llvm/test/Transforms/LowerMatrixIntrinsics/multiply-fused-volatile.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -lower-matrix-intrinsics -fuse-matrix-tile-size=2 -matrix-allow-contract -force-fuse-matrix -verify-dom-info %s -S | FileCheck %s

; REQUIRES: aarch64-registered-target

target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "aarch64-apple-ios"

define void @multiply_all_volatile(<4 x double>* noalias %A, <4 x double>* noalias %B, <4 x double>* noalias %C) {
; CHECK-LABEL: @multiply_all_volatile(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x double>* [[A:%.*]] to double*
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[TMP0]], i64 0
; CHECK-NEXT:    [[COL_CAST:%.*]] = bitcast double* [[TMP1]] to <4 x double>*
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x double>* [[COL_CAST]] to double*
; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast double* [[TMP2]] to <2 x double>*
; CHECK-NEXT:    load volatile <2 x double>, <2 x double>* [[VEC_CAST]], align 8
; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr double, double* [[TMP2]], i64 2
; CHECK-NEXT:    [[VEC_CAST1:%.*]] = bitcast double* [[VEC_GEP]] to <2 x double>*
; CHECK-NEXT:    load volatile <2 x double>, <2 x double>* [[VEC_CAST1]], align 8
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast <4 x double>* [[B:%.*]] to double*
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr double, double* [[TMP3]], i64 0
; CHECK-NEXT:    [[COL_CAST3:%.*]] = bitcast double* [[TMP4]] to <4 x double>*
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast <4 x double>* [[COL_CAST3]] to double*
; CHECK-NEXT:    [[VEC_CAST4:%.*]] = bitcast double* [[TMP5]] to <2 x double>*
; CHECK-NEXT:    load volatile <2 x double>, <2 x double>* [[VEC_CAST4]], align 8
; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr double, double* [[TMP5]], i64 2
; CHECK-NEXT:    [[VEC_CAST7:%.*]] = bitcast double* [[VEC_GEP6]] to <2 x double>*
; CHECK-NEXT:    load volatile <2 x double>, <2 x double>* [[VEC_CAST7]], align 8

; CHECK:         [[TMP18:%.*]] = bitcast <4 x double>* [[C:%.*]] to double*
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr double, double* [[TMP18]], i64 0
; CHECK-NEXT:    [[COL_CAST18:%.*]] = bitcast double* [[TMP19]] to <4 x double>*
; CHECK-NEXT:    [[TMP20:%.*]] = bitcast <4 x double>* [[COL_CAST18]] to double*
; CHECK-NEXT:    [[VEC_CAST19:%.*]] = bitcast double* [[TMP20]] to <2 x double>*
; CHECK-NEXT:    store volatile <2 x double> {{.*}}, <2 x double>* [[VEC_CAST19]], align 8
; CHECK-NEXT:    [[VEC_GEP20:%.*]] = getelementptr double, double* [[TMP20]], i64 2
; CHECK-NEXT:    [[VEC_CAST21:%.*]] = bitcast double* [[VEC_GEP20]] to <2 x double>*
; CHECK-NEXT:    store volatile <2 x double> {{.*}}, <2 x double>* [[VEC_CAST21]], align 8
; CHECK-NEXT:    ret void
;

entry:
  %a = load volatile <4 x double>, <4 x double>* %A, align 8
  %b = load volatile <4 x double>, <4 x double>* %B, align 8

  %c = call <4 x double> @llvm.matrix.multiply(<4 x double> %a, <4 x double> %b, i32 2, i32 2, i32 2)

