maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[ARM] Update and add extra WLS testing. NFC

This commit is contained in:
David Green 2021-03-01 21:46:09 +00:00
parent 53d30381f5
commit 54e2876132
3 changed files with 300 additions and 223 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

164
llvm/test/CodeGen/Thumb2/LowOverheadLoops/branch-targets.ll
View File

@ -1,24 +1,14 @@
; RUN: llc -mtriple=thumbv8.1m.main -O0 -mattr=+lob -disable-arm-loloops=false -stop-before=arm-low-overhead-loops %s -o - | FileCheck %s --check-prefix=CHECK-MID
; RUN: llc -mtriple=thumbv8.1m.main -O0 -mattr=+lob -disable-arm-loloops=false -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK-END
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+lob -disable-arm-loloops=false -start-after=hardware-loops -stop-before=arm-low-overhead-loops %s -o - | FileCheck %s --check-prefix=CHECK-MID
; Test that the branch targets are correct after isel, even though the loop
; will sometimes be reverted anyway.
; CHECK-MID: name: check_loop_dec_brcond_combine
; CHECK-MID: bb.2.for.body:
; CHECK-MID: renamable $lr = t2LoopDec killed renamable $lr, 1
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-END: .LBB0_1:
; CHECK-END: b .LBB0_3
; CHECK-END: .LBB0_2:
; CHECK-END: subs.w lr, lr, #1
; CHECK-END: bne .LBB0_3
; CHECK-END: b .LBB0_4
; CHECK-END: .LBB0_3:
; CHECK-END: b .LBB0_2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -41,7 +31,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp ne i32 %count.next, 0
br i1 %cmp, label %for.header, label %for.cond.cleanup
@ -57,11 +47,12 @@ for.cond.cleanup:
}
; CHECK-MID: name: check_loop_dec_ugt_brcond_combine
; CHECK-MID: bb.2.for.body:
; CHECK-MID: renamable $lr = t2LoopDec killed renamable $lr, 1
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: tB %bb.2, 14
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_ugt_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -84,7 +75,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp ugt i32 %count.next, 0
br i1 %cmp, label %for.header, label %for.cond.cleanup
@ -100,11 +91,12 @@ for.cond.cleanup:
}
; CHECK-MID: name: check_loop_dec_ult_brcond_combine
; CHECK-MID: bb.2.for.body:
; CHECK-MID: renamable $lr = t2LoopDec killed renamable $lr, 1
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: tB %bb.2, 14
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_ult_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -127,7 +119,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp ult i32 %count.next, 1
br i1 %cmp, label %for.cond.cleanup, label %for.header
@ -143,11 +135,12 @@ for.cond.cleanup:
}
; CHECK-MID: name: check_loop_dec_ult_xor_brcond_combine
; CHECK-MIO: bb.2.for.body:
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: tB %bb.4, 14
; CHECk-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: tB %bb.2, 14
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_ult_xor_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -170,7 +163,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp ult i32 %count.next, 1
%negate = xor i1 %cmp, 1
br i1 %negate, label %for.header, label %for.cond.cleanup
@ -187,11 +180,12 @@ for.cond.cleanup:
}
; CHECK-MID: name: check_loop_dec_sgt_brcond_combine
; CHECK-MIO: bb.2.for.body:
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: tB %bb.4, 14
; CHECk-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: tB %bb.2, 14
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_sgt_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -214,7 +208,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp sgt i32 %count.next, 0
