9540a7ae82
The dpbusd_const.ll test change is due to us losing the expanded add reduction pattern as one of the elements is known to be zero (removing one of the adds from the reduction pyramid). I don't think its of concern. Noticed while working on #107423
56 lines
1.9 KiB
LLVM
56 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc -mcpu=pwr8 < %s |\
|
|
; RUN: FileCheck %s --check-prefix=32BIT
|
|
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64 -mcpu=pwr8 < %s |\
|
|
; RUN: FileCheck %s --check-prefix=64BIT
|
|
|
|
define dso_local fastcc void @BuildVectorICE() unnamed_addr {
|
|
; 32BIT-LABEL: BuildVectorICE:
|
|
; 32BIT: # %bb.0: # %entry
|
|
; 32BIT-NEXT: stwu 1, -48(1)
|
|
; 32BIT-NEXT: .cfi_def_cfa_offset 48
|
|
; 32BIT-NEXT: lxvw4x 34, 0, 3
|
|
; 32BIT-NEXT: li 5, 0
|
|
; 32BIT-NEXT: addi 3, 1, 16
|
|
; 32BIT-NEXT: addi 4, 1, 32
|
|
; 32BIT-NEXT: xxspltw 35, 34, 1
|
|
; 32BIT-NEXT: .p2align 5
|
|
; 32BIT-NEXT: .LBB0_1: # %while.body
|
|
; 32BIT-NEXT: #
|
|
; 32BIT-NEXT: stw 5, 16(1)
|
|
; 32BIT-NEXT: lxvw4x 36, 0, 3
|
|
; 32BIT-NEXT: vadduwm 4, 2, 4
|
|
; 32BIT-NEXT: vadduwm 4, 4, 3
|
|
; 32BIT-NEXT: stxvw4x 36, 0, 4
|
|
; 32BIT-NEXT: lwz 5, 32(1)
|
|
; 32BIT-NEXT: b .LBB0_1
|
|
;
|
|
; 64BIT-LABEL: BuildVectorICE:
|
|
; 64BIT: # %bb.0: # %entry
|
|
; 64BIT-NEXT: lxvw4x 34, 0, 3
|
|
; 64BIT-NEXT: li 3, 0
|
|
; 64BIT-NEXT: xxspltw 35, 34, 1
|
|
; 64BIT-NEXT: .p2align 5
|
|
; 64BIT-NEXT: .LBB0_1: # %while.body
|
|
; 64BIT-NEXT: #
|
|
; 64BIT-NEXT: sldi 3, 3, 32
|
|
; 64BIT-NEXT: mtvsrd 36, 3
|
|
; 64BIT-NEXT: vadduwm 4, 2, 4
|
|
; 64BIT-NEXT: vadduwm 4, 4, 3
|
|
; 64BIT-NEXT: xxsldwi 0, 36, 36, 3
|
|
; 64BIT-NEXT: mffprwz 3, 0
|
|
; 64BIT-NEXT: b .LBB0_1
|
|
entry:
|
|
br label %while.body
|
|
while.body: ; preds = %while.body, %entry
|
|
%newelement = phi i32 [ 0, %entry ], [ %5, %while.body ]
|
|
%0 = insertelement <4 x i32> <i32 undef, i32 0, i32 0, i32 0>, i32 %newelement, i32 0
|
|
%1 = load <4 x i32>, ptr undef, align 1
|
|
%2 = add <4 x i32> %1, %0
|
|
%3 = shufflevector <4 x i32> %2, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
|
%4 = add <4 x i32> %2, %3
|
|
%5 = extractelement <4 x i32> %4, i32 0
|
|
br label %while.body
|
|
}
|