feat: add d4r inference engines and Windows parity tooling
Add native K/M/RR inference engines, HIP kernels, replay and validation harnesses, and Windows DLSS setup and runtime support. Include GPU profiling tools, build and packaging scripts, platform integration patches, and implementation documentation.
This commit is contained in:
ayo committed
1 parent
25493b3198
commit
7c5d3c9157
430 files changed
+76191
No files matched your search
@@ -0,0 +1,128 @@
|
||||
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
|
||||
index e619b186d..dd3e9d92b 100644
|
||||
--- a/llvm/include/llvm/BinaryFormat/ELF.h
|
||||
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
|
||||
@@ -856,7 +856,7 @@ enum : unsigned {
|
||||
EF_AMDGPU_MACH_AMDGCN_GFX11_GENERIC = 0x054,
|
||||
EF_AMDGPU_MACH_AMDGCN_GFX1152 = 0x055,
|
||||
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X56 = 0x056,
|
||||
- EF_AMDGPU_MACH_AMDGCN_RESERVED_0X57 = 0x057,
|
||||
+ EF_AMDGPU_MACH_AMDGCN_GFX1154 = 0x057,
|
||||
EF_AMDGPU_MACH_AMDGCN_GFX1153 = 0x058,
|
||||
EF_AMDGPU_MACH_AMDGCN_GFX12_GENERIC = 0x059,
|
||||
EF_AMDGPU_MACH_AMDGCN_GFX1251 = 0x05a,
|
||||
diff --git a/llvm/include/llvm/TargetParser/TargetParser.h b/llvm/include/llvm/TargetParser/TargetParser.h
|
||||
index aad985926..c0aaa465b 100644
|
||||
--- a/llvm/include/llvm/TargetParser/TargetParser.h
|
||||
+++ b/llvm/include/llvm/TargetParser/TargetParser.h
|
||||
@@ -109,6 +109,7 @@ enum GPUKind : uint32_t {
|
||||
GK_GFX1151,
|
||||
GK_GFX1152,
|
||||
GK_GFX1153,
|
||||
+ GK_GFX1154,
|
||||
|
||||
GK_GFX1200,
|
||||
GK_GFX1201,
|
||||
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
|
||||
index f9fda2346..70ddaae22 100644
|
||||
--- a/llvm/lib/Object/ELFObjectFile.cpp
|
||||
+++ b/llvm/lib/Object/ELFObjectFile.cpp
|
||||
@@ -591,6 +591,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
|
||||
return "gfx1152";
|
||||
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1153:
|
||||
return "gfx1153";
|
||||
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1154:
|
||||
+ return "gfx1154";
|
||||
|
||||
// AMDGCN GFX12.
|
||||
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1200:
|
||||
diff --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
|
||||
index d9cce1eb7..7936876f4 100644
|
||||
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
|
||||
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
|
||||
@@ -632,6 +632,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
|
||||
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1151, EF_AMDGPU_MACH);
|
||||
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1152, EF_AMDGPU_MACH);
|
||||
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1153, EF_AMDGPU_MACH);
|
||||
+ BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1154, EF_AMDGPU_MACH);
|
||||
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1200, EF_AMDGPU_MACH);
|
||||
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1201, EF_AMDGPU_MACH);
|
||||
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1250, EF_AMDGPU_MACH);
|
||||
diff --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
|
||||
index c6fb31f9c..5d21894a3 100644
|
||||
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
|
||||
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
|
||||
@@ -304,7 +304,12 @@ def : ProcessorModel<"gfx1153", GFX11SpeedModel,
|
||||
FeatureISAVersion11_5_3.Features
|
||||
>;
|
||||
|
||||
-// [gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx1153]
|
||||
+// Backported from LLVM 7a0829e41228: actual gfx1154 features and identity.
