[CUDA] Add support for CUDA-12.6 and sm_100 #112028

Artem-B · 2024-10-11T17:48:59Z

This is a copy of #97402, which is now ready to land.

llvmbot · 2024-10-11T17:49:40Z

@llvm/pr-subscribers-clang-driver
@llvm/pr-subscribers-clang

@llvm/pr-subscribers-clang-codegen

Author: Artem Belevich (Artem-B)

Changes

This is a copy of #97402, which is now ready to land.

Patch is 25.62 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/112028.diff

9 Files Affected:

(modified) clang/docs/ReleaseNotes.rst (+2)
(modified) clang/include/clang/Basic/BuiltinsNVPTX.def (+8-2)
(modified) clang/include/clang/Basic/Cuda.h (+3-1)
(modified) clang/lib/Basic/Cuda.cpp (+4)
(modified) clang/lib/Basic/Targets/NVPTX.cpp (+2)
(modified) clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp (+1)
(modified) clang/lib/Driver/ToolChains/Cuda.cpp (+3)
(added) clang/test/Misc/target-invalid-cpu-note.c (+96)
(modified) llvm/lib/Target/NVPTX/NVPTX.td (+3-2)

diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index 763bc3ac159322..1722397452a80a 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -612,6 +612,8 @@ CUDA/HIP Language Changes
 
 CUDA Support
 ^^^^^^^^^^^^
+- Clang now supports CUDA SDK up to 12.6
+- Added support for sm_100
 
 AIX Support
 ^^^^^^^^^^^
diff --git a/clang/include/clang/Basic/BuiltinsNVPTX.def b/clang/include/clang/Basic/BuiltinsNVPTX.def
index 6b7bce5bc00d4f..969dd9e41ebfa3 100644
--- a/clang/include/clang/Basic/BuiltinsNVPTX.def
+++ b/clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -27,8 +27,10 @@
 #pragma push_macro("SM_89")
 #pragma push_macro("SM_90")
 #pragma push_macro("SM_90a")
+#pragma push_macro("SM_100")
+#define SM_100 "sm_100"
 #define SM_90a "sm_90a"
-#define SM_90 "sm_90|" SM_90a
+#define SM_90 "sm_90|" SM_90a "|" SM_100
 #define SM_89 "sm_89|" SM_90
 #define SM_87 "sm_87|" SM_89
 #define SM_86 "sm_86|" SM_87
@@ -63,7 +65,9 @@
 #pragma push_macro("PTX83")
 #pragma push_macro("PTX84")
 #pragma push_macro("PTX85")
-#define PTX85 "ptx85"
+#pragma push_macro("PTX86")
+#define PTX86 "ptx86"
+#define PTX85 "ptx85|" PTX86
 #define PTX84 "ptx84|" PTX85
 #define PTX83 "ptx83|" PTX84
 #define PTX82 "ptx82|" PTX83
@@ -1086,6 +1090,7 @@ TARGET_BUILTIN(__nvvm_getctarank_shared_cluster, "iv*3", "", AND(SM_90,PTX78))
 #pragma pop_macro("SM_89")
 #pragma pop_macro("SM_90")
 #pragma pop_macro("SM_90a")
+#pragma pop_macro("SM_100")
 #pragma pop_macro("PTX42")
 #pragma pop_macro("PTX60")
 #pragma pop_macro("PTX61")
@@ -1108,3 +1113,4 @@ TARGET_BUILTIN(__nvvm_getctarank_shared_cluster, "iv*3", "", AND(SM_90,PTX78))
 #pragma pop_macro("PTX83")
 #pragma pop_macro("PTX84")
 #pragma pop_macro("PTX85")
+#pragma pop_macro("PTX86")
diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index 83699f8897f663..a18e62620dd5d0 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -43,9 +43,10 @@ enum class CudaVersion {
