; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -S %s -passes=scalarize-masked-mem-intrin -mtriple=amdgcn-amd-amdhsa | FileCheck %s

; COM: Test that, unlike on CPU targets, the mask doesn't get bitcast to a scalar,
; COM: since, on GPUs, each i1 takes up at least one register and so they should
; COM: be treated separately.

define <2 x i32> @scalarize_v2i32(<2 x ptr> %p, <2 x i1> %mask, <2 x i32> %passthru) {
; CHECK-LABEL: define <2 x i32> @scalarize_v2i32(
; CHECK-SAME: <2 x ptr> [[P:%.*]], <2 x i1> [[MASK:%.*]], <2 x i32> [[PASSTHRU:%.*]]) {
; CHECK-NEXT:    [[MASK0:%.*]] = extractelement <2 x i1> [[MASK]], i64 0
; CHECK-NEXT:    br i1 [[MASK0]], label %[[COND_LOAD:.*]], label %[[ELSE:.*]]
; CHECK:       [[COND_LOAD]]:
; CHECK-NEXT:    [[PTR0:%.*]] = extractelement <2 x ptr> [[P]], i64 0
; CHECK-NEXT:    [[LOAD0:%.*]] = load i32, ptr [[PTR0]], align 8
; CHECK-NEXT:    [[RES0:%.*]] = insertelement <2 x i32> [[PASSTHRU]], i32 [[LOAD0]], i64 0
; CHECK-NEXT:    br label %[[ELSE]]
; CHECK:       [[ELSE]]:
; CHECK-NEXT:    [[RES_PHI_ELSE:%.*]] = phi <2 x i32> [ [[RES0]], %[[COND_LOAD]] ], [ [[PASSTHRU]], [[TMP0:%.*]] ]
; CHECK-NEXT:    [[MASK1:%.*]] = extractelement <2 x i1> [[MASK]], i64 1
; CHECK-NEXT:    br i1 [[MASK1]], label %[[COND_LOAD1:.*]], label %[[ELSE2:.*]]
; CHECK:       [[COND_LOAD1]]:
; CHECK-NEXT:    [[PTR1:%.*]] = extractelement <2 x ptr> [[P]], i64 1
; CHECK-NEXT:    [[LOAD1:%.*]] = load i32, ptr [[PTR1]], align 8
; CHECK-NEXT:    [[RES1:%.*]] = insertelement <2 x i32> [[RES_PHI_ELSE]], i32 [[LOAD1]], i64 1
; CHECK-NEXT:    br label %[[ELSE2]]
; CHECK:       [[ELSE2]]:
; CHECK-NEXT:    [[RES_PHI_ELSE3:%.*]] = phi <2 x i32> [ [[RES1]], %[[COND_LOAD1]] ], [ [[RES_PHI_ELSE]], %[[ELSE]] ]
; CHECK-NEXT:    ret <2 x i32> [[RES_PHI_ELSE3]]
;
  %ret = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> %p, i32 8, <2 x i1> %mask, <2 x i32> %passthru)
  ret <2 x i32> %ret
}

declare <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr>, i32, <2 x i1>, <2 x i32>)