[AMDGPU] Introduce GFX9/10.1/10.3/11 Generic Targets (llvm#76955)

These generic targets include multiple GPUs and will, in the future,
provide a way to build once and run on multiple GPU, at the cost of less
optimization opportunities.

Note that this is just doing the compiler side of things, device libs an
runtimes/loader/etc. don't know about these targets yet, so none of them
actually work in practice right now. This is just the initial commit to
make LLVM aware of them.

This contains the documentation changes for both this change and llvm#76954
as well.

Change-Id: I0c99e616adddaae5e8ce4ad7283eabdbf64250c3

Author: Pierre-vh

clang/lib/Basic/Targets/AMDGPU.cpp

@@ -17,6 +17,7 @@
 #include "clang/Basic/LangOptions.h"
 #include "clang/Basic/MacroBuilder.h"
 #include "clang/Basic/TargetBuiltins.h"
+#include "llvm/ADT/SmallString.h"
 using namespace clang;
 using namespace clang::targets;
 
@@ -275,16 +276,25 @@ void AMDGPUTargetInfo::getTargetDefines(const LangOptions &Opts,
     Builder.defineMacro("__R600__");
 
   if (GPUKind != llvm::AMDGPU::GK_NONE) {
-    StringRef CanonName = isAMDGCN(getTriple()) ?
-      getArchNameAMDGCN(GPUKind) : getArchNameR600(GPUKind);
+
+    llvm::SmallString<16> CanonName =
+        (isAMDGCN(getTriple()) ? getArchNameAMDGCN(GPUKind)
+                              : getArchNameR600(GPUKind));
+
+    // Sanitize the name of generic targets.
+    // e.g. gfx10-1-generic -> gfx10_1_generic
+    if (GPUKind >= llvm::AMDGPU::GK_AMDGCN_GENERIC_FIRST &&
+        GPUKind <= llvm::AMDGPU::GK_AMDGCN_GENERIC_LAST) {
+      std::replace(CanonName.begin(), CanonName.end(), '.', '_');
+      std::replace(CanonName.begin(), CanonName.end(), '-', '_');
+    }
+
     Builder.defineMacro(Twine("__") + Twine(CanonName) + Twine("__"));
-    // Emit macros for gfx family e.g. gfx906 -> __GFX9__, gfx1030 -> __GFX10___
     if (isAMDGCN(getTriple())) {
-      assert(CanonName.starts_with("gfx") && "Invalid amdgcn canonical name");
-      Builder.defineMacro(Twine("__") + Twine(CanonName.drop_back(2).upper()) +
+      // Emit macros for gfx family e.g. gfx906 -> __GFX9__, gfx1030 -> __GFX10___
+      StringRef CanonFamilyName = getArchFamilyNameAMDGCN(GPUKind);
+      Builder.defineMacro(Twine("__") + Twine(CanonFamilyName.upper()) +
                           Twine("__"));
-    }
-    if (isAMDGCN(getTriple())) {
       Builder.defineMacro("__amdgcn_processor__",
                           Twine("\"") + Twine(CanonName) + Twine("\""));
       Builder.defineMacro("__amdgcn_target_id__",

clang/test/Driver/amdgpu-macros.cl

@@ -132,6 +132,11 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1200 -DFAMILY=GFX12
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1201 -DFAMILY=GFX12
 
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx9-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx9_generic -DFAMILY=GFX9
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx10.1-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx10_1_generic -DFAMILY=GFX10
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx10.3-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx10_3_generic -DFAMILY=GFX10
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx11-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx11_generic -DFAMILY=GFX11
+
 // ARCH-GCN-DAG: #define FP_FAST_FMA 1
 
 // FAST_FMAF-DAG: #define FP_FAST_FMAF 1

clang/test/Driver/amdgpu-mcpu.cl

@@ -116,6 +116,11 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefix=GFX1200 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefix=GFX1201 %s
 
+// RUN: %clang -### -target amdgcn -mcpu=gfx9-generic %s 2>&1 | FileCheck --check-prefix=GFX9_GENERIC %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx10.1-generic %s 2>&1 | FileCheck --check-prefix=GFX10_1_GENERIC %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx10.3-generic %s 2>&1 | FileCheck --check-prefix=GFX10_3_GENERIC %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx11-generic %s 2>&1 | FileCheck --check-prefix=GFX11_GENERIC %s
+
 // GCNDEFAULT-NOT: -target-cpu
 // GFX600:    "-target-cpu" "gfx600"
 // GFX601:    "-target-cpu" "gfx601"
@@ -162,3 +167,8 @@
 // GFX1152:   "-target-cpu" "gfx1152"
 // GFX1200:   "-target-cpu" "gfx1200"
 // GFX1201:   "-target-cpu" "gfx1201"
+
+// GFX9_GENERIC:      "-target-cpu" "gfx9-generic"
+// GFX10_1_GENERIC:   "-target-cpu" "gfx10.1-generic"
+// GFX10_3_GENERIC:   "-target-cpu" "gfx10.3-generic"
+// GFX11_GENERIC:     "-target-cpu" "gfx11-generic"

clang/test/Misc/target-invalid-cpu-note.c

@@ -37,7 +37,7 @@
 
 // RUN: not %clang_cc1 -triple amdgcn--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AMDGCN
 // AMDGCN: error: unknown target CPU 'not-a-cpu'
-// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx1200, gfx1201{{$}}
+// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx1200, gfx1201, gfx9-generic, gfx10.1-generic, gfx10.3-generic, gfx11-generic{{$}}
 
 // RUN: not %clang_cc1 -triple wasm64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix WEBASM
 // WEBASM: error: unknown target CPU 'not-a-cpu'