forked from OSchip/llvm-project
AMDGPU: Add D16 instructions preserve unused bits feature
- Predicate D16 patterns on this new feature - Added this new feature to gfx900/2/4 Differential Revision: https://reviews.llvm.org/D46366 llvm-svn: 331551
This commit is contained in:
Konstantin Zhuravlyov
parent
e1c7a46d5b
commit
c2c2eb7d01
|
|
@ -322,6 +322,13 @@ def FeatureDLInsts : SubtargetFeature<"dl-insts",
|
|||
"Has deep learning instructions"
|
||||
>;
|
||||
|
||||
def FeatureD16PreservesUnusedBits : SubtargetFeature<
|
||||
"d16-preserves-unused-bits",
|
||||
"D16PreservesUnusedBits",
|
||||
"true",
|
||||
"D16 memory instructions preserve unused bits rather than zeroing them out"
|
||||
>;
|
||||
|
||||
//===------------------------------------------------------------===//
|
||||
// Subtarget Features (options and debugging)
|
||||
//===------------------------------------------------------------===//
|
||||
|
|
@ -608,20 +615,23 @@ def FeatureISAVersion8_1_0 : SubtargetFeatureISAVersion <8,1,0,
|
|||
def FeatureISAVersion9_0_0 : SubtargetFeatureISAVersion <9,0,0,
|
||||
[FeatureGFX9,
|
||||
FeatureMadMixInsts,
|
||||
FeatureLDSBankCount32
|
||||
FeatureLDSBankCount32,
|
||||
FeatureD16PreservesUnusedBits
|
||||
]>;
|
||||
|
||||
def FeatureISAVersion9_0_2 : SubtargetFeatureISAVersion <9,0,2,
|
||||
[FeatureGFX9,
|
||||
FeatureMadMixInsts,
|
||||
FeatureLDSBankCount32,
|
||||
FeatureXNACK
|
||||
FeatureXNACK,
|
||||
FeatureD16PreservesUnusedBits
|
||||
]>;
|
||||
|
||||
def FeatureISAVersion9_0_4 : SubtargetFeatureISAVersion <9,0,4,
|
||||
[FeatureGFX9,
|
||||
FeatureLDSBankCount32,
|
||||
FeatureFmaMixInsts]>;
|
||||
FeatureFmaMixInsts,
|
||||
FeatureD16PreservesUnusedBits]>;
|
||||
|
||||
def FeatureISAVersion9_0_6 : SubtargetFeatureISAVersion <9,0,6,
|
||||
[FeatureGFX9,
|
||||
|
|
@ -769,6 +779,8 @@ def HasUnpackedD16VMem : Predicate<"Subtarget->hasUnpackedD16VMem()">,
|
|||
def HasPackedD16VMem : Predicate<"!Subtarget->hasUnpackedD16VMem()">,
|
||||
AssemblerPredicate<"!FeatureUnpackedD16VMem">;
|
||||
|
||||
def D16PreservesUnusedBits : Predicate<"Subtarget->d16PreservesUnusedBits()">,
|
||||
AssemblerPredicate<"FeatureD16PreservesUnusedBits">;
|
||||
|
||||
def LDSRequiresM0Init : Predicate<"Subtarget->ldsRequiresM0Init()">;
|
||||
def NotLDSRequiresM0Init : Predicate<"!Subtarget->ldsRequiresM0Init()">;
|
||||
|
|
|
|||
|
|
@ -162,6 +162,7 @@ AMDGPUSubtarget::AMDGPUSubtarget(const Triple &TT, StringRef GPU, StringRef FS,
|
|||
HasSDWAOutModsVOPC(false),
|
||||
HasDPP(false),
|
||||
HasDLInsts(false),
|
||||
D16PreservesUnusedBits(false),
|
||||
FlatAddressSpace(false),
|
||||
FlatInstOffsets(false),
|
||||
FlatGlobalInsts(false),
|
||||
|
|
|
|||
|
|
@ -166,6 +166,7 @@ protected:
|
|||
bool HasSDWAOutModsVOPC;
|
||||
bool HasDPP;
|
||||
bool HasDLInsts;
|
||||
bool D16PreservesUnusedBits;
|
||||
bool FlatAddressSpace;
|
||||
bool FlatInstOffsets;
|
||||
bool FlatGlobalInsts;
|
||||
|
|
@ -546,6 +547,10 @@ public:
|
|||
return HasDLInsts;
|
||||
}
|
||||
|
||||
bool d16PreservesUnusedBits() const {
|
||||
return D16PreservesUnusedBits;
|
||||
}
|
||||
|
||||
/// Returns the offset in bytes from the start of the input buffer
|
||||
/// of the first explicit kernel argument.
|
||||
unsigned getExplicitKernelArgOffset(const MachineFunction &MF) const {
|
||||
|
|
|
|||
|
|
@ -1374,7 +1374,7 @@ defm : MUBUFScratchLoadPat <BUFFER_LOAD_DWORD_OFFEN, BUFFER_LOAD_DWORD_OFFSET, i
|
|||
defm : MUBUFScratchLoadPat <BUFFER_LOAD_DWORDX2_OFFEN, BUFFER_LOAD_DWORDX2_OFFSET, v2i32, load_private>;
|
||||
defm : MUBUFScratchLoadPat <BUFFER_LOAD_DWORDX4_OFFEN, BUFFER_LOAD_DWORDX4_OFFSET, v4i32, load_private>;
|
||||
|
||||
let OtherPredicates = [HasD16LoadStore] in {
|
||||
let OtherPredicates = [D16PreservesUnusedBits] in {
|
||||
defm : MUBUFScratchLoadPat_Hi16<BUFFER_LOAD_SHORT_D16_HI_OFFEN, BUFFER_LOAD_SHORT_D16_HI_OFFSET, i16, load_private>;
|
||||
defm : MUBUFScratchLoadPat_Hi16<BUFFER_LOAD_UBYTE_D16_HI_OFFEN, BUFFER_LOAD_UBYTE_D16_HI_OFFSET, i16, az_extloadi8_private>;
|
||||
defm : MUBUFScratchLoadPat_Hi16<BUFFER_LOAD_SBYTE_D16_HI_OFFEN, BUFFER_LOAD_SBYTE_D16_HI_OFFSET, i16, sextloadi8_private>;
|
||||
|
|
@ -1489,7 +1489,7 @@ defm : MUBUFScratchStorePat <BUFFER_STORE_DWORDX2_OFFEN, BUFFER_STORE_DWORDX2_OF
|
|||
defm : MUBUFScratchStorePat <BUFFER_STORE_DWORDX4_OFFEN, BUFFER_STORE_DWORDX4_OFFSET, v4i32, store_private>;
|
||||
|
||||
|
||||
let OtherPredicates = [HasD16LoadStore] in {
|
||||
let OtherPredicates = [D16PreservesUnusedBits] in {
|
||||
// Hiding the extract high pattern in the PatFrag seems to not
|
||||
// automatically increase the complexity.
