c4a60c9d34
This is an attempt to reland D42600 and enabling this optimisation by default. This also resolves the issue pointed out in the context of PGO build. Differential Revision: https://reviews.llvm.org/D42600
207 lines
10 KiB
LLVM
207 lines
10 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64le-unknown-unknown -mcpu=pwr9 | FileCheck %s --check-prefixes=POWERPC64
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc-ibm-aix-xcoff -mcpu=pwr9 -mattr=-altivec | FileCheck %s --check-prefixes=POWERPC32-AIX
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64-ibm-aix-xcoff -mcpu=pwr9 -mattr=-altivec | FileCheck %s --check-prefixes=POWERPC64-AIX
|
|
|
|
define signext i32 @shrinkwrapme(i32 signext %a, i32 signext %lim) {
|
|
; POWERPC64-LABEL: shrinkwrapme:
|
|
; POWERPC64: # %bb.0: # %entry
|
|
; POWERPC64-NEXT: cmpwi 4, 0
|
|
; POWERPC64-NEXT: ble 0, .LBB0_4
|
|
; POWERPC64-NEXT: # %bb.1: # %for.body.preheader
|
|
; POWERPC64-NEXT: addi 4, 4, -1
|
|
; POWERPC64-NEXT: std 14, -144(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 15, -136(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 16, -128(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 17, -120(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 18, -112(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 19, -104(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 20, -96(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 21, -88(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 22, -80(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 23, -72(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 24, -64(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 25, -56(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 26, -48(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 27, -40(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 28, -32(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: clrldi 4, 4, 32
|
|
; POWERPC64-NEXT: addi 4, 4, 1
|
|
; POWERPC64-NEXT: std 29, -24(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 30, -16(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: std 31, -8(1) # 8-byte Folded Spill
|
|
; POWERPC64-NEXT: mtctr 4
|
|
; POWERPC64-NEXT: li 4, 0
|
|
; POWERPC64-NEXT: .p2align 4
|
|
; POWERPC64-NEXT: .LBB0_2: # %for.body
|
|
; POWERPC64-NEXT: #
|
|
; POWERPC64-NEXT: #APP
|
|
; POWERPC64-NEXT: add 4, 3, 4
|
|
; POWERPC64-NEXT: #NO_APP
|
|
; POWERPC64-NEXT: bdnz .LBB0_2
|
|
; POWERPC64-NEXT: # %bb.3:
|
|
; POWERPC64-NEXT: ld 31, -8(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 30, -16(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 29, -24(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 28, -32(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: extsw 3, 4
|
|
; POWERPC64-NEXT: ld 27, -40(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 26, -48(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 25, -56(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 24, -64(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 23, -72(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 22, -80(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 21, -88(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 20, -96(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 19, -104(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 18, -112(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 17, -120(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 16, -128(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 15, -136(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: ld 14, -144(1) # 8-byte Folded Reload
|
|
; POWERPC64-NEXT: blr
|
|
; POWERPC64-NEXT: .LBB0_4:
|
|
; POWERPC64-NEXT: li 4, 0
|
|
; POWERPC64-NEXT: extsw 3, 4
|
|
; POWERPC64-NEXT: blr
|
|
;
|
|
; POWERPC32-AIX-LABEL: shrinkwrapme:
|
|
; POWERPC32-AIX: # %bb.0: # %entry
|
|
; POWERPC32-AIX-NEXT: cmpwi 4, 0
|
|
; POWERPC32-AIX-NEXT: ble 0, L..BB0_4
|
|
; POWERPC32-AIX-NEXT: # %bb.1: # %for.body.preheader
|
|
; POWERPC32-AIX-NEXT: stw 14, -72(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 15, -68(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 16, -64(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 17, -60(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 18, -56(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 19, -52(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 20, -48(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 21, -44(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 22, -40(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 23, -36(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 24, -32(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 25, -28(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 26, -24(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 27, -20(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 28, -16(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 29, -12(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 30, -8(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: stw 31, -4(1) # 4-byte Folded Spill
|
|
; POWERPC32-AIX-NEXT: mtctr 4
|
|
; POWERPC32-AIX-NEXT: li 4, 0
|
|
; POWERPC32-AIX-NEXT: .align 4
|
|
; POWERPC32-AIX-NEXT: L..BB0_2: # %for.body
|
|
; POWERPC32-AIX-NEXT: #
|
|
; POWERPC32-AIX-NEXT: #APP
|
|
; POWERPC32-AIX-NEXT: add 4, 3, 4
|
|
; POWERPC32-AIX-NEXT: #NO_APP
|
|
; POWERPC32-AIX-NEXT: bdnz L..BB0_2
