cbdccb30c2
If a virtual register is not assigned preferred physical register, it means some COPY instructions will be changed to real register move instructions. In this case we can try to split the virtual register in colder blocks, if success, the original COPY instructions can be deleted, and the new COPY instructions in colder blocks will be generated as register move instructions. It results in fewer dynamic register move instructions executed. The new test case split-reg-with-hint.ll gives an example, the hot path contains 24 instructions without this patch, now it is only 4 instructions with this patch. Differential Revision: https://reviews.llvm.org/D156491
266 lines
9.0 KiB
LLVM
266 lines
9.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names \
|
|
; RUN: -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr9 < %s | FileCheck %s --check-prefix=CHECK-PWR9
|
|
; RUN: llc -verify-machineinstrs -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names \
|
|
; RUN: -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 < %s | FileCheck %s
|
|
|
|
; Check CSR split can work properly for tests below.
|
|
|
|
@a = dso_local local_unnamed_addr global i32 0, align 4
|
|
|
|
define dso_local signext i32 @test1(ptr %b) local_unnamed_addr {
|
|
; CHECK-PWR9-LABEL: test1:
|
|
; CHECK-PWR9: # %bb.0: # %entry
|
|
; CHECK-PWR9-NEXT: addis r4, r2, a@toc@ha
|
|
; CHECK-PWR9-NEXT: lwa r4, a@toc@l(r4)
|
|
; CHECK-PWR9-NEXT: cmpld r4, r3
|
|
; CHECK-PWR9-NEXT: # implicit-def: $r4
|
|
; CHECK-PWR9-NEXT: beq cr0, .LBB0_2
|
|
; CHECK-PWR9-NEXT: # %bb.1: # %if.end
|
|
; CHECK-PWR9-NEXT: extsw r3, r4
|
|
; CHECK-PWR9-NEXT: blr
|
|
; CHECK-PWR9-NEXT: .LBB0_2: # %if.then
|
|
; CHECK-PWR9-NEXT: mflr r0
|
|
; CHECK-PWR9-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-PWR9-NEXT: .cfi_offset lr, 16
|
|
; CHECK-PWR9-NEXT: .cfi_offset r30, -16
|
|
; CHECK-PWR9-NEXT: std r30, -16(r1) # 8-byte Folded Spill
|
|
; CHECK-PWR9-NEXT: stdu r1, -48(r1)
|
|
; CHECK-PWR9-NEXT: std r0, 64(r1)
|
|
; CHECK-PWR9-NEXT: mr r30, r3
|
|
; CHECK-PWR9-NEXT: bl callVoid
|
|
; CHECK-PWR9-NEXT: nop
|
|
; CHECK-PWR9-NEXT: mr r3, r30
|
|
; CHECK-PWR9-NEXT: bl callNonVoid
|
|
; CHECK-PWR9-NEXT: nop
|
|
; CHECK-PWR9-NEXT: mr r4, r3
|
|
; CHECK-PWR9-NEXT: addi r1, r1, 48
|
|
; CHECK-PWR9-NEXT: ld r0, 16(r1)
|
|
; CHECK-PWR9-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
|
|
; CHECK-PWR9-NEXT: mtlr r0
|
|
; CHECK-PWR9-NEXT: extsw r3, r4
|
|
; CHECK-PWR9-NEXT: blr
|
|
;
|
|
; CHECK-LABEL: test1:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: addis r4, r2, a@toc@ha