br i1 %cmp, label %for.header, label %for.cond.cleanup
@ -230,11 +224,12 @@ for.cond.cleanup:
}
; CHECK-MID: name: check_loop_dec_sge_brcond_combine
; CHECK-MIO: bb.2.for.body:
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: tB %bb.4, 14
; CHECk-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: tB %bb.2, 14
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_sge_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -257,7 +252,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp sge i32 %count.next, 1
br i1 %cmp, label %for.header, label %for.cond.cleanup
@ -273,11 +268,12 @@ for.cond.cleanup:
}
; CHECK-MID: name: check_loop_dec_sge_xor_brcond_combine
; CHECK-MIO: bb.2.for.body:
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: tB %bb.4, 14
; CHECk-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: tB %bb.2, 14
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_sge_xor_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -300,7 +296,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp sge i32 %count.next, 1
%negated = xor i1 %cmp, 1
br i1 %negated, label %for.cond.cleanup, label %for.header
@ -317,11 +313,12 @@ for.cond.cleanup:
}
; CHECK-MID: name: check_loop_dec_uge_brcond_combine
; CHECK-MIO: bb.2.for.body:
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: tB %bb.4, 14
; CHECk-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: tB %bb.2, 14
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_uge_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -344,7 +341,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp uge i32 %count.next, 1
br i1 %cmp, label %for.header, label %for.cond.cleanup
@ -360,11 +357,12 @@ for.cond.cleanup:
}
; CHECK-MID: name: check_loop_dec_uge_xor_brcond_combine
; CHECK-MIO: bb.2.for.body:
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.3
; CHECK-MID: tB %bb.4, 14
; CHECk-MID: bb.3.for.header:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.0.entry:
; CHECK-MID: renamable $lr = t2DoLoopStart killed renamable $r3
; CHECK-MID: bb.1.for.header:
; CHECK-MID: renamable $lr = t2LoopEndDec killed renamable $lr, %bb.1
; CHECK-MID: tB %bb.2, 14
; CHECK-MID: bb.2.for.cond.cleanup:
define void @check_loop_dec_uge_xor_brcond_combine(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
entry:
%start = call i32 @llvm.start.loop.iterations.i32(i32 %N)
@ -387,7 +385,7 @@ for.body:
%scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1
%scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1
%scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp uge i32 %count.next, 1
%negated = xor i1 %cmp, 1
br i1 %negated, label %for.cond.cleanup, label %for.header
@ -404,11 +402,11 @@ for.cond.cleanup:
}
; CHECK-MID: check_negated_xor_wls
; CHECK-MID: t2WhileLoopStart renamable $r2, %bb.3
; CHECK-MID: tB %bb.1
; CHECK-MID: t2WhileLoopStart $r2, %bb.3
; CHECK-MID: tB %bb.1
; CHECK-MID: bb.1.while.body.preheader:
; CHECK-MID: $lr = t2LoopDec killed renamable $lr, 1
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.2
; CHECK-MID: t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
; CHECk-MID: tB %bb.3
; CHECK-MID: bb.3.while.end:
define void @check_negated_xor_wls(i16* nocapture %a, i16* nocapture readonly %b, i32 %N) {
@ -428,7 +426,7 @@ while.body:
%ld.b = load i16, i16* %b.addr.05, align 2
%incdec.ptr1 = getelementptr inbounds i16, i16* %a.addr.06, i32 1
store i16 %ld.b, i16* %a.addr.06, align 2