|
||||
let AddedComplexity = 1 in {
|
||||
|
|
|
|||
|
|
@ -655,7 +655,7 @@ defm : DSReadPat_mc <DS_READ_B128, v4i32, "load_align16_local">;
|
|||
|
||||
} // End AddedComplexity = 100
|
||||
|
||||
let OtherPredicates = [HasD16LoadStore] in {
|
||||
let OtherPredicates = [D16PreservesUnusedBits] in {
|
||||
let AddedComplexity = 100 in {
|
||||
defm : DSReadPat_Hi16<DS_READ_U16_D16_HI, load_local>;
|
||||
defm : DSReadPat_Hi16<DS_READ_U8_D16_HI, az_extloadi8_local>;
|
||||
|
|
@ -689,7 +689,7 @@ defm : DSWritePat_mc <DS_WRITE_B8, i16, "truncstorei8_local">;
|
|||
defm : DSWritePat_mc <DS_WRITE_B16, i16, "store_local">;
|
||||
defm : DSWritePat_mc <DS_WRITE_B32, i32, "store_local">;
|
||||
|
||||
let OtherPredicates = [HasD16LoadStore] in {
|
||||
let OtherPredicates = [D16PreservesUnusedBits] in {
|
||||
def : DSWritePat <DS_WRITE_B16_D16_HI, i32, store_local_hi16>;
|
||||
def : DSWritePat <DS_WRITE_B8_D16_HI, i32, truncstorei8_local_hi16>;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -780,7 +780,7 @@ def : FlatAtomicPat <FLAT_ATOMIC_XOR_X2_RTN, atomic_xor_global, i64>;
|
|||
def : FlatStorePat <FLAT_STORE_BYTE, truncstorei8_flat, i16>;
|
||||
def : FlatStorePat <FLAT_STORE_SHORT, store_flat, i16>;
|
||||
|
||||
let OtherPredicates = [HasD16LoadStore] in {
|
||||
let OtherPredicates = [D16PreservesUnusedBits] in {
|
||||
def : FlatStorePat <FLAT_STORE_SHORT_D16_HI, truncstorei16_hi16_flat, i32>;
|
||||
def : FlatStorePat <FLAT_STORE_BYTE_D16_HI, truncstorei8_hi16_flat, i32>;
|
||||
|
||||
|
|
@ -824,7 +824,7 @@ def : FlatStoreSignedPat <GLOBAL_STORE_DWORD, store_global, i32>;
|
|||
def : FlatStoreSignedPat <GLOBAL_STORE_DWORDX2, store_global, v2i32>;
|
||||
def : FlatStoreSignedPat <GLOBAL_STORE_DWORDX4, store_global, v4i32>;
|
||||
|
||||
let OtherPredicates = [HasD16LoadStore] in {
|
||||
let OtherPredicates = [D16PreservesUnusedBits] in {
|
||||
def : FlatStoreSignedPat <GLOBAL_STORE_SHORT_D16_HI, truncstorei16_hi16_global, i32>;
|
||||
def : FlatStoreSignedPat <GLOBAL_STORE_BYTE_D16_HI, truncstorei8_hi16_global, i32>;
|
||||
|
||||
|
|
|
|||
|
|
@ -1,13 +1,14 @@
|
|||
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9 %s
|
||||
; RUN: llc -march=amdgcn -mcpu=fiji -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI %s
|
||||
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX900 %s
|
||||
; RUN: llc -march=amdgcn -mcpu=gfx906 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX906,NO-D16-HI %s
|
||||
; RUN: llc -march=amdgcn -mcpu=fiji -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX803,NO-D16-HI %s
|
||||
|
||||
; GCN-LABEL: {{^}}load_local_hi_v2i16_undeflo:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_u16_d16_hi v0, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: ds_read_u16_d16_hi v0, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: ds_read_u16 v
|
||||
; NO-D16-HI: ds_read_u16 v
|
||||
define <2 x i16> @load_local_hi_v2i16_undeflo(i16 addrspace(3)* %in) #0 {
|
||||
entry:
|
||||
%load = load i16, i16 addrspace(3)* %in
|
||||
|
|
@ -17,12 +18,12 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_local_hi_v2i16_reglo:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_u16_d16_hi v1, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: ds_read_u16_d16_hi v1, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: v_mov_b32_e32 v0, v1
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: ds_read_u16 v
|
||||
; NO-D16-HI: ds_read_u16 v
|
||||
define <2 x i16> @load_local_hi_v2i16_reglo(i16 addrspace(3)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load i16, i16 addrspace(3)* %in
|
||||
|
|
@ -34,13 +35,13 @@ entry:
|
|||
; Show that we get reasonable regalloc without physreg constraints.
