECK-NEXT: br label [[LOOP:%.*]]
|
|
; CHECK: loop:
|
|
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, [[START:%.*]] ], [ [[IV_NEXT_4:%.*]], [[LATCH_4:%.*]] ]
|
|
; CHECK-NEXT: br label [[LATCH:%.*]]
|
|
; CHECK: latch:
|
|
; CHECK-NEXT: [[IV_NEXT:%.*]] = add nuw nsw i64 [[IV]], 1
|
|
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i64, i64* [[A1:%.*]], i64 [[IV]]
|
|
; CHECK-NEXT: [[GEP2:%.*]] = getelementptr inbounds i64, i64* [[A2:%.*]], i64 [[IV]]
|
|
; CHECK-NEXT: [[LOAD1:%.*]] = load i64, i64* [[GEP1]], align 8
|
|
; CHECK-NEXT: [[LOAD2:%.*]] = load i64, i64* [[GEP2]], align 8
|
|
; CHECK-NEXT: [[EXITCOND2:%.*]] = icmp eq i64 [[LOAD1]], [[LOAD2]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND2]], label [[LOOP_1:%.*]], label [[EXIT:%.*]]
|
|
; CHECK: loop.1:
|
|
; CHECK-NEXT: br label [[LATCH_1:%.*]]
|
|
; CHECK: latch.1:
|
|
; CHECK-NEXT: [[IV_NEXT_1:%.*]] = add nuw nsw i64 [[IV_NEXT]], 1
|
|
; CHECK-NEXT: [[GEP1_1:%.*]] = getelementptr inbounds i64, i64* [[A1]], i64 [[IV_NEXT]]
|
|
; CHECK-NEXT: [[GEP2_1:%.*]] = getelementptr inbounds i64, i64* [[A2]], i64 [[IV_NEXT]]
|
|
; CHECK-NEXT: [[LOAD1_1:%.*]] = load i64, i64* [[GEP1_1]], align 8
|
|
; CHECK-NEXT: [[LOAD2_1:%.*]] = load i64, i64* [[GEP2_1]], align 8
|
|
; CHECK-NEXT: [[EXITCOND2_1:%.*]] = icmp eq i64 [[LOAD1_1]], [[LOAD2_1]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND2_1]], label [[LOOP_2:%.*]], label [[EXIT]]
|
|
; CHECK: loop.2:
|
|
; CHECK-NEXT: br label [[LATCH_2:%.*]]
|
|
; CHECK: latch.2:
|
|
; CHECK-NEXT: [[IV_NEXT_2:%.*]] = add nuw nsw i64 [[IV_NEXT_1]], 1
|
|
; CHECK-NEXT: [[GEP1_2:%.*]] = getelementptr inbounds i64, i64* [[A1]], i64 [[IV_NEXT_1]]
|
|
; CHECK-NEXT: [[GEP2_2:%.*]] = getelementptr inbounds i64, i64* [[A2]], i64 [[IV_NEXT_1]]
|
|
; CHECK-NEXT: [[LOAD1_2:%.*]] = load i64, i64* [[GEP1_2]], align 8
|
|
; CHECK-NEXT: [[LOAD2_2:%.*]] = load i64, i64* [[GEP2_2]], align 8
|
|
; CHECK-NEXT: [[EXITCOND2_2:%.*]] = icmp eq i64 [[LOAD1_2]], [[LOAD2_2]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND2_2]], label [[LOOP_3:%.*]], label [[EXIT]]
|
|
; CHECK: loop.3:
|
|
; CHECK-NEXT: br label [[LATCH_3:%.*]]
|
|
; CHECK: latch.3:
|
|
; CHECK-NEXT: [[IV_NEXT_3:%.*]] = add nuw nsw i64 [[IV_NEXT_2]], 1
|
|
; CHECK-NEXT: [[GEP1_3:%.*]] = getelementptr inbounds i64, i64* [[A1]], i64 [[IV_NEXT_2]]
|
|
; CHECK-NEXT: [[GEP2_3:%.*]] = getelementptr inbounds i64, i64* [[A2]], i64 [[IV_NEXT_2]]
|
|
; CHECK-NEXT: [[LOAD1_3:%.*]] = load i64, i64* [[GEP1_3]], align 8
|
|
; CHECK-NEXT: [[LOAD2_3:%.*]] = load i64, i64* [[GEP2_3]], align 8
|
|
; CHECK-NEXT: [[EXITCOND2_3:%.*]] = icmp eq i64 [[LOAD1_3]], [[LOAD2_3]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND2_3]], label [[LOOP_4:%.*]], label [[EXIT]]
|
|
; CHECK: loop.4:
|
|
; CHECK-NEXT: [[EXITCOND_4:%.*]] = icmp eq i64 [[IV_NEXT_3]], 24
|
|
; CHECK-NEXT: br i1 [[EXITCOND_4]], label [[EXIT]], label [[LATCH_4]]
|
|
; CHECK: latch.4:
|
|
; CHECK-NEXT: [[IV_NEXT_4]] = add nuw nsw i64 [[IV_NEXT_3]], 1
|
|
; CHECK-NEXT: [[GEP1_4:%.*]] = getelementptr inbounds i64, i64* [[A1]], i64 [[IV_NEXT_3]]
|
|
; CHECK-NEXT: [[GEP2_4:%.*]] = getelementptr inbounds i64, i64* [[A2]], i64 [[IV_NEXT_3]]
|
|
; CHECK-NEXT: [[LOAD1_4:%.*]] = load i64, i64* [[GEP1_4]], align 8
|
|
; CHECK-NEXT: [[LOAD2_4:%.*]] = load i64, i64* [[GEP2_4]], align 8
|
|
; CHECK-NEXT: [[EXITCOND2_4:%.*]] = icmp eq i64 [[LOAD1_4]], [[LOAD2_4]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND2_4]], label [[LOOP]], label [[EXIT]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: [[EXIT_VAL:%.*]] = phi i1 [ false, [[LATCH]] ], [ false, [[LATCH_1]] ], [ false, [[LATCH_2]] ], [ false, [[LATCH_3]] ], [ true, [[LOOP_4]] ], [ false, [[LATCH_4]] ]
|
|
; CHECK-NEXT: ret i1 [[EXIT_VAL]]
|
|
;
|
|
start:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %start ], [ %iv.next, %latch ]
|
|
%exitcond = icmp eq i64 %iv, 24
|
|
br i1 %exitcond, label %exit, label %latch
|
|
|
|
latch:
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%gep1 = getelementptr inbounds i64, i64* %a1, i64 %iv
|
|
%gep2 = getelementptr inbounds i64, i64* %a2, i64 %iv
|
|
%load1 = load i64, i64* %gep1, align 8
|
|
%load2 = load i64, i64* %gep2, align 8
|
|
%exitcond2 = icmp eq i64 %load1, %load2
|
|
br i1 %exitcond2, label %loop, label %exit
|
|
|
|
exit:
|
|
%exit.val = phi i1 [ false, %latch ], [ true, %loop ]
|
|
ret i1 %exit.val
|
|
}
|