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp ne i32 %count.next, 0
br i1 %cmp, label %while.body, label %while.end
@ -437,11 +435,11 @@ while.end:
}
; CHECK-MID: check_negated_cmp_wls
; CHECK-MID: t2WhileLoopStart renamable $r2, %bb.3
; CHECK-MID: tB %bb.1
; CHECK-MID: t2WhileLoopStart $r2, %bb.3
; CHECK-MID: tB %bb.1
; CHECK-MID: bb.1.while.body.preheader:
; CHECK-MID: $lr = t2LoopDec killed renamable $lr, 1
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.2
; CHECK-MID: t2LoopEnd renamable $lr, %bb.2
; CHECk-MID: tB %bb.3
; CHECK-MID: bb.3.while.end:
define void @check_negated_cmp_wls(i16* nocapture %a, i16* nocapture readonly %b, i32 %N) {
@ -461,7 +459,7 @@ while.body:
%ld.b = load i16, i16* %b.addr.05, align 2
%incdec.ptr1 = getelementptr inbounds i16, i16* %a.addr.06, i32 1
store i16 %ld.b, i16* %a.addr.06, align 2
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp.1 = icmp ne i32 %count.next, 0
br i1 %cmp.1, label %while.body, label %while.end
@ -470,15 +468,13 @@ while.end:
}
; CHECK-MID: check_negated_reordered_wls
; CHECK-MID: bb.1.while.body.preheader:
; CHECK-MID: tB %bb.2
; CHECK-MID: bb.2.while.body:
; CHECK-MID: t2LoopDec killed renamable $lr, 1
; CHECK-MID: t2LoopEnd killed renamable $lr, %bb.2
; CHECK-MID: tB %bb.4
; CHECK-MID: bb.3.while:
; CHECK-MID: t2WhileLoopStart {{.*}}, %bb.4
; CHECK-MID: bb.4.while.end
; CHECK-MID: t2WhileLoopStart killed $r2, %bb.2
; CHECK-MID: tB %bb.1
; CHECK-MID: bb.1.while.body:
; CHECK-MID: $lr = t2LoopDec killed renamable $lr, 1
; CHECK-MID: t2LoopEnd renamable $lr, %bb.1
; CHECk-MID: tB %bb.2
; CHECK-MID: bb.2.while.end:
define void @check_negated_reordered_wls(i16* nocapture %a, i16* nocapture readonly %b, i32 %N) {
entry:
br label %while
@ -494,7 +490,7 @@ while.body:
%ld.b = load i16, i16* %b.addr.05, align 2
%incdec.ptr1 = getelementptr inbounds i16, i16* %a.addr.06, i32 1
store i16 %ld.b, i16* %a.addr.06, align 2
%count.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
%count.next = call i32 @llvm.loop.decrement.reg.i32(i32 %count, i32 1)
%cmp = icmp ne i32 %count.next, 0
br i1 %cmp, label %while.body, label %while.end
@ -509,4 +505,4 @@ while.end:
declare i32 @llvm.start.loop.iterations.i32(i32)
declare i1 @llvm.test.set.loop.iterations.i32(i32)
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
declare i32 @llvm.loop.decrement.reg.i32(i32, i32)

220
llvm/test/CodeGen/Thumb2/LowOverheadLoops/while-loops.ll
View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve --verify-machineinstrs %s -o - | FileCheck %s
; Tail predicated so we use DLSTP
define void @simple(i32* nocapture readonly %x, i32* nocapture readnone %y, i32* nocapture %z, i32 %m, i32 %n) {
; CHECK-LABEL: simple:
; CHECK: @ %bb.0: @ %entry
@ -50,6 +51,7 @@ if.end: ; preds = %do.body, %entry
ret void
}
; Tail predicated so we use DLSTP
define void @nested(i32* nocapture readonly %x, i32* nocapture readnone %y, i32* nocapture %z, i32 %m, i32 %n) {
; CHECK-LABEL: nested:
; CHECK: @ %bb.0: @ %entry
@ -148,3 +150,221 @@ if.end: ; preds = %if.end.loopexit, %f
declare <4 x i1> @llvm.arm.mve.vctp32(i32)
declare i32 @llvm.arm.mve.addv.predicated.v4i32.v4i1(<4 x i32>, i32, <4 x i1>)
; Long test that was spilling lr between t2LoopDec and End
define dso_local i32 @b(i32* %c, i32 %d, i32 %e) "frame-pointer"="all" {
; CHECK-LABEL: b:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r4, r5, r6, r7, lr}
; CHECK-NEXT: push {r4, r5, r6, r7, lr}
; CHECK-NEXT: .setfp r7, sp, #12
; CHECK-NEXT: add r7, sp, #12
; CHECK-NEXT: .save {r8, r9, r10, r11}