  store volatile <4 x double> %c, <4 x double>* %C, align 8
  ret void
}


define void @multiply_load0_volatile(<4 x double>* noalias %A, <4 x double>* noalias %B, <4 x double>* noalias %C) {
; CHECK-LABEL: @multiply_load0_volatile(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x double>* [[A:%.*]] to double*
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[TMP0]], i64 0
; CHECK-NEXT:    [[COL_CAST:%.*]] = bitcast double* [[TMP1]] to <4 x double>*
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x double>* [[COL_CAST]] to double*
; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast double* [[TMP2]] to <2 x double>*
; CHECK-NEXT:    load volatile <2 x double>, <2 x double>* [[VEC_CAST]], align 8
; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr double, double* [[TMP2]], i64 2
; CHECK-NEXT:    [[VEC_CAST1:%.*]] = bitcast double* [[VEC_GEP]] to <2 x double>*
; CHECK-NEXT:    load volatile <2 x double>, <2 x double>* [[VEC_CAST1]], align 8
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast <4 x double>* [[B:%.*]] to double*
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr double, double* [[TMP3]], i64 0
; CHECK-NEXT:    [[COL_CAST3:%.*]] = bitcast double* [[TMP4]] to <4 x double>*
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast <4 x double>* [[COL_CAST3]] to double*
; CHECK-NEXT:    [[VEC_CAST4:%.*]] = bitcast double* [[TMP5]] to <2 x double>*
; CHECK-NEXT:    load <2 x double>, <2 x double>* [[VEC_CAST4]], align 8
; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr double, double* [[TMP5]], i64 2
; CHECK-NEXT:    [[VEC_CAST7:%.*]] = bitcast double* [[VEC_GEP6]] to <2 x double>*
; CHECK-NEXT:    load <2 x double>, <2 x double>* [[VEC_CAST7]], align 8

; CHECK:         [[TMP18:%.*]] = bitcast <4 x double>* [[C:%.*]] to double*
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr double, double* [[TMP18]], i64 0
; CHECK-NEXT:    [[COL_CAST18:%.*]] = bitcast double* [[TMP19]] to <4 x double>*
; CHECK-NEXT:    [[TMP20:%.*]] = bitcast <4 x double>* [[COL_CAST18]] to double*
; CHECK-NEXT:    [[VEC_CAST19:%.*]] = bitcast double* [[TMP20]] to <2 x double>*
; CHECK-NEXT:    store <2 x double> {{.*}}, <2 x double>* [[VEC_CAST19]], align 8
; CHECK-NEXT:    [[VEC_GEP20:%.*]] = getelementptr double, double* [[TMP20]], i64 2
; CHECK-NEXT:    [[VEC_CAST21:%.*]] = bitcast double* [[VEC_GEP20]] to <2 x double>*
; CHECK-NEXT:    store <2 x double> {{.*}}, <2 x double>* [[VEC_CAST21]], align 8
; CHECK-NEXT:    ret void
;

entry:
  %a = load volatile <4 x double>, <4 x double>* %A, align 8
  %b = load <4 x double>, <4 x double>* %B, align 8

  %c = call <4 x double> @llvm.matrix.multiply(<4 x double> %a, <4 x double> %b, i32 2, i32 2, i32 2)

  store <4 x double> %c, <4 x double>* %C, align 8
  ret void
}

define void @multiply_load1_volatile(<4 x double>* noalias %A, <4 x double>* noalias %B, <4 x double>* noalias %C) {
; CHECK-LABEL: @multiply_load1_volatile(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x double>* [[A:%.*]] to double*
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[TMP0]], i64 0
; CHECK-NEXT:    [[COL_CAST:%.*]] = bitcast double* [[TMP1]] to <4 x double>*
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x double>* [[COL_CAST]] to double*
; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast double* [[TMP2]] to <2 x double>*
; CHECK-NEXT:    load <2 x double>, <2 x double>* [[VEC_CAST]], align 8
; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr double, double* [[TMP2]], i64 2
; CHECK-NEXT:    [[VEC_CAST1:%.*]] = bitcast double* [[VEC_GEP]] to <2 x double>*
; CHECK-NEXT:    load <2 x double>, <2 x double>* [[VEC_CAST1]], align 8
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast <4 x double>* [[B:%.*]] to double*
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr double, double* [[TMP3]], i64 0
; CHECK-NEXT:    [[COL_CAST3:%.*]] = bitcast double* [[TMP4]] to <4 x double>*
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast <4 x double>* [[COL_CAST3]] to double*
; CHECK-NEXT:    [[VEC_CAST4:%.*]] = bitcast double* [[TMP5]] to <2 x double>*
; CHECK-NEXT:    load volatile <2 x double>, <2 x double>* [[VEC_CAST4]], align 8
; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr double, double* [[TMP5]], i64 2
; CHECK-NEXT:    [[VEC_CAST7:%.*]] = bitcast double* [[VEC_GEP6]] to <2 x double>*
; CHECK-NEXT:    load volatile <2 x double>, <2 x double>* [[VEC_CAST7]], align 8