|
|
; POWERPC32-AIX-NEXT: # %bb.3:
|
|
; POWERPC32-AIX-NEXT: lwz 31, -4(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 30, -8(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 29, -12(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 28, -16(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: mr 3, 4
|
|
; POWERPC32-AIX-NEXT: lwz 27, -20(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 26, -24(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 25, -28(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 24, -32(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 23, -36(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 22, -40(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 21, -44(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 20, -48(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 19, -52(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 18, -56(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 17, -60(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 16, -64(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 15, -68(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: lwz 14, -72(1) # 4-byte Folded Reload
|
|
; POWERPC32-AIX-NEXT: blr
|
|
; POWERPC32-AIX-NEXT: L..BB0_4:
|
|
; POWERPC32-AIX-NEXT: li 3, 0
|
|
; POWERPC32-AIX-NEXT: blr
|
|
;
|
|
; POWERPC64-AIX-LABEL: shrinkwrapme:
|
|
; POWERPC64-AIX: # %bb.0: # %entry
|
|
; POWERPC64-AIX-NEXT: cmpwi 4, 1
|
|
; POWERPC64-AIX-NEXT: blt 0, L..BB0_4
|
|
; POWERPC64-AIX-NEXT: # %bb.1: # %for.body.preheader
|
|
; POWERPC64-AIX-NEXT: addi 4, 4, -1
|
|
; POWERPC64-AIX-NEXT: std 14, -144(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 15, -136(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 16, -128(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 17, -120(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 18, -112(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 19, -104(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 20, -96(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 21, -88(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 22, -80(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 23, -72(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 24, -64(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 25, -56(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 26, -48(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 27, -40(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 28, -32(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: clrldi 4, 4, 32
|
|
; POWERPC64-AIX-NEXT: addi 4, 4, 1
|
|
; POWERPC64-AIX-NEXT: std 29, -24(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 30, -16(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: std 31, -8(1) # 8-byte Folded Spill
|
|
; POWERPC64-AIX-NEXT: mtctr 4
|
|
; POWERPC64-AIX-NEXT: li 4, 0
|
|
; POWERPC64-AIX-NEXT: .align 4
|
|
; POWERPC64-AIX-NEXT: L..BB0_2: # %for.body
|
|
; POWERPC64-AIX-NEXT: #
|
|
; POWERPC64-AIX-NEXT: #APP
|
|
; POWERPC64-AIX-NEXT: add 4, 3, 4
|
|
; POWERPC64-AIX-NEXT: #NO_APP
|
|
; POWERPC64-AIX-NEXT: bdnz L..BB0_2
|
|
; POWERPC64-AIX-NEXT: # %bb.3:
|
|
; POWERPC64-AIX-NEXT: ld 31, -8(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 30, -16(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 29, -24(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 28, -32(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: extsw 3, 4
|
|
; POWERPC64-AIX-NEXT: ld 27, -40(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 26, -48(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 25, -56(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 24, -64(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 23, -72(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 22, -80(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 21, -88(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 20, -96(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 19, -104(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 18, -112(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 17, -120(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 16, -128(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 15, -136(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: ld 14, -144(1) # 8-byte Folded Reload
|
|
; POWERPC64-AIX-NEXT: blr
|
|
; POWERPC64-AIX-NEXT: L..BB0_4:
|
|
; POWERPC64-AIX-NEXT: li 4, 0
|
|
; POWERPC64-AIX-NEXT: extsw 3, 4
|
|
; POWERPC64-AIX-NEXT: blr
|
|
entry:
|
|
%cmp5 = icmp sgt i32 %lim, 0
|
|
br i1 %cmp5, label %for.body.preheader, label %for.cond.cleanup
|
|
|
|
for.body.preheader: ; preds = %entry
|
|
br label %for.body
|
|
|
|
for.cond.cleanup.loopexit: ; preds = %for.body
|
|
br label %for.cond.cleanup
|
|
|
|
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
|
|
%Ret.0.lcssa = phi i32 [ 0, %entry ], [ %0, %for.cond.cleanup.loopexit ]
|
|
ret i32 %Ret.0.lcssa
|
|
|
|
for.body: ; preds = %for.body.preheader, %for.body
|
|
%i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
|
|
%Ret.06 = phi i32 [ %0, %for.body ], [ 0, %for.body.preheader ]
|
|
%0 = tail call i32 asm "add $0, $1, $2", "=r,r,r,~{r14},~{r15},~{r16},~{r17},~{r18},~{r19},~{r20},~{r21},~{r22},~{r23},~{r24},~{r25},~{r26},~{r27},~{r28},~{r29},~{r30},~{r31}"(i32 %a, i32 %Ret.06)
|
|
%inc = add nuw nsw i32 %i.07, 1
|
|
%exitcond = icmp eq i32 %inc, %lim
|
|
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
|
|
}
|