; CHECK-NEXT: push.w {r8, r9, r10, r11}
; CHECK-NEXT: .pad #8
; CHECK-NEXT: sub sp, #8
; CHECK-NEXT: str r1, [sp, #4] @ 4-byte Spill
; CHECK-NEXT: cmp.w r1, #0
; CHECK-NEXT: beq .LBB2_3
; CHECK-NEXT: b .LBB2_1
; CHECK-NEXT: .LBB2_1: @ %while.body.preheader
; CHECK-NEXT: adds r1, r0, #4
; CHECK-NEXT: mov r3, r2
; CHECK-NEXT: mvn r2, #1
; CHECK-NEXT: @ implicit-def: $r9
; CHECK-NEXT: @ implicit-def: $r10
; CHECK-NEXT: @ implicit-def: $r6
; CHECK-NEXT: @ implicit-def: $r8
; CHECK-NEXT: str r3, [sp] @ 4-byte Spill
; CHECK-NEXT: .LBB2_2: @ %while.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mov lr, r1
; CHECK-NEXT: ldr r1, [r1, #-4]
; CHECK-NEXT: mul r1, r1, r9
; CHECK-NEXT: adds.w r12, r1, #-2147483648
; CHECK-NEXT: asr.w r5, r1, #31
; CHECK-NEXT: ldr.w r1, [r10]
; CHECK-NEXT: adc r5, r5, #0
; CHECK-NEXT: mul r11, r1, r0
; CHECK-NEXT: adds r0, #4
; CHECK-NEXT: add.w r3, r11, #-2147483648
; CHECK-NEXT: asrl r12, r5, r3
; CHECK-NEXT: smull r4, r3, r1, r12
; CHECK-NEXT: lsll r4, r3, #30
; CHECK-NEXT: asrs r5, r3, #31
; CHECK-NEXT: mov r4, r3
; CHECK-NEXT: lsll r4, r5, r1
; CHECK-NEXT: lsll r4, r5, #30
; CHECK-NEXT: ldrd r4, r11, [r2]
; CHECK-NEXT: asrs r3, r5, #31
; CHECK-NEXT: mov r12, r5
; CHECK-NEXT: ldr.w r5, [lr]
; CHECK-NEXT: muls r4, r6, r4
; CHECK-NEXT: mul r5, r5, r9
; CHECK-NEXT: add.w r9, r9, #4
; CHECK-NEXT: adds r4, #2
; CHECK-NEXT: lsll r12, r3, r4
; CHECK-NEXT: asr.w r4, r8, #31
; CHECK-NEXT: adds.w r3, r8, r5
; CHECK-NEXT: add.w r12, r12, #-2147483648
; CHECK-NEXT: adc.w r4, r4, r5, asr #31
; CHECK-NEXT: smull r5, r6, r11, r6
; CHECK-NEXT: adds.w r3, r3, #-2147483648
; CHECK-NEXT: adc r3, r4, #0
; CHECK-NEXT: asrs r4, r3, #31
; CHECK-NEXT: subs r5, r3, r5
; CHECK-NEXT: sbcs r4, r6
; CHECK-NEXT: adds.w r6, r5, #-2147483648
; CHECK-NEXT: adc r5, r4, #0
; CHECK-NEXT: asrl r6, r5, r12
; CHECK-NEXT: lsrl r6, r5, #2
; CHECK-NEXT: movs r5, #2
; CHECK-NEXT: str r6, [r5]
; CHECK-NEXT: ldr r5, [r2], #-4
; CHECK-NEXT: mls r1, r5, r1, r3
; CHECK-NEXT: adds.w r8, r1, #-2147483648
; CHECK-NEXT: asr.w r3, r1, #31
; CHECK-NEXT: adc r1, r3, #0
; CHECK-NEXT: ldr r3, [sp] @ 4-byte Reload
; CHECK-NEXT: lsrl r8, r1, #2
; CHECK-NEXT: rsb.w r1, r8, #0
; CHECK-NEXT: str r1, [r10, #-4]
; CHECK-NEXT: add.w r10, r10, #4
; CHECK-NEXT: str r1, [r3]
; CHECK-NEXT: mov r1, lr
; CHECK-NEXT: add.w r1, lr, #4
; CHECK-NEXT: ldr.w lr, [sp, #4] @ 4-byte Reload
; CHECK-NEXT: subs.w lr, lr, #1
; CHECK-NEXT: str.w lr, [sp, #4] @ 4-byte Spill
; CHECK-NEXT: bne .LBB2_2
; CHECK-NEXT: b .LBB2_3
; CHECK-NEXT: .LBB2_3: @ %while.end
; CHECK-NEXT: add sp, #8
; CHECK-NEXT: pop.w {r8, r9, r10, r11}
; CHECK-NEXT: pop {r4, r5, r6, r7, pc}
entry:
%0 = inttoptr i32 %e to i32*
%tobool.not70 = icmp eq i32 %d, 0
br i1 %tobool.not70, label %while.end, label %while.body
while.body: ; preds = %entry, %while.body
%p.077 = phi i32* [ %incdec.ptr22, %while.body ], [ inttoptr (i32 2 to i32*), %entry ]
%c.addr.076 = phi i32* [ %incdec.ptr1, %while.body ], [ %c, %entry ]
%n.075 = phi i32* [ %incdec.ptr43, %while.body ], [ undef, %entry ]
%m.074 = phi i32 [ %conv35, %while.body ], [ undef, %entry ]
%d.addr.073 = phi i32 [ %dec, %while.body ], [ %d, %entry ]
%h.072 = phi i32 [ %conv41, %while.body ], [ undef, %entry ]
%incdec.ptr43 = getelementptr inbounds i32, i32* %n.075, i32 1
%1 = ptrtoint i32* %n.075 to i32
%2 = load i32, i32* %incdec.ptr43, align 4
%3 = load i32, i32* %c.addr.076, align 4
%mul = mul nsw i32 %3, %1
%conv = sext i32 %mul to i64
%add = add nsw i64 %conv, 2147483648
