mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
39 lines
1.8 KiB
LLVM
39 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-tile -mattr=+avx512f -verify-machineinstrs | FileCheck %s
|
|
|
|
define void @test_amx(i8* %pointer, i8* %base, i64 %stride) {
|
|
; CHECK-LABEL: test_amx:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
|
|
; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movb $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movb $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movb $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, %ax
|
|
; CHECK-NEXT: tilezero %tmm0
|
|
; CHECK-NEXT: tileloadd (%rsi,%rdx), %tmm1
|
|
; CHECK-NEXT: tileloadd (%rsi,%rdx), %tmm2
|
|
; CHECK-NEXT: tdpbssd %tmm2, %tmm1, %tmm0
|
|
; CHECK-NEXT: tilestored %tmm0, (%rdi,%rdx)
|
|
; CHECK-NEXT: tilerelease
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
%c = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 8)
|
|
%a = call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 8, i8* %base, i64 %stride)
|
|
%b = call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 8, i8* %base, i64 %stride)
|
|
%d = call x86_amx @llvm.x86.tdpbssd.internal(i16 8, i16 8, i16 8, x86_amx %c, x86_amx %a, x86_amx %b)
|
|
call void @llvm.x86.tilestored64.internal(i16 8, i16 8, i8* %pointer, i64 %stride, x86_amx %d)
|
|
|
|
ret void
|
|
}
|
|
|
|
declare x86_amx @llvm.x86.tilezero.internal(i16, i16)
|
|
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64)
|
|
declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
|
|
declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)
|