|
||||
; GCN-LABEL: {{^}}load_local_hi_v2i16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_u16_d16_hi v1, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v[0:1], v1, off{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: ds_read_u16_d16_hi v1, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v[0:1], v1, off{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: ds_read_u16 v
|
||||
; NO-D16-HI: ds_read_u16 v
|
||||
define void @load_local_hi_v2i16_reglo_vreg(i16 addrspace(3)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load i16, i16 addrspace(3)* %in
|
||||
|
|
@ -52,13 +53,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_local_hi_v2i16_zerolo:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
||||
; GFX9-NEXT: ds_read_u16_d16_hi v1, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: v_mov_b32_e32 v1, 0
|
||||
; GFX900-NEXT: ds_read_u16_d16_hi v1, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: v_mov_b32_e32 v0, v1
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: ds_read_u16 v
|
||||
; NO-D16-HI: ds_read_u16 v
|
||||
define <2 x i16> @load_local_hi_v2i16_zerolo(i16 addrspace(3)* %in) #0 {
|
||||
entry:
|
||||
%load = load i16, i16 addrspace(3)* %in
|
||||
|
|
@ -69,13 +70,13 @@ entry:
|
|||
; FIXME: Remove m0 initialization
|
||||
; GCN-LABEL: {{^}}load_local_hi_v2i16_zerolo_shift:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_u16 v0, v0
|
||||
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
||||
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 16, v0
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: ds_read_u16 v0, v0
|
||||
; GFX900-NEXT: s_waitcnt lgkmcnt(0)
|
||||
; GFX900-NEXT: v_lshlrev_b32_e32 v0, 16, v0
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: ds_read_u16 v
|
||||
; VI: v_lshlrev_b32_e32 v0, 16, v0
|
||||
; NO-D16-HI: ds_read_u16 v
|
||||
; NO-D16-HI: v_lshlrev_b32_e32 v0, 16, v0
|
||||
define i32 @load_local_hi_v2i16_zerolo_shift(i16 addrspace(3)* %in) #0 {
|
||||
entry:
|
||||
%load = load i16, i16 addrspace(3)* %in
|
||||
|
|
@ -86,13 +87,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_local_hi_v2f16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_u16_d16_hi v1, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v[0:1], v1, off{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: ds_read_u16_d16_hi v1, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v[0:1], v1, off{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: ds_read_u16 v
|
||||
; NO-D16-HI: ds_read_u16 v
|
||||
define void @load_local_hi_v2f16_reglo_vreg(half addrspace(3)* %in, half %reg) #0 {
|
||||
entry:
|
||||
%load = load half, half addrspace(3)* %in
|
||||
|
|
@ -104,13 +105,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_local_hi_v2i16_reglo_vreg_zexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_u8_d16_hi v1, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v[0:1], v1, off{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: ds_read_u8_d16_hi v1, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v[0:1], v1, off{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: ds_read_u8 v
|
||||
; NO-D16-HI: ds_read_u8 v
|
||||
define void @load_local_hi_v2i16_reglo_vreg_zexti8(i8 addrspace(3)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load i8, i8 addrspace(3)* %in
|
||||
|
|
@ -123,13 +124,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_local_hi_v2i16_reglo_vreg_sexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_i8_d16_hi v1, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v[0:1], v1, off{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: ds_read_i8_d16_hi v1, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v[0:1], v1, off{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: ds_read_i8 v
|
||||
; NO-D16-HI: ds_read_i8 v
|
||||
define void @load_local_hi_v2i16_reglo_vreg_sexti8(i8 addrspace(3)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load i8, i8 addrspace(3)* %in
|
||||
|
|
@ -142,11 +143,11 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_global_hi_v2i16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_load_short_d16_hi v2, v[0:1], off offset:-4094
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: global_load_short_d16_hi v2, v[0:1], off offset:-4094
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define void @load_global_hi_v2i16_reglo_vreg(i16 addrspace(1)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 -2047
|
||||
|
|
@ -159,11 +160,11 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_global_hi_v2f16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_load_short_d16_hi v2, v[0:1], off offset:-4094
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: global_load_short_d16_hi v2, v[0:1], off offset:-4094
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define void @load_global_hi_v2f16_reglo_vreg(half addrspace(1)* %in, half %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds half, half addrspace(1)* %in, i64 -2047
|
||||
|
|
@ -176,11 +177,11 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_global_hi_v2i16_reglo_vreg_zexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_load_ubyte_d16_hi v2, v[0:1], off offset:-4095
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: global_load_ubyte_d16_hi v2, v[0:1], off offset:-4095
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define void @load_global_hi_v2i16_reglo_vreg_zexti8(i8 addrspace(1)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i8, i8 addrspace(1)* %in, i64 -4095
|
||||
|
|
@ -194,11 +195,11 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_global_hi_v2i16_reglo_vreg_sexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_load_sbyte_d16_hi v2, v[0:1], off offset:-4095
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: global_load_sbyte_d16_hi v2, v[0:1], off offset:-4095
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define void @load_global_hi_v2i16_reglo_vreg_sexti8(i8 addrspace(1)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i8, i8 addrspace(1)* %in, i64 -4095
|
||||
|
|
@ -212,15 +213,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: load_flat_hi_v2i16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: flat_load_short_d16_hi v2, v[0:1]
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v[0:1], v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: flat_load_short_d16_hi v2, v[0:1]
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v[0:1], v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: flat_load_ushort v{{[0-9]+}}
|
||||
; VI: v_lshlrev_b32_e32 v{{[0-9]+}}, 16,
|
||||
; VI: v_or_b32_sdwa
|
||||
; NO-D16-HI: flat_load_ushort v{{[0-9]+}}
|
||||
; GFX803: v_lshlrev_b32_e32 v{{[0-9]+}}, 16,
|
||||
; GFX803: v_or_b32_sdwa
|
||||
; GFX906: v_lshl_or_b32 v{{[0-9]+}}, v{{[0-9]+}}, 16,
|
||||
define void @load_flat_hi_v2i16_reglo_vreg(i16* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load i16, i16* %in
|
||||
|
|
@ -232,15 +234,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_flat_hi_v2f16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: flat_load_short_d16_hi v2, v[0:1]
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v[0:1], v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: flat_load_short_d16_hi v2, v[0:1]
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v[0:1], v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: flat_load_ushort v{{[0-9]+}}
|
||||
; VI: v_lshlrev_b32_e32 v{{[0-9]+}}, 16,
|
||||
; VI: v_or_b32_sdwa
|
||||
; NO-D16-HI: flat_load_ushort v{{[0-9]+}}
|
||||
; GFX803: v_lshlrev_b32_e32 v{{[0-9]+}}, 16,
|
||||
; GFX803: v_or_b32_sdwa
|
||||
; GFX906: v_lshl_or_b32 v{{[0-9]+}}, v{{[0-9]+}}, 16,
|
||||
define void @load_flat_hi_v2f16_reglo_vreg(half* %in, half %reg) #0 {
|
||||
entry:
|
||||
%load = load half, half* %in
|
||||
|
|
@ -252,15 +255,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_flat_hi_v2i16_reglo_vreg_zexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: flat_load_ubyte_d16_hi v2, v[0:1]
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v[0:1], v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: flat_load_ubyte_d16_hi v2, v[0:1]
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v[0:1], v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: flat_load_ubyte v{{[0-9]+}}
|
||||
; VI: v_lshlrev_b32_e32 v{{[0-9]+}}, 16,
|
||||
; VI: v_or_b32_sdwa
|
||||
; NO-D16-HI: flat_load_ubyte v{{[0-9]+}}
|
||||
; GFX803: v_lshlrev_b32_e32 v{{[0-9]+}}, 16,
|
||||
; GFX803: v_or_b32_sdwa
|
||||
; GFX906: v_lshl_or_b32 v{{[0-9]+}}, v{{[0-9]+}}, 16,