%incdec.ptr1 = getelementptr inbounds i32, i32* %c.addr.076, i32 1
%4 = ptrtoint i32* %c.addr.076 to i32
%mul2 = mul nsw i32 %2, %4
%conv3 = sext i32 %mul2 to i64
%add4 = add nsw i64 %conv3, 2147483648
%shr = ashr i64 %add, %add4
%5 = shl nuw i64 %shr, 32
%conv6 = ashr exact i64 %5, 32
%conv7 = sext i32 %2 to i64
%conv11 = sext i32 %h.072 to i64
%6 = load i32, i32* %incdec.ptr1, align 4
%mul12 = mul nsw i32 %6, %1
%conv13 = sext i32 %mul12 to i64
%add14 = add nuw nsw i64 %conv11, 2147483648
%add15 = add nsw i64 %add14, %conv13
%shr16 = ashr i64 %add15, 32
%conv17 = trunc i64 %shr16 to i32
%mul8 = shl nsw i64 %conv7, 30
%7 = mul i64 %mul8, %conv6
%conv18 = ashr i64 %7, 32
%sh_prom = zext i32 %2 to i64
%shl = shl i64 %conv18, %sh_prom
%conv21 = sext i32 %conv17 to i64
%incdec.ptr22 = getelementptr inbounds i32, i32* %p.077, i32 -1
%8 = load i32, i32* %p.077, align 4
%conv23 = sext i32 %8 to i64
%conv24 = sext i32 %m.074 to i64
%mul25 = mul nsw i64 %conv23, %conv24
%sub = sub nsw i64 2147483648, %mul25
%add26 = add nsw i64 %sub, %conv21
%9 = shl i64 %shl, 30
%conv27 = ashr i64 %9, 32
%10 = load i32, i32* %incdec.ptr22, align 4
%mul28 = mul nsw i32 %10, %m.074
%add29 = add nsw i32 %mul28, 2
%sh_prom30 = zext i32 %add29 to i64
%shl31 = shl i64 %conv27, %sh_prom30
%add32 = add nsw i64 %shl31, 2147483648
%shr33 = ashr i64 %add26, %add32
%11 = lshr i64 %shr33, 2
%conv35 = trunc i64 %11 to i32
store i32 %conv35, i32* inttoptr (i32 2 to i32*), align 4
%12 = load i32, i32* %incdec.ptr22, align 4
%mul36 = mul nsw i32 %12, %2
%sub37 = sub nsw i32 %conv17, %mul36
%conv38 = sext i32 %sub37 to i64
%add39 = add nsw i64 %conv38, 2147483648
%13 = lshr i64 %add39, 2
%conv41 = trunc i64 %13 to i32
%sub42 = sub nsw i32 0, %conv41
store i32 %sub42, i32* %0, align 4
store i32 %sub42, i32* %n.075, align 4
%dec = add nsw i32 %d.addr.073, -1
%tobool.not = icmp eq i32 %dec, 0
br i1 %tobool.not, label %while.end, label %while.body
while.end: ; preds = %while.body, %entry
ret i32 undef
}
declare void @callee()
define void @callinpreheader(i32* noalias nocapture readonly %pAngle, i32* nocapture %pDst, i32 %size) {
; CHECK-LABEL: callinpreheader:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r4, r5, r6, lr}
; CHECK-NEXT: push {r4, r5, r6, lr}
; CHECK-NEXT: mov r5, r0
; CHECK-NEXT: mov r4, r1
; CHECK-NEXT: movs r0, #0
; CHECK-NEXT: wls lr, r2, .LBB3_3
; CHECK-NEXT: @ %bb.1: @ %for.body.ph
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: bl callee
; CHECK-NEXT: mov lr, r6
; CHECK-NEXT: movs r0, #0
; CHECK-NEXT: .LBB3_2: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r5], #4
; CHECK-NEXT: add r0, r1
; CHECK-NEXT: le lr, .LBB3_2
; CHECK-NEXT: .LBB3_3: @ %for.cond.cleanup
; CHECK-NEXT: str r0, [r4]
; CHECK-NEXT: pop {r4, r5, r6, pc}
entry:
%cmp7.not = icmp eq i32 %size, 0
br i1 %cmp7.not, label %for.cond.cleanup, label %for.body.ph
for.body.ph:
call void @callee()
br label %for.body
for.body:
%i.09 = phi i32 [ %inc, %for.body ], [ 0, %for.body.ph ]
%s.08 = phi i32 [ %add, %for.body ], [ 0, %for.body.ph ]
%arrayidx = getelementptr inbounds i32, i32* %pAngle, i32 %i.09
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %0, %s.08
%inc = add nuw nsw i32 %i.09, 1
%exitcond.not = icmp eq i32 %inc, %size
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
for.cond.cleanup:
%s.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
store i32 %s.0.lcssa, i32* %pDst, align 4
ret void
}

139
llvm/test/Transforms/HardwareLoops/scalar-while.ll
View File

@ -100,25 +100,6 @@ define void @while_lt(i32 %i, i32 %N, i32* nocapture %A) {