|
|
; CHECK-NEXT: lwa r4, a@toc@l(r4)
|
|
; CHECK-NEXT: cmpld r4, r3
|
|
; CHECK-NEXT: # implicit-def: $r4
|
|
; CHECK-NEXT: beq cr0, .LBB0_2
|
|
; CHECK-NEXT: # %bb.1: # %if.end
|
|
; CHECK-NEXT: extsw r3, r4
|
|
; CHECK-NEXT: blr
|
|
; CHECK-NEXT: .LBB0_2: # %if.then
|
|
; CHECK-NEXT: mflr r0
|
|
; CHECK-NEXT: stdu r1, -128(r1)
|
|
; CHECK-NEXT: std r0, 144(r1)
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 128
|
|
; CHECK-NEXT: .cfi_offset lr, 16
|
|
; CHECK-NEXT: .cfi_offset r30, -16
|
|
; CHECK-NEXT: std r30, 112(r1) # 8-byte Folded Spill
|
|
; CHECK-NEXT: mr r30, r3
|
|
; CHECK-NEXT: bl callVoid
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: mr r3, r30
|
|
; CHECK-NEXT: bl callNonVoid
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: ld r30, 112(r1) # 8-byte Folded Reload
|
|
; CHECK-NEXT: mr r4, r3
|
|
; CHECK-NEXT: addi r1, r1, 128
|
|
; CHECK-NEXT: ld r0, 16(r1)
|
|
; CHECK-NEXT: mtlr r0
|
|
; CHECK-NEXT: extsw r3, r4
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%0 = load i32, ptr @a, align 4, !tbaa !2
|
|
%conv = sext i32 %0 to i64
|
|
%1 = inttoptr i64 %conv to ptr
|
|
%cmp = icmp eq ptr %1, %b
|
|
br i1 %cmp, label %if.then, label %if.end
|
|
|
|
if.then: ; preds = %entry
|
|
%call = tail call signext i32 @callVoid()
|
|
%call2 = tail call signext i32 @callNonVoid(ptr %b)
|
|
br label %if.end
|
|
|
|
if.end: ; preds = %if.then, %entry
|
|
%retval.0 = phi i32 [ %call2, %if.then ], [ undef, %entry ]
|
|
ret i32 %retval.0
|
|
}
|
|
|
|
declare signext i32 @callVoid(...) local_unnamed_addr
|
|
|
|
declare signext i32 @callNonVoid(ptr) local_unnamed_addr
|
|
|
|
define dso_local signext i32 @test2(ptr %p1) local_unnamed_addr {
|
|
; CHECK-PWR9-LABEL: test2:
|
|
; CHECK-PWR9: # %bb.0: # %entry
|
|
; CHECK-PWR9-NEXT: mflr r0
|
|
; CHECK-PWR9-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-PWR9-NEXT: .cfi_offset lr, 16
|
|
; CHECK-PWR9-NEXT: .cfi_offset r30, -16
|
|
; CHECK-PWR9-NEXT: std r30, -16(r1) # 8-byte Folded Spill
|
|
; CHECK-PWR9-NEXT: stdu r1, -48(r1)
|
|
; CHECK-PWR9-NEXT: mr r30, r3
|
|
; CHECK-PWR9-NEXT: li r3, 0
|
|
; CHECK-PWR9-NEXT: std r0, 64(r1)
|
|
; CHECK-PWR9-NEXT: cmpldi r30, 0
|
|
; CHECK-PWR9-NEXT: beq cr0, .LBB1_3
|
|
; CHECK-PWR9-NEXT: # %bb.1: # %if.end
|
|
; CHECK-PWR9-NEXT: addis r4, r2, a@toc@ha
|
|
; CHECK-PWR9-NEXT: lwa r4, a@toc@l(r4)
|
|
; CHECK-PWR9-NEXT: cmpld r4, r30
|
|
; CHECK-PWR9-NEXT: bne cr0, .LBB1_3
|
|
; CHECK-PWR9-NEXT: # %bb.2: # %if.then2
|
|
; CHECK-PWR9-NEXT: bl callVoid
|
|
; CHECK-PWR9-NEXT: nop
|
|
; CHECK-PWR9-NEXT: mr r3, r30
|
|
