test/Transforms/InstCombine/X86/x86-amx-load-store.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=instcombine -S < %s | FileCheck %s

; Prohibit poiter cast for amx.
define dso_local void @test_amx_load_store(ptr %src, ptr %dst) {
; CHECK-LABEL: @test_amx_load_store(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VEC:%.*]] = load <256 x i32>, ptr [[SRC:%.*]], align 64
; CHECK-NEXT:    [[BC:%.*]] = bitcast <256 x i32> [[VEC]] to x86_amx
; CHECK-NEXT:    tail call void @llvm.x86.tilestored64.internal(i16 16, i16 16, ptr [[DST:%.*]], i64 64, x86_amx [[BC]])
; CHECK-NEXT:    ret void
;
entry:
  %vec = load <256 x i32>, ptr %src, align 64
  %bc = bitcast <256 x i32> %vec to x86_amx
  tail call void @llvm.x86.tilestored64.internal(i16 16, i16 16, ptr %dst, i64 64, x86_amx %bc)
  ret void
}

; Prohibit poiter cast for amx.
define dso_local void @test_amx_load_store2(ptr %dst, ptr %src) {
; CHECK-LABEL: @test_amx_load_store2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[AMX:%.*]] = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 16, i16 16, ptr [[SRC:%.*]], i64 64)
; CHECK-NEXT:    [[BC:%.*]] = bitcast x86_amx [[AMX]] to <256 x i32>
; CHECK-NEXT:    store <256 x i32> [[BC]], ptr [[DST:%.*]], align 1024
; CHECK-NEXT:    ret void
;
entry:
  %amx = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 16, i16 16, ptr %src, i64 64)
  %bc = bitcast x86_amx %amx to <256 x i32>
  store <256 x i32> %bc, ptr %dst
  ret void
}

declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, ptr, i64)
declare void @llvm.x86.tilestored64.internal(i16, i16, ptr, i64, x86_amx)