; CHECK-PHIGUARD: while.end:
; CHECK-PHIGUARD-NEXT: ret void
;
; CHECK-REGDEC-LABEL: @while_lt(
; CHECK-REGDEC-NEXT: entry:
; CHECK-REGDEC-NEXT: [[CMP4:%.*]] = icmp ult i32 [[I:%.*]], [[N:%.*]]
; CHECK-REGDEC-NEXT: br i1 [[CMP4]], label [[WHILE_BODY_PREHEADER:%.*]], label [[WHILE_END:%.*]]
; CHECK-REGDEC: while.body.preheader:
; CHECK-REGDEC-NEXT: [[TMP0:%.*]] = sub i32 [[N]], [[I]]
; CHECK-REGDEC-NEXT: [[TMP1:%.*]] = call i32 @llvm.start.loop.iterations.i32(i32 [[TMP0]])
; CHECK-REGDEC-NEXT: br label [[WHILE_BODY:%.*]]
; CHECK-REGDEC: while.body:
; CHECK-REGDEC-NEXT: [[I_ADDR_05:%.*]] = phi i32 [ [[INC:%.*]], [[WHILE_BODY]] ], [ [[I]], [[WHILE_BODY_PREHEADER]] ]
; CHECK-REGDEC-NEXT: [[TMP2:%.*]] = phi i32 [ [[TMP1]], [[WHILE_BODY_PREHEADER]] ], [ [[TMP3:%.*]], [[WHILE_BODY]] ]
; CHECK-REGDEC-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_ADDR_05]]
; CHECK-REGDEC-NEXT: store i32 [[I_ADDR_05]], i32* [[ARRAYIDX]], align 4
; CHECK-REGDEC-NEXT: [[INC]] = add nuw i32 [[I_ADDR_05]], 1
; CHECK-REGDEC-NEXT: [[TMP3]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[TMP2]], i32 1)
; CHECK-REGDEC-NEXT: [[TMP4:%.*]] = icmp ne i32 [[TMP3]], 0
; CHECK-REGDEC-NEXT: br i1 [[TMP4]], label [[WHILE_BODY]], label [[WHILE_END]]
; CHECK-REGDEC: while.end:
; CHECK-REGDEC-NEXT: ret void
entry:
%cmp4 = icmp ult i32 %i, %N
br i1 %cmp4, label %while.body, label %while.end
@ -230,25 +211,6 @@ define void @while_gt(i32 %i, i32 %N, i32* nocapture %A) {
; CHECK-PHIGUARD: while.end:
; CHECK-PHIGUARD-NEXT: ret void
;
; CHECK-REGDEC-LABEL: @while_gt(
; CHECK-REGDEC-NEXT: entry:
; CHECK-REGDEC-NEXT: [[CMP4:%.*]] = icmp sgt i32 [[I:%.*]], [[N:%.*]]
; CHECK-REGDEC-NEXT: br i1 [[CMP4]], label [[WHILE_BODY_PREHEADER:%.*]], label [[WHILE_END:%.*]]
; CHECK-REGDEC: while.body.preheader:
; CHECK-REGDEC-NEXT: [[TMP0:%.*]] = sub i32 [[I]], [[N]]
; CHECK-REGDEC-NEXT: [[TMP1:%.*]] = call i32 @llvm.start.loop.iterations.i32(i32 [[TMP0]])
; CHECK-REGDEC-NEXT: br label [[WHILE_BODY:%.*]]
; CHECK-REGDEC: while.body:
; CHECK-REGDEC-NEXT: [[I_ADDR_05:%.*]] = phi i32 [ [[DEC:%.*]], [[WHILE_BODY]] ], [ [[I]], [[WHILE_BODY_PREHEADER]] ]
; CHECK-REGDEC-NEXT: [[TMP2:%.*]] = phi i32 [ [[TMP1]], [[WHILE_BODY_PREHEADER]] ], [ [[TMP3:%.*]], [[WHILE_BODY]] ]
; CHECK-REGDEC-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_ADDR_05]]
; CHECK-REGDEC-NEXT: store i32 [[I_ADDR_05]], i32* [[ARRAYIDX]], align 4
; CHECK-REGDEC-NEXT: [[DEC]] = add nsw i32 [[I_ADDR_05]], -1
; CHECK-REGDEC-NEXT: [[TMP3]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[TMP2]], i32 1)
; CHECK-REGDEC-NEXT: [[TMP4:%.*]] = icmp ne i32 [[TMP3]], 0
; CHECK-REGDEC-NEXT: br i1 [[TMP4]], label [[WHILE_BODY]], label [[WHILE_END]]
; CHECK-REGDEC: while.end:
; CHECK-REGDEC-NEXT: ret void
entry:
%cmp4 = icmp sgt i32 %i, %N
br i1 %cmp4, label %while.body, label %while.end
@ -365,26 +327,6 @@ define void @while_gte(i32 %i, i32 %N, i32* nocapture %A) {
; CHECK-PHIGUARD: while.end:
; CHECK-PHIGUARD-NEXT: ret void
;
; CHECK-REGDEC-LABEL: @while_gte(
; CHECK-REGDEC-NEXT: entry:
; CHECK-REGDEC-NEXT: [[CMP4:%.*]] = icmp slt i32 [[I:%.*]], [[N:%.*]]
; CHECK-REGDEC-NEXT: br i1 [[CMP4]], label [[WHILE_END:%.*]], label [[WHILE_BODY_PREHEADER:%.*]]
; CHECK-REGDEC: while.body.preheader:
; CHECK-REGDEC-NEXT: [[TMP0:%.*]] = add i32 [[I]], 1
; CHECK-REGDEC-NEXT: [[TMP1:%.*]] = sub i32 [[TMP0]], [[N]]
; CHECK-REGDEC-NEXT: [[TMP2:%.*]] = call i32 @llvm.start.loop.iterations.i32(i32 [[TMP1]])
; CHECK-REGDEC-NEXT: br label [[WHILE_BODY:%.*]]