; CHECK-PWR9-NEXT: bl callNonVoid
|
|
; CHECK-PWR9-NEXT: nop
|
|
; CHECK-PWR9-NEXT: .LBB1_3: # %return
|
|
; CHECK-PWR9-NEXT: addi r1, r1, 48
|
|
; CHECK-PWR9-NEXT: ld r0, 16(r1)
|
|
; CHECK-PWR9-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
|
|
; CHECK-PWR9-NEXT: mtlr r0
|
|
; CHECK-PWR9-NEXT: blr
|
|
;
|
|
; CHECK-LABEL: test2:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: mflr r0
|
|
; CHECK-NEXT: stdu r1, -128(r1)
|
|
; CHECK-NEXT: std r0, 144(r1)
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 128
|
|
; CHECK-NEXT: .cfi_offset lr, 16
|
|
; CHECK-NEXT: .cfi_offset r30, -16
|
|
; CHECK-NEXT: std r30, 112(r1) # 8-byte Folded Spill
|
|
; CHECK-NEXT: mr r30, r3
|
|
; CHECK-NEXT: li r3, 0
|
|
; CHECK-NEXT: cmpldi r30, 0
|
|
; CHECK-NEXT: beq cr0, .LBB1_3
|
|
; CHECK-NEXT: # %bb.1: # %if.end
|
|
; CHECK-NEXT: addis r4, r2, a@toc@ha
|
|
; CHECK-NEXT: lwa r4, a@toc@l(r4)
|
|
; CHECK-NEXT: cmpld r4, r30
|
|
; CHECK-NEXT: bne cr0, .LBB1_3
|
|
; CHECK-NEXT: # %bb.2: # %if.then2
|
|
; CHECK-NEXT: bl callVoid
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: mr r3, r30
|
|
; CHECK-NEXT: bl callNonVoid
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: .LBB1_3: # %return
|
|
; CHECK-NEXT: ld r30, 112(r1) # 8-byte Folded Reload
|
|
; CHECK-NEXT: addi r1, r1, 128
|
|
; CHECK-NEXT: ld r0, 16(r1)
|
|
; CHECK-NEXT: mtlr r0
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%tobool = icmp eq ptr %p1, null
|
|
br i1 %tobool, label %return, label %if.end
|
|
|
|
if.end: ; preds = %entry
|
|
%0 = load i32, ptr @a, align 4, !tbaa !2
|
|
%conv = sext i32 %0 to i64
|
|
%1 = inttoptr i64 %conv to ptr
|
|
%cmp = icmp eq ptr %1, %p1
|
|
br i1 %cmp, label %if.then2, label %return
|
|
|
|
if.then2: ; preds = %if.end
|
|
%call = tail call signext i32 @callVoid()
|
|
%call3 = tail call signext i32 @callNonVoid(ptr nonnull %p1)
|
|
br label %return
|
|
|
|
return: ; preds = %if.end, %entry, %if.then2
|
|
%retval.0 = phi i32 [ %call3, %if.then2 ], [ 0, %entry ], [ 0, %if.end ]
|
|
ret i32 %retval.0
|
|
}
|
|
|
|
|
|
define dso_local ptr @test3(ptr nocapture %p1, i8 zeroext %p2) local_unnamed_addr {
|
|
; CHECK-PWR9-LABEL: test3:
|
|
; CHECK-PWR9: # %bb.0: # %entry
|
|
; CHECK-PWR9-NEXT: mflr r0
|
|
; CHECK-PWR9-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-PWR9-NEXT: .cfi_offset lr, 16
|
|
; CHECK-PWR9-NEXT: .cfi_offset r29, -24
|
|
; CHECK-PWR9-NEXT: .cfi_offset r30, -16
|
|
; CHECK-PWR9-NEXT: std r29, -24(r1) # 8-byte Folded Spill
|
|
; CHECK-PWR9-NEXT: std r30, -16(r1) # 8-byte Folded Spill
|
|
; CHECK-PWR9-NEXT: stdu r1, -64(r1)
|
|