|
||||
define void @load_flat_hi_v2i16_reglo_vreg_zexti8(i8* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load i8, i8* %in
|
||||
|
|
@ -273,15 +277,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_flat_hi_v2i16_reglo_vreg_sexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: flat_load_sbyte_d16_hi v2, v[0:1]
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v[0:1], v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: flat_load_sbyte_d16_hi v2, v[0:1]
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v[0:1], v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: flat_load_sbyte v{{[0-9]+}}
|
||||
; VI: v_lshlrev_b32_e32 v{{[0-9]+}}, 16,
|
||||
; VI: v_or_b32_sdwa
|
||||
; NO-D16-HI: flat_load_sbyte v{{[0-9]+}}
|
||||
; GFX803: v_lshlrev_b32_e32 v{{[0-9]+}}, 16,
|
||||
; GFX803: v_or_b32_sdwa
|
||||
; GFX906: v_lshl_or_b32 v{{[0-9]+}}, v{{[0-9]+}}, 16,
|
||||
define void @load_flat_hi_v2i16_reglo_vreg_sexti8(i8* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load i8, i8* %in
|
||||
|
|
@ -294,13 +299,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_load_short_d16_hi v0, off, s[0:3], s5 offset:4094{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900: buffer_load_short_d16_hi v0, off, s[0:3], s5 offset:4094{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_ushort v{{[0-9]+}}, off, s[0:3], s5 offset:4094{{$}}
|
||||
; NO-D16-HI: buffer_load_ushort v{{[0-9]+}}, off, s[0:3], s5 offset:4094{{$}}
|
||||
define void @load_private_hi_v2i16_reglo_vreg(i16 addrspace(5)* byval %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i16, i16 addrspace(5)* %in, i64 2045
|
||||
|
|
@ -313,13 +318,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2f16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_load_short_d16_hi v0, off, s[0:3], s5 offset:4094{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900: buffer_load_short_d16_hi v0, off, s[0:3], s5 offset:4094{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_ushort v{{[0-9]+}}, off, s[0:3], s5 offset:4094{{$}}
|
||||
; NO-D16-HI: buffer_load_ushort v{{[0-9]+}}, off, s[0:3], s5 offset:4094{{$}}
|
||||
define void @load_private_hi_v2f16_reglo_vreg(half addrspace(5)* byval %in, half %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds half, half addrspace(5)* %in, i64 2045
|
||||
|
|
@ -332,13 +337,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg_nooff:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_load_short_d16_hi v0, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX9: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900: buffer_load_short_d16_hi v0, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX900: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_ushort v{{[0-9]+}}, off, s[0:3], s4 offset:4094{{$}}
|
||||
; NO-D16-HI: buffer_load_ushort v{{[0-9]+}}, off, s[0:3], s4 offset:4094{{$}}
|
||||
define void @load_private_hi_v2i16_reglo_vreg_nooff(i16 addrspace(5)* byval %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load volatile i16, i16 addrspace(5)* inttoptr (i32 4094 to i16 addrspace(5)*)
|
||||
|
|
@ -350,13 +355,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2f16_reglo_vreg_nooff:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: buffer_load_short_d16_hi v1, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: buffer_load_short_d16_hi v1, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_ushort v{{[0-9]+}}, off, s[0:3], s4 offset:4094{{$}}
|
||||
; NO-D16-HI: buffer_load_ushort v{{[0-9]+}}, off, s[0:3], s4 offset:4094{{$}}
|
||||
define void @load_private_hi_v2f16_reglo_vreg_nooff(half addrspace(5)* %in, half %reg) #0 {
|
||||
entry:
|
||||
%load = load volatile half, half addrspace(5)* inttoptr (i32 4094 to half addrspace(5)*)
|
||||
|
|
@ -368,13 +373,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg_zexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_load_ubyte_d16_hi v0, off, s[0:3], s5 offset:4095{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900: buffer_load_ubyte_d16_hi v0, off, s[0:3], s5 offset:4095{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_ubyte v{{[0-9]+}}, off, s[0:3], s5 offset:4095{{$}}
|
||||
; NO-D16-HI: buffer_load_ubyte v{{[0-9]+}}, off, s[0:3], s5 offset:4095{{$}}
|
||||
define void @load_private_hi_v2i16_reglo_vreg_zexti8(i8 addrspace(5)* byval %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i8, i8 addrspace(5)* %in, i64 4091
|
||||
|
|
@ -388,13 +393,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg_sexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_load_sbyte_d16_hi v0, off, s[0:3], s5 offset:4095{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900: buffer_load_sbyte_d16_hi v0, off, s[0:3], s5 offset:4095{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_sbyte v{{[0-9]+}}, off, s[0:3], s5 offset:4095{{$}}
|
||||
; NO-D16-HI: buffer_load_sbyte v{{[0-9]+}}, off, s[0:3], s5 offset:4095{{$}}
|
||||
define void @load_private_hi_v2i16_reglo_vreg_sexti8(i8 addrspace(5)* byval %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i8, i8 addrspace(5)* %in, i64 4091
|
||||
|
|
@ -408,13 +413,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg_nooff_zexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: buffer_load_ubyte_d16_hi v1, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: buffer_load_ubyte_d16_hi v1, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_ubyte v0, off, s[0:3], s4 offset:4094{{$}}
|
||||
; NO-D16-HI: buffer_load_ubyte v0, off, s[0:3], s4 offset:4094{{$}}
|
||||
define void @load_private_hi_v2i16_reglo_vreg_nooff_zexti8(i8 addrspace(5)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load volatile i8, i8 addrspace(5)* inttoptr (i32 4094 to i8 addrspace(5)*)
|
||||
|
|
@ -427,13 +432,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg_nooff_sexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: buffer_load_sbyte_d16_hi v1, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: buffer_load_sbyte_d16_hi v1, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_sbyte v0, off, s[0:3], s4 offset:4094{{$}}
|
||||
; NO-D16-HI: buffer_load_sbyte v0, off, s[0:3], s4 offset:4094{{$}}
|
||||
define void @load_private_hi_v2i16_reglo_vreg_nooff_sexti8(i8 addrspace(5)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%load = load volatile i8, i8 addrspace(5)* inttoptr (i32 4094 to i8 addrspace(5)*)
|
||||
|
|
@ -446,13 +451,13 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2f16_reglo_vreg_nooff_zexti8:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: buffer_load_ubyte_d16_hi v1, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: buffer_load_ubyte_d16_hi v1, off, s[0:3], s4 offset:4094{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: buffer_load_ubyte v0, off, s[0:3], s4 offset:4094{{$}}
|
||||
; NO-D16-HI: buffer_load_ubyte v0, off, s[0:3], s4 offset:4094{{$}}
|
||||
define void @load_private_hi_v2f16_reglo_vreg_nooff_zexti8(i8 addrspace(5)* %in, half %reg) #0 {
|
||||
entry:
|
||||
%load = load volatile i8, i8 addrspace(5)* inttoptr (i32 4094 to i8 addrspace(5)*)
|
||||
|
|
@ -466,13 +471,14 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}load_constant_hi_v2i16_reglo_vreg:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_load_short_d16_hi v2, v[0:1], off offset:-4094
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: global_load_short_d16_hi v2, v[0:1], off offset:-4094
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: flat_load_ushort
|
||||
; GFX803: flat_load_ushort
|
||||
; GFX906: global_load_ushort
|
||||
define void @load_constant_hi_v2i16_reglo_vreg(i16 addrspace(4)* %in, i16 %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i16, i16 addrspace(4)* %in, i64 -2047
|
||||
|
|
@ -485,13 +491,14 @@ entry:
|
|||
|
||||
; GCN-LABEL: load_constant_hi_v2f16_reglo_vreg
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_load_short_d16_hi v2, v[0:1], off offset:-4094
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_store_dword
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: global_load_short_d16_hi v2, v[0:1], off offset:-4094
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_store_dword
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
|
||||
; VI: flat_load_ushort
|
||||
; GFX803: flat_load_ushort
|
||||
; GFX906: global_load_ushort
|
||||
define void @load_constant_hi_v2f16_reglo_vreg(half addrspace(4)* %in, half %reg) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds half, half addrspace(4)* %in, i64 -2047
|
||||
|
|
@ -506,8 +513,8 @@ entry:
|
|||
; to offset variant.
