45 lines
2.1 KiB
LLVM
45 lines
2.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -stop-after=irtranslator < %s | FileCheck %s
|
|
|
|
define ptr @ptrmask_flat_i64(ptr %ptr, i64 %mask) {
|
|
; CHECK-LABEL: name: ptrmask_flat_i64
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; CHECK-NEXT: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
|
|
; CHECK-NEXT: [[PTRMASK:%[0-9]+]]:_(p0) = G_PTRMASK [[MV]], [[MV1]](s64)
|
|
; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[PTRMASK]](p0)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[UV]](s32)
|
|
; CHECK-NEXT: $vgpr1 = COPY [[UV1]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
|
|
%masked = call ptr @llvm.ptrmask.p0.i64(ptr %ptr, i64 %mask)
|
|
ret ptr %masked
|
|
}
|
|
|
|
define ptr addrspace(3) @ptrmask_local_i32(ptr addrspace(3) %ptr, i32 %mask) {
|
|
; CHECK-LABEL: name: ptrmask_local_i32
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p3) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[PTRMASK:%[0-9]+]]:_(p3) = G_PTRMASK [[COPY]], [[COPY1]](s32)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[PTRMASK]](p3)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0
|
|
%masked = call ptr addrspace(3) @llvm.ptrmask.p3.i32(ptr addrspace(3) %ptr, i32 %mask)
|
|
ret ptr addrspace(3) %masked
|
|
}
|
|
|
|
; Seems to not work
|
|
; define <2 x ptr> @ptrmask_flat_i64_v2(<2 x ptr> %ptr, <2 x i64> %mask) {
|
|
; %masked = call <2 x ptr> @llvm.ptrmask.v2p0.v2i64(<2 x ptr> %ptr, <2 x i64> %mask)
|
|
; ret <2 x ptr> %masked
|
|
; }
|
|
|
|
declare ptr @llvm.ptrmask.p0.i64(ptr, i64)
|
|
declare ptr addrspace(3) @llvm.ptrmask.p3.i32(ptr addrspace(3), i32)
|