; CHECK-PWR9-NEXT: std r0, 80(r1)
|
|
; CHECK-PWR9-NEXT: ld r30, 0(r3)
|
|
; CHECK-PWR9-NEXT: cmpldi r30, 0
|
|
; CHECK-PWR9-NEXT: beq cr0, .LBB2_2
|
|
; CHECK-PWR9-NEXT: # %bb.1: # %land.rhs
|
|
; CHECK-PWR9-NEXT: mr r29, r3
|
|
; CHECK-PWR9-NEXT: mr r3, r30
|
|
; CHECK-PWR9-NEXT: bl bar
|
|
; CHECK-PWR9-NEXT: nop
|
|
; CHECK-PWR9-NEXT: std r3, 0(r29)
|
|
; CHECK-PWR9-NEXT: .LBB2_2: # %land.end
|
|
; CHECK-PWR9-NEXT: mr r3, r30
|
|
; CHECK-PWR9-NEXT: addi r1, r1, 64
|
|
; CHECK-PWR9-NEXT: ld r0, 16(r1)
|
|
; CHECK-PWR9-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
|
|
; CHECK-PWR9-NEXT: ld r29, -24(r1) # 8-byte Folded Reload
|
|
; CHECK-PWR9-NEXT: mtlr r0
|
|
; CHECK-PWR9-NEXT: blr
|
|
;
|
|
; CHECK-LABEL: test3:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: mflr r0
|
|
; CHECK-NEXT: stdu r1, -144(r1)
|
|
; CHECK-NEXT: std r0, 160(r1)
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 144
|
|
; CHECK-NEXT: .cfi_offset lr, 16
|
|
; CHECK-NEXT: .cfi_offset r29, -24
|
|
; CHECK-NEXT: .cfi_offset r30, -16
|
|
; CHECK-NEXT: std r30, 128(r1) # 8-byte Folded Spill
|
|
; CHECK-NEXT: ld r30, 0(r3)
|
|
; CHECK-NEXT: std r29, 120(r1) # 8-byte Folded Spill
|
|
; CHECK-NEXT: cmpldi r30, 0
|
|
; CHECK-NEXT: beq cr0, .LBB2_2
|
|
; CHECK-NEXT: # %bb.1: # %land.rhs
|
|
; CHECK-NEXT: mr r29, r3
|
|
; CHECK-NEXT: mr r3, r30
|
|
; CHECK-NEXT: bl bar
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: std r3, 0(r29)
|
|
; CHECK-NEXT: .LBB2_2: # %land.end
|
|
; CHECK-NEXT: mr r3, r30
|
|
; CHECK-NEXT: ld r30, 128(r1) # 8-byte Folded Reload
|
|
; CHECK-NEXT: ld r29, 120(r1) # 8-byte Folded Reload
|
|
; CHECK-NEXT: addi r1, r1, 144
|
|
; CHECK-NEXT: ld r0, 16(r1)
|
|
; CHECK-NEXT: mtlr r0
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%0 = load ptr, ptr %p1, align 8, !tbaa !6
|
|
%tobool = icmp eq ptr %0, null
|
|
br i1 %tobool, label %land.end, label %land.rhs
|
|
|
|
land.rhs: ; preds = %entry
|
|
%call = tail call ptr @bar(ptr nonnull %0, i8 zeroext %p2)
|
|
store ptr %call, ptr %p1, align 8, !tbaa !6
|
|
br label %land.end
|
|
|
|
land.end: ; preds = %entry, %land.rhs
|
|
ret ptr %0
|
|
}
|
|
|
|
declare ptr @bar(ptr, i8 zeroext) local_unnamed_addr
|
|
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!llvm.ident = !{!1}
|
|
|
|
!0 = !{i32 1, !"wchar_size", i32 4}
|
|
!1 = !{!"clang version 10.0.0 (trunk 367381) (llvm/trunk 367388)"}
|
|
!2 = !{!3, !3, i64 0}
|
|
!3 = !{!"int", !4, i64 0}
|
|
!4 = !{!"omnipotent char", !5, i64 0}
|
|
!5 = !{!"Simple C/C++ TBAA"}
|
|
!6 = !{!7, !7, i64 0}
|
|
!7 = !{!"any pointer", !4, i64 0}
|