|
||||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg_to_offset:
|
||||
; GFX9: buffer_store_dword
|
||||
; GFX9-NEXT: buffer_load_short_d16_hi v{{[0-9]+}}, off, s[0:3], s5 offset:4094
|
||||
; GFX900: buffer_store_dword
|
||||
; GFX900-NEXT: buffer_load_short_d16_hi v{{[0-9]+}}, off, s[0:3], s5 offset:4094
|
||||
define void @load_private_hi_v2i16_reglo_vreg_to_offset(i16 %reg) #0 {
|
||||
entry:
|
||||
%obj0 = alloca [10 x i32], align 4, addrspace(5)
|
||||
|
|
@ -523,8 +530,8 @@ entry:
|
|||
}
|
||||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg_sexti8_to_offset:
|
||||
; GFX9: buffer_store_dword
|
||||
; GFX9-NEXT: buffer_load_sbyte_d16_hi v{{[0-9]+}}, off, s[0:3], s5 offset:4095
|
||||
; GFX900: buffer_store_dword
|
||||
; GFX900-NEXT: buffer_load_sbyte_d16_hi v{{[0-9]+}}, off, s[0:3], s5 offset:4095
|
||||
define void @load_private_hi_v2i16_reglo_vreg_sexti8_to_offset(i16 %reg) #0 {
|
||||
entry:
|
||||
%obj0 = alloca [10 x i32], align 4, addrspace(5)
|
||||
|
|
@ -541,8 +548,8 @@ entry:
|
|||
}
|
||||
|
||||
; GCN-LABEL: {{^}}load_private_hi_v2i16_reglo_vreg_zexti8_to_offset:
|
||||
; GFX9: buffer_store_dword
|
||||
; GFX9-NEXT: buffer_load_ubyte_d16_hi v{{[0-9]+}}, off, s[0:3], s5 offset:4095
|
||||
; GFX900: buffer_store_dword
|
||||
; GFX900-NEXT: buffer_load_ubyte_d16_hi v{{[0-9]+}}, off, s[0:3], s5 offset:4095
|
||||
define void @load_private_hi_v2i16_reglo_vreg_zexti8_to_offset(i16 %reg) #0 {
|
||||
entry:
|
||||
%obj0 = alloca [10 x i32], align 4, addrspace(5)
|
||||
|
|
@ -562,12 +569,12 @@ entry:
|
|||
; FIXME: Is there a cost to using the extload over not?
|
||||
; GCN-LABEL: {{^}}load_local_v2i16_split:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_u16 v1, v0
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: ds_read_u16_d16_hi v1, v0 offset:2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: ds_read_u16 v1, v0
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: ds_read_u16_d16_hi v1, v0 offset:2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: v_mov_b32_e32 v0, v1
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define <2 x i16> @load_local_v2i16_split(i16 addrspace(3)* %in) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i16, i16 addrspace(3)* %in, i32 1
|
||||
|
|
@ -581,12 +588,12 @@ entry:
|
|||
; FIXME: Remove waitcnt between reads
|
||||
; GCN-LABEL: {{^}}load_global_v2i16_split:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_load_ushort v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_load_short_d16_hi v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: global_load_ushort v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_load_short_d16_hi v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define <2 x i16> @load_global_v2i16_split(i16 addrspace(1)* %in) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 1
|
||||
|
|
@ -600,12 +607,12 @@ entry:
|
|||
; FIXME: Remove waitcnt between reads
|
||||
; GCN-LABEL: {{^}}load_flat_v2i16_split:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: flat_load_ushort v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: flat_load_short_d16_hi v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: flat_load_ushort v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: flat_load_short_d16_hi v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define <2 x i16> @load_flat_v2i16_split(i16* %in) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i16, i16* %in, i64 1
|
||||
|
|
@ -619,12 +626,12 @@ entry:
|
|||
; FIXME: Remove waitcnt between reads
|
||||
; GCN-LABEL: {{^}}load_constant_v2i16_split:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_load_ushort v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: global_load_short_d16_hi v2
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900-NEXT: global_load_ushort v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: global_load_short_d16_hi v2
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define <2 x i16> @load_constant_v2i16_split(i16 addrspace(4)* %in) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i16, i16 addrspace(4)* %in, i64 1
|
||||
|
|
@ -639,11 +646,11 @@ entry:
|
|||
; FIXME: Is there a cost to using the extload over not?