; CHECK:         [[TMP18:%.*]] = bitcast <4 x double>* [[C:%.*]] to double*
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr double, double* [[TMP18]], i64 0
; CHECK-NEXT:    [[COL_CAST18:%.*]] = bitcast double* [[TMP19]] to <4 x double>*
; CHECK-NEXT:    [[TMP20:%.*]] = bitcast <4 x double>* [[COL_CAST18]] to double*
; CHECK-NEXT:    [[VEC_CAST19:%.*]] = bitcast double* [[TMP20]] to <2 x double>*
; CHECK-NEXT:    store <2 x double> {{.*}}, <2 x double>* [[VEC_CAST19]], align 8
; CHECK-NEXT:    [[VEC_GEP20:%.*]] = getelementptr double, double* [[TMP20]], i64 2
; CHECK-NEXT:    [[VEC_CAST21:%.*]] = bitcast double* [[VEC_GEP20]] to <2 x double>*
; CHECK-NEXT:    store <2 x double> {{.*}}, <2 x double>* [[VEC_CAST21]], align 8
; CHECK-NEXT:    ret void
;

entry:
  %a = load <4 x double>, <4 x double>* %A, align 8
  %b = load volatile <4 x double>, <4 x double>* %B, align 8

  %c = call <4 x double> @llvm.matrix.multiply(<4 x double> %a, <4 x double> %b, i32 2, i32 2, i32 2)

  store <4 x double> %c, <4 x double>* %C, align 8
  ret void
}

define void @multiply_store_volatile(<4 x double>* noalias %A, <4 x double>* noalias %B, <4 x double>* noalias %C) {
; CHECK-LABEL: @multiply_store_volatile(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x double>* [[A:%.*]] to double*
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[TMP0]], i64 0
; CHECK-NEXT:    [[COL_CAST:%.*]] = bitcast double* [[TMP1]] to <4 x double>*
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x double>* [[COL_CAST]] to double*
; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast double* [[TMP2]] to <2 x double>*
; CHECK-NEXT:    load <2 x double>, <2 x double>* [[VEC_CAST]], align 8
; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr double, double* [[TMP2]], i64 2
; CHECK-NEXT:    [[VEC_CAST1:%.*]] = bitcast double* [[VEC_GEP]] to <2 x double>*
; CHECK-NEXT:    load <2 x double>, <2 x double>* [[VEC_CAST1]], align 8
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast <4 x double>* [[B:%.*]] to double*
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr double, double* [[TMP3]], i64 0
; CHECK-NEXT:    [[COL_CAST3:%.*]] = bitcast double* [[TMP4]] to <4 x double>*
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast <4 x double>* [[COL_CAST3]] to double*
; CHECK-NEXT:    [[VEC_CAST4:%.*]] = bitcast double* [[TMP5]] to <2 x double>*
; CHECK-NEXT:    load <2 x double>, <2 x double>* [[VEC_CAST4]], align 8
; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr double, double* [[TMP5]], i64 2
; CHECK-NEXT:    [[VEC_CAST7:%.*]] = bitcast double* [[VEC_GEP6]] to <2 x double>*
; CHECK-NEXT:    load <2 x double>, <2 x double>* [[VEC_CAST7]], align 8

; CHECK:         [[TMP18:%.*]] = bitcast <4 x double>* [[C:%.*]] to double*
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr double, double* [[TMP18]], i64 0
; CHECK-NEXT:    [[COL_CAST18:%.*]] = bitcast double* [[TMP19]] to <4 x double>*
; CHECK-NEXT:    [[TMP20:%.*]] = bitcast <4 x double>* [[COL_CAST18]] to double*
; CHECK-NEXT:    [[VEC_CAST19:%.*]] = bitcast double* [[TMP20]] to <2 x double>*
; CHECK-NEXT:    store volatile <2 x double> {{.*}}, <2 x double>* [[VEC_CAST19]], align 8
; CHECK-NEXT:    [[VEC_GEP20:%.*]] = getelementptr double, double* [[TMP20]], i64 2
; CHECK-NEXT:    [[VEC_CAST21:%.*]] = bitcast double* [[VEC_GEP20]] to <2 x double>*
; CHECK-NEXT:    store volatile <2 x double> {{.*}}, <2 x double>* [[VEC_CAST21]], align 8
; CHECK-NEXT:    ret void
;
entry:
  %a = load <4 x double>, <4 x double>* %A, align 8
  %b = load <4 x double>, <4 x double>* %B, align 8

  %c = call <4 x double> @llvm.matrix.multiply(<4 x double> %a, <4 x double> %b, i32 2, i32 2, i32 2)

  store volatile <4 x double> %c, <4 x double>* %C, align 8
  ret void
}

declare <4 x double> @llvm.matrix.multiply(<4 x double>, <4 x double>, i32, i32, i32)