; CHECK-REGDEC: while.body:
; CHECK-REGDEC-NEXT: [[I_ADDR_05:%.*]] = phi i32 [ [[DEC:%.*]], [[WHILE_BODY]] ], [ [[I]], [[WHILE_BODY_PREHEADER]] ]
; CHECK-REGDEC-NEXT: [[TMP3:%.*]] = phi i32 [ [[TMP2]], [[WHILE_BODY_PREHEADER]] ], [ [[TMP4:%.*]], [[WHILE_BODY]] ]
; CHECK-REGDEC-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_ADDR_05]]
; CHECK-REGDEC-NEXT: store i32 [[I_ADDR_05]], i32* [[ARRAYIDX]], align 4
; CHECK-REGDEC-NEXT: [[DEC]] = add nsw i32 [[I_ADDR_05]], -1
; CHECK-REGDEC-NEXT: [[TMP4]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[TMP3]], i32 1)
; CHECK-REGDEC-NEXT: [[TMP5:%.*]] = icmp ne i32 [[TMP4]], 0
; CHECK-REGDEC-NEXT: br i1 [[TMP5]], label [[WHILE_BODY]], label [[WHILE_END]]
; CHECK-REGDEC: while.end:
; CHECK-REGDEC-NEXT: ret void
entry:
%cmp4 = icmp slt i32 %i, %N
br i1 %cmp4, label %while.end, label %while.body
@ -491,24 +433,6 @@ define void @while_ne(i32 %N, i32* nocapture %A) {
; CHECK-PHIGUARD: while.end:
; CHECK-PHIGUARD-NEXT: ret void
;
; CHECK-REGDEC-LABEL: @while_ne(
; CHECK-REGDEC-NEXT: entry:
; CHECK-REGDEC-NEXT: [[CMP:%.*]] = icmp ne i32 [[N:%.*]], 0
; CHECK-REGDEC-NEXT: br i1 [[CMP]], label [[WHILE_BODY_PREHEADER:%.*]], label [[WHILE_END:%.*]]
; CHECK-REGDEC: while.body.preheader:
; CHECK-REGDEC-NEXT: [[TMP0:%.*]] = call i32 @llvm.start.loop.iterations.i32(i32 [[N]])
; CHECK-REGDEC-NEXT: br label [[WHILE_BODY:%.*]]
; CHECK-REGDEC: while.body:
; CHECK-REGDEC-NEXT: [[I_ADDR_05:%.*]] = phi i32 [ [[INC:%.*]], [[WHILE_BODY]] ], [ 0, [[WHILE_BODY_PREHEADER]] ]
; CHECK-REGDEC-NEXT: [[TMP1:%.*]] = phi i32 [ [[TMP0]], [[WHILE_BODY_PREHEADER]] ], [ [[TMP2:%.*]], [[WHILE_BODY]] ]
; CHECK-REGDEC-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_ADDR_05]]
; CHECK-REGDEC-NEXT: store i32 [[I_ADDR_05]], i32* [[ARRAYIDX]], align 4
; CHECK-REGDEC-NEXT: [[INC]] = add nuw i32 [[I_ADDR_05]], 1
; CHECK-REGDEC-NEXT: [[TMP2]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[TMP1]], i32 1)
; CHECK-REGDEC-NEXT: [[TMP3:%.*]] = icmp ne i32 [[TMP2]], 0
; CHECK-REGDEC-NEXT: br i1 [[TMP3]], label [[WHILE_BODY]], label [[WHILE_END]]
; CHECK-REGDEC: while.end:
; CHECK-REGDEC-NEXT: ret void
entry:
%cmp = icmp ne i32 %N, 0
br i1 %cmp, label %while.body, label %while.end
@ -615,24 +539,6 @@ define void @while_eq(i32 %N, i32* nocapture %A) {
; CHECK-PHIGUARD: while.end:
; CHECK-PHIGUARD-NEXT: ret void
;
; CHECK-REGDEC-LABEL: @while_eq(
; CHECK-REGDEC-NEXT: entry:
; CHECK-REGDEC-NEXT: [[CMP:%.*]] = icmp eq i32 [[N:%.*]], 0
; CHECK-REGDEC-NEXT: br i1 [[CMP]], label [[WHILE_END:%.*]], label [[WHILE_BODY_PREHEADER:%.*]]
; CHECK-REGDEC: while.body.preheader:
; CHECK-REGDEC-NEXT: [[TMP0:%.*]] = call i32 @llvm.start.loop.iterations.i32(i32 [[N]])
; CHECK-REGDEC-NEXT: br label [[WHILE_BODY:%.*]]
; CHECK-REGDEC: while.body:
; CHECK-REGDEC-NEXT: [[I_ADDR_05:%.*]] = phi i32 [ [[INC:%.*]], [[WHILE_BODY]] ], [ 0, [[WHILE_BODY_PREHEADER]] ]
; CHECK-REGDEC-NEXT: [[TMP1:%.*]] = phi i32 [ [[TMP0]], [[WHILE_BODY_PREHEADER]] ], [ [[TMP2:%.*]], [[WHILE_BODY]] ]
; CHECK-REGDEC-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_ADDR_05]]
; CHECK-REGDEC-NEXT: store i32 [[I_ADDR_05]], i32* [[ARRAYIDX]], align 4
; CHECK-REGDEC-NEXT: [[INC]] = add nuw i32 [[I_ADDR_05]], 1
; CHECK-REGDEC-NEXT: [[TMP2]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[TMP1]], i32 1)
; CHECK-REGDEC-NEXT: [[TMP3:%.*]] = icmp ne i32 [[TMP2]], 0
; CHECK-REGDEC-NEXT: br i1 [[TMP3]], label [[WHILE_BODY]], label [[WHILE_END]]
; CHECK-REGDEC: while.end:
; CHECK-REGDEC-NEXT: ret void
entry:
%cmp = icmp eq i32 %N, 0