   CUDA_123,
   CUDA_124,
   CUDA_125,
+  CUDA_126,
   FULLY_SUPPORTED = CUDA_123,
   PARTIALLY_SUPPORTED =
-      CUDA_125, // Partially supported. Proceed with a warning.
+      CUDA_126, // Partially supported. Proceed with a warning.
   NEW = 10000,  // Too new. Issue a warning, but allow using it.
 };
 const char *CudaVersionToString(CudaVersion V);
@@ -78,6 +79,7 @@ enum class OffloadArch {
   SM_89,
   SM_90,
   SM_90a,
+  SM_100,
   GFX600,
   GFX601,
   GFX602,
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index faf3878f064d20..72d9bd89c36e71 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -43,6 +43,7 @@ static const CudaVersionMapEntry CudaNameVersionMap[] = {
     CUDA_ENTRY(12, 3),
     CUDA_ENTRY(12, 4),
     CUDA_ENTRY(12, 5),
+    CUDA_ENTRY(12, 6),
     {"", CudaVersion::NEW, llvm::VersionTuple(std::numeric_limits<int>::max())},
     {"unknown", CudaVersion::UNKNOWN, {}} // End of list tombstone.
 };
@@ -96,6 +97,7 @@ static const OffloadArchToStringMap arch_names[] = {
     SM(89),                          // Ada Lovelace
     SM(90),                          // Hopper
     SM(90a),                         // Hopper
+    SM(100),                         // Blackwell
     GFX(600),  // gfx600
     GFX(601),  // gfx601
     GFX(602),  // gfx602
@@ -221,6 +223,8 @@ CudaVersion MinVersionForOffloadArch(OffloadArch A) {
     return CudaVersion::CUDA_118;
   case OffloadArch::SM_90a:
     return CudaVersion::CUDA_120;
+  case OffloadArch::SM_100:
+    return CudaVersion::CUDA_126;
   default:
     llvm_unreachable("invalid enum");
   }
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 43b653dc52ce0d..88a0dbde52d52b 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -281,6 +281,8 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case OffloadArch::SM_90:
       case OffloadArch::SM_90a:
         return "900";
+      case OffloadArch::SM_100:
+        return "1000";
       }
       llvm_unreachable("unhandled OffloadArch");
     }();
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index c920d93957b16e..35ff75416cb776 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -2274,6 +2274,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(const OMPRequiresDecl *D) {
       case OffloadArch::SM_89:
       case OffloadArch::SM_90:
       case OffloadArch::SM_90a:
+      case OffloadArch::SM_100:
       case OffloadArch::GFX600:
       case OffloadArch::GFX601:
       case OffloadArch::GFX602:
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index 7a70cf1c5694fd..c1beca840dde5b 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -87,6 +87,8 @@ CudaVersion getCudaVersion(uint32_t raw_version) {
     return CudaVersion::CUDA_124;
   if (raw_version < 12060)
     return CudaVersion::CUDA_125;
+  if (raw_version < 12070)
+    return CudaVersion::CUDA_126;
   return CudaVersion::NEW;
 }
 