|
||||
+def : ProcessorModel<"gfx1154", GFX11SpeedModel,
|
||||
+ FeatureISAVersion11_5_Common.Features
|
||||
+>;
|
||||
+
|
||||
+// [gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx1153, gfx1154]
|
||||
def : ProcessorModel<"gfx11-generic", GFX11SpeedModel,
|
||||
FeatureISAVersion11_Generic.Features
|
||||
>;
|
||||
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
|
||||
index 5a0857322..c506fc308 100644
|
||||
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
|
||||
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
|
||||
@@ -114,6 +114,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
|
||||
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1151: AK = GK_GFX1151; break;
|
||||
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1152: AK = GK_GFX1152; break;
|
||||
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1153: AK = GK_GFX1153; break;
|
||||
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1154: AK = GK_GFX1154; break;
|
||||
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1200: AK = GK_GFX1200; break;
|
||||
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1201: AK = GK_GFX1201; break;
|
||||
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1250: AK = GK_GFX1250; break;
|
||||
@@ -201,6 +202,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
|
||||
case GK_GFX1151: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1151;
|
||||
case GK_GFX1152: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1152;
|
||||
case GK_GFX1153: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1153;
|
||||
+ case GK_GFX1154: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1154;
|
||||
case GK_GFX1200: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1200;
|
||||
case GK_GFX1201: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1201;
|
||||
case GK_GFX1250: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1250;
|
||||
diff --git a/llvm/lib/TargetParser/TargetParser.cpp b/llvm/lib/TargetParser/TargetParser.cpp
|
||||
index 34b09b14b..39acbb942 100644
|
||||
--- a/llvm/lib/TargetParser/TargetParser.cpp
|
||||
+++ b/llvm/lib/TargetParser/TargetParser.cpp
|
||||
@@ -172,6 +172,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
|
||||
{{"gfx1151"}, {"gfx1151"}, GK_GFX1151, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
|
||||
{{"gfx1152"}, {"gfx1152"}, GK_GFX1152, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
|
||||
{{"gfx1153"}, {"gfx1153"}, GK_GFX1153, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
|
||||
+ {{"gfx1154"}, {"gfx1154"}, GK_GFX1154, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
|
||||
{{"gfx1200"}, {"gfx1200"}, GK_GFX1200, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
|
||||
{{"gfx1201"}, {"gfx1201"}, GK_GFX1201, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
|
||||
{{"gfx1250"}, {"gfx1250"}, GK_GFX1250, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
|
||||
@@ -328,6 +329,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
|
||||
case GK_GFX1151: return {11, 5, 1};
|
||||
case GK_GFX1152: return {11, 5, 2};
|
||||
case GK_GFX1153: return {11, 5, 3};
|
||||
+ case GK_GFX1154: return {11, 5, 4};
|
||||
case GK_GFX1200: return {12, 0, 0};
|
||||
case GK_GFX1201: return {12, 0, 1};
|
||||
case GK_GFX1250: return {12, 5, 0};
|
||||
@@ -475,6 +477,7 @@ static void fillAMDGCNFeatureMap(StringRef GPU, const Triple &T,
|
||||
Features["atomic-fmin-fmax-global-f32"] = true;
|
||||
break;
|
||||
case GK_GFX1153:
|
||||
+ case GK_GFX1154:
|
||||
case GK_GFX1152:
|
||||
case GK_GFX1151:
|
||||
case GK_GFX1150:
|
||||
diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
|
||||
index ab9331690..0ade2d412 100644
|
||||
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
|
||||
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
|
||||
@@ -1655,6 +1655,7 @@ const EnumEntry<unsigned> ElfHeaderMipsFlags[] = {
|
||||
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1151, "gfx1151"), \
|
||||
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1152, "gfx1152"), \
|
||||
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1153, "gfx1153"), \
|
||||
+ ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1154, "gfx1154"), \
|
||||
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1200, "gfx1200"), \
|
||||
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1201, "gfx1201"), \
|
||||
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1250, "gfx1250"), \
|
||||
@@ -0,0 +1,24 @@
|
||||
# LLVM source patches for the Windows compiler
|
||||
|
||||
Base: ZLUDA's LLVM submodule `ff4dc1f7c9e1c64d4d69e40f4ed30c2280a96dfd`
|
||||
(LLVM 22). `build-zluda-llvm.ps1` applies these patches idempotently before
|
||||
building. ZLUDA's parent source patches remain in `patches/zluda`.
|
||||
|
||||
`0001-backport-gfx1154.patch` adapts official LLVM
|
||||
[`7a0829e41228`](https://github.com/llvm/llvm-project/commit/7a0829e41228513299c5108685b0bc127463c6a1)
|
||||
to the older parser/ELF structures. It adds actual gfx1154 processor features,
|
||||
ISA 11.5.4, parser identity and ELF machine 0x57. It does not map gfx1154 onto
|
||||
another CPU, patch binary headers or alter existing processors' features.
|
||||
LLVM's gfx1154 uses `FeatureISAVersion11_5_Common` and the GFX11 speed model.
|
||||
LLVM code remains Apache-2.0 WITH LLVM-exception (see the dependency license).
|
||||
|
||||
The prior offline compiler aborts on a public PTX pattern for gfx1154 with
|
||||
unrecognized-processor diagnostics and exit `0xC0000409`. After rebuilding
|
||||
LLVM, rebuild/relink ZLUDA and its offline emitter; changing native Clang
|
||||
objects alone cannot fix the translated PTX path. Run
|
||||
`scripts/windows/test-zluda-target-compilation.ps1` to compile the public
|
||||
Driver API pattern and FP16 MMA fixtures (strict/reference and WMMA modes)
|
||||
for every target without GPU work. All 33 compilations pass with correct ELF
|
||||
targets and wave32. Strict gfx12 F16 reference retains its prior FP64 helper;
|
||||
WMMA mode here is a compilation check, not a default arithmetic change.
|
||||
This checks code generation and ELF identity, not hardware execution/numerics.
|
||||
Reference in new issue
Block a user