br i1 %cmp, label %while.end, label %while.body
@ -749,26 +655,6 @@ define void @while_preheader_eq(i32 %N, i32* nocapture %A) {
; CHECK-PHIGUARD: while.end:
; CHECK-PHIGUARD-NEXT: ret void
;
; CHECK-REGDEC-LABEL: @while_preheader_eq(
; CHECK-REGDEC-NEXT: entry:
; CHECK-REGDEC-NEXT: br label [[PREHEADER:%.*]]
; CHECK-REGDEC: preheader:
; CHECK-REGDEC-NEXT: [[CMP:%.*]] = icmp eq i32 [[N:%.*]], 0
; CHECK-REGDEC-NEXT: br i1 [[CMP]], label [[WHILE_END:%.*]], label [[WHILE_BODY_PREHEADER:%.*]]
; CHECK-REGDEC: while.body.preheader:
; CHECK-REGDEC-NEXT: [[TMP0:%.*]] = call i32 @llvm.start.loop.iterations.i32(i32 [[N]])
; CHECK-REGDEC-NEXT: br label [[WHILE_BODY:%.*]]
; CHECK-REGDEC: while.body:
; CHECK-REGDEC-NEXT: [[I_ADDR_05:%.*]] = phi i32 [ [[INC:%.*]], [[WHILE_BODY]] ], [ 0, [[WHILE_BODY_PREHEADER]] ]
; CHECK-REGDEC-NEXT: [[TMP1:%.*]] = phi i32 [ [[TMP0]], [[WHILE_BODY_PREHEADER]] ], [ [[TMP2:%.*]], [[WHILE_BODY]] ]
; CHECK-REGDEC-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_ADDR_05]]
; CHECK-REGDEC-NEXT: store i32 [[I_ADDR_05]], i32* [[ARRAYIDX]], align 4
; CHECK-REGDEC-NEXT: [[INC]] = add nuw i32 [[I_ADDR_05]], 1
; CHECK-REGDEC-NEXT: [[TMP2]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[TMP1]], i32 1)
; CHECK-REGDEC-NEXT: [[TMP3:%.*]] = icmp ne i32 [[TMP2]], 0
; CHECK-REGDEC-NEXT: br i1 [[TMP3]], label [[WHILE_BODY]], label [[WHILE_END]]
; CHECK-REGDEC: while.end:
; CHECK-REGDEC-NEXT: ret void
entry:
br label %preheader
@ -916,31 +802,6 @@ define void @nested(i32* nocapture %A, i32 %N) {
; CHECK-PHIGUARD: while.end7:
; CHECK-PHIGUARD-NEXT: ret void
;
; CHECK-REGDEC-LABEL: @nested(
; CHECK-REGDEC-NEXT: entry:
; CHECK-REGDEC-NEXT: [[CMP20:%.*]] = icmp eq i32 [[N:%.*]], 0
; CHECK-REGDEC-NEXT: br i1 [[CMP20]], label [[WHILE_END7:%.*]], label [[WHILE_COND1_PREHEADER_US:%.*]]
; CHECK-REGDEC: while.cond1.preheader.us:
; CHECK-REGDEC-NEXT: [[I_021_US:%.*]] = phi i32 [ [[INC6_US:%.*]], [[WHILE_COND1_WHILE_END_CRIT_EDGE_US:%.*]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-REGDEC-NEXT: [[MUL_US:%.*]] = mul i32 [[I_021_US]], [[N]]
; CHECK-REGDEC-NEXT: [[TMP0:%.*]] = call i32 @llvm.start.loop.iterations.i32(i32 [[N]])
; CHECK-REGDEC-NEXT: br label [[WHILE_BODY3_US:%.*]]
; CHECK-REGDEC: while.body3.us:
; CHECK-REGDEC-NEXT: [[J_019_US:%.*]] = phi i32 [ 0, [[WHILE_COND1_PREHEADER_US]] ], [ [[INC_US:%.*]], [[WHILE_BODY3_US]] ]
; CHECK-REGDEC-NEXT: [[TMP1:%.*]] = phi i32 [ [[TMP0]], [[WHILE_COND1_PREHEADER_US]] ], [ [[TMP2:%.*]], [[WHILE_BODY3_US]] ]
; CHECK-REGDEC-NEXT: [[ADD_US:%.*]] = add i32 [[J_019_US]], [[MUL_US]]
; CHECK-REGDEC-NEXT: [[ARRAYIDX_US:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[ADD_US]]
; CHECK-REGDEC-NEXT: store i32 [[ADD_US]], i32* [[ARRAYIDX_US]], align 4
; CHECK-REGDEC-NEXT: [[INC_US]] = add nuw i32 [[J_019_US]], 1
; CHECK-REGDEC-NEXT: [[TMP2]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[TMP1]], i32 1)
; CHECK-REGDEC-NEXT: [[TMP3:%.*]] = icmp ne i32 [[TMP2]], 0
; CHECK-REGDEC-NEXT: br i1 [[TMP3]], label [[WHILE_BODY3_US]], label [[WHILE_COND1_WHILE_END_CRIT_EDGE_US]]
; CHECK-REGDEC: while.cond1.while.end_crit_edge.us:
; CHECK-REGDEC-NEXT: [[INC6_US]] = add nuw i32 [[I_021_US]], 1
; CHECK-REGDEC-NEXT: [[EXITCOND23:%.*]] = icmp eq i32 [[INC6_US]], [[N]]
; CHECK-REGDEC-NEXT: br i1 [[EXITCOND23]], label [[WHILE_END7]], label [[WHILE_COND1_PREHEADER_US]]
; CHECK-REGDEC: while.end7:
; CHECK-REGDEC-NEXT: ret void
entry:
%cmp20 = icmp eq i32 %N, 0
br i1 %cmp20, label %while.end7, label %while.cond1.preheader.us