eb7d16ea25
mflr is kind of expensive on Power version smaller than 10, so we should schedule the store for the mflr's def away from mflr. In epilogue, the expensive mtlr has no user for its def, so it doesn't matter that the load and the mtlr are back-to-back. Reviewed By: RolandF Differential Revision: https://reviews.llvm.org/D137423
87 lines
3.2 KiB
LLVM
87 lines
3.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mcpu=pwr9 -verify-machineinstrs -ppc-asm-full-reg-names \
|
|
; RUN: -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s --check-prefix=LE
|
|
; RUN: llc -mcpu=pwr9 -verify-machineinstrs -ppc-asm-full-reg-names \
|
|
; RUN: -mtriple=powerpc64-unknown-linux-gnu < %s | FileCheck %s --check-prefix=P9BE
|
|
; RUN: llc -mcpu=pwr8 -verify-machineinstrs -ppc-asm-full-reg-names \
|
|
; RUN: -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s --check-prefix=LE
|
|
; RUN: llc -mcpu=pwr8 -verify-machineinstrs -ppc-asm-full-reg-names \
|
|
; RUN: -mtriple=powerpc64-unknown-linux-gnu < %s | FileCheck %s --check-prefix=P8BE
|
|
|
|
declare ppc_fp128 @llvm.fmuladd.ppcf128(ppc_fp128, ppc_fp128, ppc_fp128) #2
|
|
|
|
define ppc_fp128 @test_ctr0() {
|
|
; P9BE-LABEL: test_ctr0:
|
|
; P9BE: # %bb.0: # %bb
|
|
; P9BE-NEXT: mflr r0
|
|
; P9BE-NEXT: stdu r1, -128(r1)
|
|
; P9BE-NEXT: std r0, 144(r1)
|
|
; P9BE-NEXT: .cfi_def_cfa_offset 128
|
|
; P9BE-NEXT: .cfi_offset lr, 16
|
|
; P9BE-NEXT: .cfi_offset r30, -16
|
|
; P9BE-NEXT: std r30, 112(r1) # 8-byte Folded Spill
|
|
; P9BE-NEXT: xxlxor f1, f1, f1
|
|
; P9BE-NEXT: li r30, 0
|
|
; P9BE-NEXT: xxlxor f2, f2, f2
|
|
; P9BE-NEXT: .p2align 5
|
|
; P9BE-NEXT: .LBB0_1: # %bb6
|
|
; P9BE-NEXT: #
|
|
; P9BE-NEXT: xxlxor f3, f3, f3
|
|
; P9BE-NEXT: xxlxor f4, f4, f4
|
|
; P9BE-NEXT: bl __gcc_qadd
|
|
; P9BE-NEXT: nop
|
|
; P9BE-NEXT: addi r30, r30, 4
|
|
; P9BE-NEXT: cmpldi r30, 0
|
|
; P9BE-NEXT: bne cr0, .LBB0_1
|
|
; P9BE-NEXT: # %bb.2: # %bb14
|
|
; P9BE-NEXT: ld r30, 112(r1) # 8-byte Folded Reload
|
|
; P9BE-NEXT: addi r1, r1, 128
|
|
; P9BE-NEXT: ld r0, 16(r1)
|
|
; P9BE-NEXT: mtlr r0
|
|
; P9BE-NEXT: blr
|
|
;
|
|
; P8BE-LABEL: test_ctr0:
|
|
; P8BE: # %bb.0: # %bb
|
|
; P8BE-NEXT: mflr r0
|
|
; P8BE-NEXT: stdu r1, -128(r1)
|
|
; P8BE-NEXT: std r0, 144(r1)
|
|
; P8BE-NEXT: .cfi_def_cfa_offset 128
|
|
; P8BE-NEXT: .cfi_offset lr, 16
|
|
; P8BE-NEXT: .cfi_offset r30, -16
|
|
; P8BE-NEXT: xxlxor f1, f1, f1
|
|
; P8BE-NEXT: std r30, 112(r1) # 8-byte Folded Spill
|
|
; P8BE-NEXT: li r30, 0
|
|
; P8BE-NEXT: xxlxor f2, f2, f2
|
|
; P8BE-NEXT: .p2align 5
|
|
; P8BE-NEXT: .LBB0_1: # %bb6
|
|
; P8BE-NEXT: #
|
|
; P8BE-NEXT: xxlxor f3, f3, f3
|
|
; P8BE-NEXT: xxlxor f4, f4, f4
|
|
; P8BE-NEXT: bl __gcc_qadd
|
|
; P8BE-NEXT: nop
|
|
; P8BE-NEXT: addi r30, r30, 4
|
|
; P8BE-NEXT: cmpldi r30, 0
|
|
; P8BE-NEXT: bne cr0, .LBB0_1
|
|
; P8BE-NEXT: # %bb.2: # %bb14
|
|
; P8BE-NEXT: ld r30, 112(r1) # 8-byte Folded Reload
|
|
; P8BE-NEXT: addi r1, r1, 128
|
|
; P8BE-NEXT: ld r0, 16(r1)
|
|
; P8BE-NEXT: mtlr r0
|
|
; P8BE-NEXT: blr
|
|
bb:
|
|
br label %bb6
|
|
|
|
bb6: ; preds = %bb6, %bb
|
|
%i = phi ppc_fp128 [ %i8, %bb6 ], [ 0xM00000000000000000000000000000000, %bb ]
|
|
%i7 = phi i64 [ %i9, %bb6 ], [ 0, %bb ]
|
|
%i8 = tail call ppc_fp128 @llvm.fmuladd.ppcf128(ppc_fp128 0xM00000000000000000000000000000000, ppc_fp128 0xM00000000000000000000000000000000, ppc_fp128 %i) #4
|
|
%i9 = add i64 %i7, -4
|
|
%i10 = icmp eq i64 %i9, 0
|
|
br i1 %i10, label %bb14, label %bb6
|
|
|
|
bb14: ; preds = %bb6
|
|
ret ppc_fp128 %i8
|
|
}
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; LE: {{.*}}
|