Skip to content

AMDGPU: Define a feature for v_dot4_f32_* instructions #84248

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 6, 2024
Merged

AMDGPU: Define a feature for v_dot4_f32_* instructions #84248

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions clang/include/clang/Basic/BuiltinsAMDGPU.def
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,10 +256,10 @@ TARGET_BUILTIN(__builtin_amdgcn_sudot4, "iIbiIbiiIb", "nc", "dot8-insts")
TARGET_BUILTIN(__builtin_amdgcn_sdot8, "SiSiSiSiIb", "nc", "dot1-insts")
TARGET_BUILTIN(__builtin_amdgcn_udot8, "UiUiUiUiIb", "nc", "dot7-insts")
TARGET_BUILTIN(__builtin_amdgcn_sudot8, "iIbiIbiiIb", "nc", "dot8-insts")
TARGET_BUILTIN(__builtin_amdgcn_dot4_f32_fp8_bf8, "fUiUif", "nc", "gfx12-insts")
TARGET_BUILTIN(__builtin_amdgcn_dot4_f32_bf8_fp8, "fUiUif", "nc", "gfx12-insts")
TARGET_BUILTIN(__builtin_amdgcn_dot4_f32_fp8_fp8, "fUiUif", "nc", "gfx12-insts")
TARGET_BUILTIN(__builtin_amdgcn_dot4_f32_bf8_bf8, "fUiUif", "nc", "gfx12-insts")
TARGET_BUILTIN(__builtin_amdgcn_dot4_f32_fp8_bf8, "fUiUif", "nc", "dot11-insts")
TARGET_BUILTIN(__builtin_amdgcn_dot4_f32_bf8_fp8, "fUiUif", "nc", "dot11-insts")
TARGET_BUILTIN(__builtin_amdgcn_dot4_f32_fp8_fp8, "fUiUif", "nc", "dot11-insts")
TARGET_BUILTIN(__builtin_amdgcn_dot4_f32_bf8_bf8, "fUiUif", "nc", "dot11-insts")

//===----------------------------------------------------------------------===//
// GFX10+ only builtins.
Expand Down
4 changes: 2 additions & 2 deletions clang/test/CodeGenOpenCL/amdgpu-features.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,8 +100,8 @@
// GFX1103: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1150: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1151: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1201: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1201: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"

// GFX1103-W64: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize64"

Expand Down
8 changes: 4 additions & 4 deletions clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,8 +50,8 @@ kernel void builtins_amdgcn_dl_insts_err(
iOut[3] = __builtin_amdgcn_sudot8(false, A, true, B, C, false); // expected-error {{'__builtin_amdgcn_sudot8' needs target feature dot8-insts}}
iOut[4] = __builtin_amdgcn_sudot8(true, A, false, B, C, true); // expected-error {{'__builtin_amdgcn_sudot8' needs target feature dot8-insts}}

fOut[5] = __builtin_amdgcn_dot4_f32_fp8_bf8(uiA, uiB, fC); // expected-error {{'__builtin_amdgcn_dot4_f32_fp8_bf8' needs target feature gfx12-insts}}
fOut[6] = __builtin_amdgcn_dot4_f32_bf8_fp8(uiA, uiB, fC); // expected-error {{'__builtin_amdgcn_dot4_f32_bf8_fp8' needs target feature gfx12-insts}}
fOut[7] = __builtin_amdgcn_dot4_f32_fp8_fp8(uiA, uiB, fC); // expected-error {{'__builtin_amdgcn_dot4_f32_fp8_fp8' needs target feature gfx12-insts}}
fOut[8] = __builtin_amdgcn_dot4_f32_bf8_bf8(uiA, uiB, fC); // expected-error {{'__builtin_amdgcn_dot4_f32_bf8_bf8' needs target feature gfx12-insts}}
fOut[5] = __builtin_amdgcn_dot4_f32_fp8_bf8(uiA, uiB, fC); // expected-error {{'__builtin_amdgcn_dot4_f32_fp8_bf8' needs target feature dot11-insts}}
fOut[6] = __builtin_amdgcn_dot4_f32_bf8_fp8(uiA, uiB, fC); // expected-error {{'__builtin_amdgcn_dot4_f32_bf8_fp8' needs target feature dot11-insts}}
fOut[7] = __builtin_amdgcn_dot4_f32_fp8_fp8(uiA, uiB, fC); // expected-error {{'__builtin_amdgcn_dot4_f32_fp8_fp8' needs target feature dot11-insts}}
fOut[8] = __builtin_amdgcn_dot4_f32_bf8_bf8(uiA, uiB, fC); // expected-error {{'__builtin_amdgcn_dot4_f32_bf8_bf8' needs target feature dot11-insts}}
}
10 changes: 10 additions & 0 deletions llvm/lib/Target/AMDGPU/AMDGPU.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -650,6 +650,12 @@ def FeatureDot10Insts : SubtargetFeature<"dot10-insts",
"Has v_dot2_f32_f16 instruction"
>;