|
||||
; GCN-LABEL: {{^}}load_private_v2i16_split:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_load_ushort v0, off, s[0:3], s5 offset:4{{$}}
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: buffer_load_short_d16_hi v0, off, s[0:3], s5 offset:6
|
||||
; GFX9-NEXT: s_waitcnt
|
||||
; GFX9-NEXT: s_setpc_b64
|
||||
; GFX900: buffer_load_ushort v0, off, s[0:3], s5 offset:4{{$}}
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: buffer_load_short_d16_hi v0, off, s[0:3], s5 offset:6
|
||||
; GFX900-NEXT: s_waitcnt
|
||||
; GFX900-NEXT: s_setpc_b64
|
||||
define <2 x i16> @load_private_v2i16_split(i16 addrspace(5)* byval %in) #0 {
|
||||
entry:
|
||||
%gep = getelementptr inbounds i16, i16 addrspace(5)* %in, i32 1
|
||||
|
|
|
|||
|
|
@ -1,13 +1,15 @@
|
|||
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9 %s
|
||||
; RUN: llc -march=amdgcn -mcpu=fiji -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI %s
|
||||
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX900 %s
|
||||
; RUN: llc -march=amdgcn -mcpu=gfx906 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX906,NO-D16-HI %s
|
||||
; RUN: llc -march=amdgcn -mcpu=fiji -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX803,NO-D16-HI %s
|
||||
|
||||
; GCN-LABEL: {{^}}store_global_hi_v2i16:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: global_store_short_d16_hi v[0:1], v2, off
|
||||
; GFX900-NEXT: global_store_short_d16_hi v[0:1], v2, off
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_short v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-NEXT: flat_store_short v[0:1], v2
|
||||
; GFX906-NEXT: global_store_short v[0:1], v2, off
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -23,10 +25,11 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_global_hi_v2f16:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: global_store_short_d16_hi v[0:1], v2, off
|
||||
; GFX900-NEXT: global_store_short_d16_hi v[0:1], v2, off
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_short v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-NEXT: flat_store_short v[0:1], v2
|
||||
; GFX906-NEXT: global_store_short v[0:1], v2, off
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -42,10 +45,11 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_global_hi_i32_shift:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: global_store_short_d16_hi v[0:1], v2, off
|
||||
; GFX900-NEXT: global_store_short_d16_hi v[0:1], v2, off
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_short v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-NEXT: flat_store_short v[0:1], v2
|
||||
; GFX906-NEXT: global_store_short v[0:1], v2, off
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -60,10 +64,11 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_global_hi_v2i16_i8:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: global_store_byte_d16_hi v[0:1], v2, off
|
||||
; GFX900-NEXT: global_store_byte_d16_hi v[0:1], v2, off
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_byte v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-NEXT: flat_store_byte v[0:1], v2
|
||||
; GFX906-NEXT: global_store_byte v[0:1], v2, off
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -79,10 +84,11 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_global_hi_i8_shift:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: global_store_byte_d16_hi v[0:1], v2, off
|
||||
; GFX900-NEXT: global_store_byte_d16_hi v[0:1], v2, off
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_byte v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-NEXT: flat_store_byte v[0:1], v2
|
||||
; GFX906-NEXT: global_store_byte v[0:1], v2, off
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -96,13 +102,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_global_hi_v2i16_max_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_store_short_d16_hi v[0:1], v2, off offset:4094
|
||||
; GFX900-NEXT: global_store_short_d16_hi v[0:1], v2, off offset:4094
|
||||
|
||||
; VI-DAG: v_add_u32_e32
|
||||
; VI-DAG: v_addc_u32_e32
|
||||
; VI-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-DAG: v_add_u32_e32
|
||||
; GFX803-DAG: v_addc_u32_e32
|
||||
; GFX803-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803: flat_store_short v[0:1], v2{{$}}
|
||||
|
||||
; GFX906-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX906-NEXT: global_store_short v[0:1], v2, off
|
||||
|
||||
; VI: flat_store_short v[0:1], v2{{$}}
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
define void @store_global_hi_v2i16_max_offset(i16 addrspace(1)* %out, i32 %arg) #0 {
|
||||
|
|
@ -117,13 +126,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_global_hi_v2i16_min_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_store_short_d16_hi v[0:1], v2, off offset:-4096{{$}}
|
||||
; GFX900-NEXT: global_store_short_d16_hi v[0:1], v2, off offset:-4096{{$}}
|
||||
|
||||
; VI-DAG: v_add_u32_e32
|
||||
; VI-DAG: v_addc_u32_e32
|
||||
; VI-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-DAG: v_add_u32_e32
|
||||
; GFX803-DAG: v_addc_u32_e32
|
||||
; GFX803-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803: flat_store_short v[0:1], v{{[0-9]$}}
|
||||
|
||||
; GFX906-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX906-NEXT: global_store_short v[0:1], v2, off
|
||||
|
||||
; VI: flat_store_short v[0:1], v{{[0-9]$}}
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
define void @store_global_hi_v2i16_min_offset(i16 addrspace(1)* %out, i32 %arg) #0 {
|
||||
|
|
@ -137,12 +149,15 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_global_hi_v2i16_i8_max_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_store_byte_d16_hi v[0:1], v2, off offset:4095
|
||||
; GFX900-NEXT: global_store_byte_d16_hi v[0:1], v2, off offset:4095
|
||||
|
||||
; VI-DAG: v_add_u32_e32
|
||||
; VI-DAG: v_addc_u32_e32
|
||||
; VI-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI: flat_store_byte v[0:1], v{{[0-9]$}}
|
||||
; GFX803-DAG: v_add_u32_e32
|
||||
; GFX803-DAG: v_addc_u32_e32
|
||||
; GFX803-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803: flat_store_byte v[0:1], v{{[0-9]$}}
|
||||
|
||||
; GFX906-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX906-NEXT: global_store_byte v[0:1], v2, off
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -158,13 +173,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_global_hi_v2i16_i8_min_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: global_store_byte_d16_hi v[0:1], v2, off offset:-4095
|
||||
; GFX900-NEXT: global_store_byte_d16_hi v[0:1], v2, off offset:-4095
|
||||
|
||||
; VI-DAG: v_add_u32_e32
|
||||
; VI-DAG: v_addc_u32_e32
|
||||
; VI-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-DAG: v_add_u32_e32
|
||||
; GFX803-DAG: v_addc_u32_e32
|
||||
; GFX803-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803: flat_store_byte v[0:1], v{{[0-9]$}}
|
||||
|
||||