def FeatureDot11Insts : SubtargetFeature<"dot11-insts",
"HasDot11Insts",
"true",
"Has v_dot4_f32_fp8_fp8, v_dot4_f32_fp8_bf8, v_dot4_f32_bf8_fp8, v_dot4_f32_bf8_bf8 instructions"
>;

def FeatureMAIInsts : SubtargetFeature<"mai-insts",
"HasMAIInsts",
"true",
Expand Down Expand Up @@ -1521,6 +1527,7 @@ def FeatureISAVersion12 : FeatureSet<
FeatureDot8Insts,
FeatureDot9Insts,
FeatureDot10Insts,
FeatureDot11Insts,
FeatureNSAEncoding,
FeaturePartialNSAEncoding,
FeatureWavefrontSize32,
Expand Down Expand Up @@ -2029,6 +2036,9 @@ def HasDot9Insts : Predicate<"Subtarget->hasDot9Insts()">,
def HasDot10Insts : Predicate<"Subtarget->hasDot10Insts()">,
AssemblerPredicate<(all_of FeatureDot10Insts)>;

def HasDot11Insts : Predicate<"Subtarget->hasDot11Insts()">,
AssemblerPredicate<(all_of FeatureDot11Insts)>;

def HasGetWaveIdInst : Predicate<"Subtarget->hasGetWaveIdInst()">,
AssemblerPredicate<(all_of FeatureGetWaveIdInst)>;

Expand Down
5 changes: 5 additions & 0 deletions llvm/lib/Target/AMDGPU/GCNSubtarget.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,6 +153,7 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool HasDot8Insts = false;
bool HasDot9Insts = false;
bool HasDot10Insts = false;
bool HasDot11Insts = false;
bool HasMAIInsts = false;
bool HasFP8Insts = false;
bool HasFP8ConversionInsts = false;
Expand Down Expand Up @@ -793,6 +794,10 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
return HasDot10Insts;
}

bool hasDot11Insts() const {
return HasDot11Insts;
}

bool hasMAIInsts() const {
return HasMAIInsts;
}
Expand Down
2 changes: 2 additions & 0 deletions llvm/lib/Target/AMDGPU/VOP3PInstructions.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -480,10 +480,12 @@ multiclass VOP3PDOTF8Inst <string OpName, SDPatternOperator intrinsic_node> {
i32:$src2_modifiers, f32:$src2)>;
}

let OtherPredicates = [HasDot11Insts] in {
defm V_DOT4_F32_FP8_BF8 : VOP3PDOTF8Inst<"v_dot4_f32_fp8_bf8", int_amdgcn_dot4_f32_fp8_bf8>;
defm V_DOT4_F32_BF8_FP8 : VOP3PDOTF8Inst<"v_dot4_f32_bf8_fp8", int_amdgcn_dot4_f32_bf8_fp8>;
defm V_DOT4_F32_FP8_FP8 : VOP3PDOTF8Inst<"v_dot4_f32_fp8_fp8", int_amdgcn_dot4_f32_fp8_fp8>;
defm V_DOT4_F32_BF8_BF8 : VOP3PDOTF8Inst<"v_dot4_f32_bf8_bf8", int_amdgcn_dot4_f32_bf8_bf8>;
}

def : UDot2Pat<V_DOT2_U32_U16>;
def : SDot2Pat<V_DOT2_I32_I16>;
Expand Down
1 change: 1 addition & 0 deletions llvm/lib/TargetParser/TargetParser.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -318,6 +318,7 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
Features["dot8-insts"] = true;
Features["dot9-insts"] = true;
Features["dot10-insts"] = true;
Features["dot11-insts"] = true;
Features["dl-insts"] = true;
Features["atomic-ds-pk-add-16-insts"] = true;
Features["atomic-flat-pk-add-16-insts"] = true;
Expand Down