; GFX906-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX906-NEXT: global_store_byte v[0:1], v2, off
|
||||
|
||||
; VI: flat_store_byte v[0:1], v{{[0-9]$}}
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
define void @store_global_hi_v2i16_i8_min_offset(i8 addrspace(1)* %out, i32 %arg) #0 {
|
||||
|
|
@ -180,10 +198,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_flat_hi_v2i16:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: flat_store_short_d16_hi v[0:1], v2{{$}}
|
||||
; GFX900-NEXT: flat_store_short_d16_hi v[0:1], v2{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_short v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; NO-D16-HI-NEXT: flat_store_short v[0:1], v2
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -198,10 +216,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_flat_hi_v2f16:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: flat_store_short_d16_hi v[0:1], v2{{$}}
|
||||
; GFX900-NEXT: flat_store_short_d16_hi v[0:1], v2{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_short v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; NO-D16-HI-NEXT: flat_store_short v[0:1], v2
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -216,10 +234,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_flat_hi_i32_shift:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: flat_store_short_d16_hi v[0:1], v2{{$}}
|
||||
; GFX900-NEXT: flat_store_short_d16_hi v[0:1], v2{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_short v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; NO-D16-HI-NEXT: flat_store_short v[0:1], v2
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -234,10 +252,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_flat_hi_v2i16_i8:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: flat_store_byte_d16_hi v[0:1], v2{{$}}
|
||||
; GFX900-NEXT: flat_store_byte_d16_hi v[0:1], v2{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_byte v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; NO-D16-HI-NEXT: flat_store_byte v[0:1], v2
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -253,10 +271,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_flat_hi_i8_shift:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: flat_store_byte_d16_hi v[0:1], v2{{$}}
|
||||
; GFX900-NEXT: flat_store_byte_d16_hi v[0:1], v2{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-NEXT: flat_store_byte v[0:1], v2
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; NO-D16-HI-NEXT: flat_store_byte v[0:1], v2
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -270,12 +288,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_flat_hi_v2i16_max_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: flat_store_short_d16_hi v[0:1], v2 offset:4094{{$}}
|
||||
; GFX900-NEXT: flat_store_short_d16_hi v[0:1], v2 offset:4094{{$}}
|
||||
|
||||
; GFX906-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX906-NEXT: flat_store_short v[0:1], v2 offset:4094
|
||||
|
||||
; GFX803-DAG: v_add_u32_e32
|
||||
; GFX803-DAG: v_addc_u32_e32
|
||||
; GFX803-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803: flat_store_short v[0:1], v2{{$}}
|
||||
|
||||
; VI-DAG: v_add_u32_e32
|
||||
; VI-DAG: v_addc_u32_e32
|
||||
; VI-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI: flat_store_short v[0:1], v2{{$}}
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
define void @store_flat_hi_v2i16_max_offset(i16* %out, i32 %arg) #0 {
|
||||
|
|
@ -290,11 +312,16 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_flat_hi_v2i16_neg_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GCN: v_add{{(_co)?}}_{{i|u}}32_e32
|
||||
; VI: v_addc_u32_e32
|
||||
; GFX9: v_addc_co_u32_e32
|
||||
|
||||
; GFX9-NEXT: flat_store_short_d16_hi v[0:1], v2{{$}}
|
||||
; VI: flat_store_short v[0:1], v2{{$}}
|
||||
; GFX803: v_addc_u32_e32
|
||||
; GFX900: v_addc_co_u32_e32
|
||||
|
||||
; GFX906-NEXT: v_lshrrev_b32_e32
|
||||
; GFX906-NEXT: v_addc_co_u32_e32
|
||||
; GFX906: flat_store_short v[0:1], v2
|
||||
|
||||
; GFX900-NEXT: flat_store_short_d16_hi v[0:1], v2{{$}}
|
||||
; GFX803: flat_store_short v[0:1], v2{{$}}
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
define void @store_flat_hi_v2i16_neg_offset(i16* %out, i32 %arg) #0 {
|
||||
|
|
@ -308,12 +335,16 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_flat_hi_v2i16_i8_max_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: flat_store_byte_d16_hi v[0:1], v2 offset:4095{{$}}
|
||||
; GFX900-NEXT: flat_store_byte_d16_hi v[0:1], v2 offset:4095{{$}}
|
||||
|
||||
; GFX803-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803-DAG: v_add_u32_e32
|
||||
; GFX803-DAG: v_addc_u32_e32
|
||||
; GFX803: flat_store_byte v[0:1], v2{{$}}
|
||||
|
||||
; GFX906-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX906-NEXT: flat_store_byte v[0:1], v2 offset:4095{{$}}
|
||||
|
||||
; VI-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI-DAG: v_add_u32_e32
|
||||
; VI-DAG: v_addc_u32_e32
|
||||
; VI: flat_store_byte v[0:1], v2{{$}}
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
define void @store_flat_hi_v2i16_i8_max_offset(i8* %out, i32 %arg) #0 {
|
||||
|
|
@ -329,12 +360,20 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_flat_hi_v2i16_i8_neg_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GCN-DAG: v_add{{(_co)?}}_{{i|u}}32_e32
|
||||
; VI-DAG: v_addc_u32_e32
|
||||
; GFX9-DAG: v_addc_co_u32_e32
|
||||
|
||||
; GFX9-NEXT: flat_store_byte_d16_hi v[0:1], v2{{$}}
|
||||
; VI-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; VI: flat_store_byte v[0:1], v2{{$}}
|
||||
; GFX803-DAG: v_addc_u32_e32
|
||||
; GFX900-DAG: v_addc_co_u32_e32
|
||||
; GFX906-DAG: v_add_co_u32_e32
|
||||
|
||||
; GFX900-NEXT: flat_store_byte_d16_hi v[0:1], v2{{$}}
|
||||
|
||||
; GFX906-NEXT: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX906-NEXT: v_addc_co_u32_e32
|
||||
; GFX906-NEXT: flat_store_byte v[0:1], v2{{$}}
|
||||
|
||||
; GFX803-DAG: v_lshrrev_b32_e32 v2, 16, v2
|
||||
; GFX803: flat_store_byte v[0:1], v2{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
define void @store_flat_hi_v2i16_i8_neg_offset(i8* %out, i32 %arg) #0 {
|
||||
|
|
@ -350,10 +389,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_private_hi_v2i16:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: buffer_store_short_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
; GFX900-NEXT: buffer_store_short_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI: buffer_store_short v1, v0, s[0:3], s4 offen{{$}}
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI: buffer_store_short v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -369,10 +408,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_private_hi_v2f16:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: buffer_store_short_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
; GFX900-NEXT: buffer_store_short_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI: buffer_store_short v1, v0, s[0:3], s4 offen{{$}}
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI: buffer_store_short v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -388,10 +427,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_private_hi_i32_shift:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: buffer_store_short_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
; GFX900-NEXT: buffer_store_short_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI-NEXT: buffer_store_short v1, v0, s[0:3], s4 offen{{$}}
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI-NEXT: buffer_store_short v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -406,10 +445,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_private_hi_v2i16_i8:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: buffer_store_byte_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
; GFX900-NEXT: buffer_store_byte_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI-NEXT: buffer_store_byte v1, v0, s[0:3], s4 offen{{$}}
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI-NEXT: buffer_store_byte v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -425,10 +464,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_private_hi_i8_shift:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: buffer_store_byte_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
; GFX900-NEXT: buffer_store_byte_d16_hi v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI-NEXT: buffer_store_byte v1, v0, s[0:3], s4 offen{{$}}
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI-NEXT: buffer_store_byte v1, v0, s[0:3], s4 offen{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -442,10 +481,10 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_private_hi_v2i16_max_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_store_short_d16_hi v0, off, s[0:3], s5 offset:4094{{$}}
|
||||
; GFX900: buffer_store_short_d16_hi v0, off, s[0:3], s5 offset:4094{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v0, 16, v0
|
||||
; VI-NEXT: buffer_store_short v0, off, s[0:3], s5 offset:4094{{$}}
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v0, 16, v0
|
||||
; NO-D16-HI-NEXT: buffer_store_short v0, off, s[0:3], s5 offset:4094{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -463,10 +502,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_private_hi_v2i16_nooff:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: buffer_store_short_d16_hi v0, off, s[0:3], s4{{$}}
|
||||
; GFX900-NEXT: buffer_store_short_d16_hi v0, off, s[0:3], s4{{$}}
|
||||
|
||||
; VI-NEXT: v_lshrrev_b32_e32 v0, 16, v0
|
||||
; VI-NEXT: buffer_store_short v0, off, s[0:3], s4{{$}}
|
||||
; NO-D16-HI-NEXT: v_lshrrev_b32_e32 v0, 16, v0
|
||||
; NO-D16-HI-NEXT: buffer_store_short v0, off, s[0:3], s4{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -483,10 +522,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_private_hi_v2i16_i8_nooff:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: buffer_store_byte_d16_hi v0, off, s[0:3], s4{{$}}
|
||||
; GFX900-NEXT: buffer_store_byte_d16_hi v0, off, s[0:3], s4{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v0, 16, v0
|
||||
; VI: buffer_store_byte v0, off, s[0:3], s4{{$}}
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v0, 16, v0
|
||||
; NO-D16-HI: buffer_store_byte v0, off, s[0:3], s4{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -502,10 +541,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_local_hi_v2i16:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: ds_write_b16_d16_hi v0, v1{{$}}
|
||||
; GFX900-NEXT: ds_write_b16_d16_hi v0, v1{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI: ds_write_b16 v0, v1
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI: ds_write_b16 v0, v1
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -521,10 +560,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_local_hi_v2f16:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: ds_write_b16_d16_hi v0, v1{{$}}
|
||||
; GFX900-NEXT: ds_write_b16_d16_hi v0, v1{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI: ds_write_b16 v0, v1
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI: ds_write_b16 v0, v1
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -540,10 +579,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_local_hi_i32_shift:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: ds_write_b16_d16_hi v0, v1{{$}}
|
||||
; GFX900-NEXT: ds_write_b16_d16_hi v0, v1{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI: ds_write_b16 v0, v1
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI: ds_write_b16 v0, v1
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -558,10 +597,10 @@ entry:
|
|||
; GCN-LABEL: {{^}}store_local_hi_v2i16_i8:
|
||||
; GCN: s_waitcnt
|
||||
|
||||
; GFX9-NEXT: ds_write_b8_d16_hi v0, v1{{$}}
|
||||
; GFX900-NEXT: ds_write_b8_d16_hi v0, v1{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI: ds_write_b8 v0, v1
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI: ds_write_b8 v0, v1
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -576,10 +615,10 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_local_hi_v2i16_max_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9-NEXT: ds_write_b16_d16_hi v0, v1 offset:65534{{$}}
|
||||
; GFX900-NEXT: ds_write_b16_d16_hi v0, v1 offset:65534{{$}}
|
||||
|
||||
; VI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; VI: ds_write_b16 v0, v1 offset:65534{{$}}
|
||||
; NO-D16-HI: v_lshrrev_b32_e32 v1, 16, v1
|
||||
; NO-D16-HI: ds_write_b16 v0, v1 offset:65534{{$}}
|
||||
|
||||
; GCN-NEXT: s_waitcnt
|
||||
; GCN-NEXT: s_setpc_b64
|
||||
|
|
@ -595,8 +634,8 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_private_hi_v2i16_to_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_store_dword
|
||||
; GFX9-NEXT: buffer_store_short_d16_hi v0, off, s[0:3], s5 offset:4094
|
||||
; GFX900: buffer_store_dword
|
||||
; GFX900-NEXT: buffer_store_short_d16_hi v0, off, s[0:3], s5 offset:4094
|
||||
define void @store_private_hi_v2i16_to_offset(i32 %arg) #0 {
|
||||
entry:
|
||||
%obj0 = alloca [10 x i32], align 4, addrspace(5)
|
||||
|
|
@ -612,8 +651,8 @@ entry:
|
|||
|
||||
; GCN-LABEL: {{^}}store_private_hi_v2i16_i8_to_offset:
|
||||
; GCN: s_waitcnt
|
||||
; GFX9: buffer_store_dword
|
||||
; GFX9-NEXT: buffer_store_byte_d16_hi v0, off, s[0:3], s5 offset:4095
|
||||
; GFX900: buffer_store_dword
|
||||
; GFX900-NEXT: buffer_store_byte_d16_hi v0, off, s[0:3], s5 offset:4095
|
||||
define void @store_private_hi_v2i16_i8_to_offset(i32 %arg) #0 {
|
||||
entry:
|
||||
%obj0 = alloca [10 x i32], align 4, addrspace(5)
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s | FileCheck %s
|
||||
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -mattr=+d16-preserves-unused-bits -show-encoding %s | FileCheck %s
|
||||
|
||||
ds_add_u32 v1, v2 offset:65535
|
||||
// CHECK: [0xff,0xff,0x00,0xd8,0x01,0x02,0x00,0x00]
|
||||
|
|
|
|||
Loading…
Reference in New Issue