@@ -669,6 +671,7 @@ void NVPTX::getNVPTXTargetFeatures(const Driver &D, const llvm::Triple &Triple,
   case CudaVersion::CUDA_##CUDA_VER:                                           \
     PtxFeature = "+ptx" #PTX_VER;                                              \
     break;
+    CASE_CUDA_VERSION(126, 86);
     CASE_CUDA_VERSION(125, 85);
     CASE_CUDA_VERSION(124, 84);
     CASE_CUDA_VERSION(123, 83);
diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
new file mode 100644
index 00000000000000..92b28c9a165209
--- /dev/null
+++ b/clang/test/Misc/target-invalid-cpu-note.c
@@ -0,0 +1,96 @@
+// Use CHECK-NEXT instead of multiple CHECK-SAME to ensure we will fail if there is anything extra in the output.
+// RUN: not %clang_cc1 -triple armv5--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix ARM
+// ARM: error: unknown target CPU 'not-a-cpu'
+// ARM-NEXT: note: valid target CPU values are: arm8, arm810, strongarm, strongarm110, strongarm1100, strongarm1110, arm7tdmi, arm7tdmi-s, arm710t, arm720t, arm9, arm9tdmi, arm920, arm920t, arm922t, arm940t, ep9312, arm10tdmi, arm1020t, arm9e, arm946e-s, arm966e-s, arm968e-s, arm10e, arm1020e, arm1022e, arm926ej-s, arm1136j-s, arm1136jf-s, mpcore, mpcorenovfp, arm1176jz-s, arm1176jzf-s, arm1156t2-s, arm1156t2f-s, cortex-m0, cortex-m0plus, cortex-m1, sc000, cortex-a5, cortex-a7, cortex-a8, cortex-a9, cortex-a12, cortex-a15, cortex-a17, krait, cortex-r4, cortex-r4f, cortex-r5, cortex-r7, cortex-r8, cortex-r52, cortex-r52plus, sc300, cortex-m3, cortex-m4, cortex-m7, cortex-m23, cortex-m33, cortex-m35p, cortex-m55, cortex-m85, cortex-m52, cortex-a32, cortex-a35, cortex-a53, cortex-a55, cortex-a57, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-a710, cortex-x1, cortex-x1c, neoverse-n1, neoverse-n2, neoverse-v1, cyclone, exynos-m3, exynos-m4, exynos-m5, kryo, iwmmxt, xscale, swift{{$}}
+
+// RUN: not %clang_cc1 -triple arm64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AARCH64
+// AARCH64: error: unknown target CPU 'not-a-cpu'
+// AARCH64-NEXT: note: valid target CPU values are: a64fx, ampere1, ampere1a, ampere1b, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-a7, apple-a8, apple-a9, apple-m1, apple-m2, apple-m3, apple-m4, apple-s4, apple-s5, carmel, cobalt-100, cortex-a34, cortex-a35, cortex-a510, cortex-a520, cortex-a520ae, cortex-a53, cortex-a55, cortex-a57, cortex-a65, cortex-a65ae, cortex-a710, cortex-a715, cortex-a72, cortex-a720, cortex-a720ae, cortex-a725, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-r82, cortex-r82ae, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, cortex-x925, cyclone, exynos-m3, exynos-m4, exynos-m5, falkor, generic, grace, kryo, neoverse-512tvb, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-n3, neoverse-v1, neoverse-v2, neoverse-v3, neoverse-v3ae, oryon-1, saphira, thunderx, thunderx2t99, thunderx3t110, thunderxt81, thunderxt83, thunderxt88, tsv110{{$}}
+
+// RUN: not %clang_cc1 -triple arm64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_AARCH64
+// TUNE_AARCH64: error: unknown target CPU 'not-a-cpu'
+// TUNE_AARCH64-NEXT: note: valid target CPU values are: a64fx, ampere1, ampere1a, ampere1b, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-a7, apple-a8, apple-a9, apple-m1, apple-m2, apple-m3, apple-m4, apple-s4, apple-s5, carmel, cobalt-100, cortex-a34, cortex-a35, cortex-a510, cortex-a520, cortex-a520ae, cortex-a53, cortex-a55, cortex-a57, cortex-a65, cortex-a65ae, cortex-a710, cortex-a715, cortex-a72, cortex-a720, cortex-a720ae, cortex-a725, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-r82, cortex-r82ae, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, cortex-x925, cyclone, exynos-m3, exynos-m4, exynos-m5, falkor, generic, grace, kryo, neoverse-512tvb, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-n3, neoverse-v1, neoverse-v2, neoverse-v3, neoverse-v3ae, oryon-1, saphira, thunderx, thunderx2t99, thunderx3t110, thunderxt81, thunderxt83, thunderxt88, tsv110{{$}}
+
+// RUN: not %clang_cc1 -triple i386--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86
+// X86: error: unknown target CPU 'not-a-cpu'
+// X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, pantherlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, clearwaterforest, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4, geode{{$}}
+
+// RUN: not %clang_cc1 -triple x86_64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86_64
+// X86_64: error: unknown target CPU 'not-a-cpu'
+// X86_64-NEXT: note: valid target CPU values are: nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, pantherlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, clearwaterforest, knl, knm, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4{{$}}
+
+// RUN: not %clang_cc1 -triple i386--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_X86
+// TUNE_X86: error: unknown target CPU 'not-a-cpu'
+// TUNE_X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, pantherlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, clearwaterforest, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
+
+// RUN: not %clang_cc1 -triple x86_64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_X86_64
+// TUNE_X86_64: error: unknown target CPU 'not-a-cpu'
+// TUNE_X86_64-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, pantherlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, clearwaterforest, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
+
+// RUN: not %clang_cc1 -triple nvptx--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix NVPTX
+// NVPTX: error: unknown target CPU 'not-a-cpu'
+// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, sm_87, sm_89, sm_90, sm_90a, sm_100, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx9-generic, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx10-1-generic, gfx1010, gfx1011, gfx1012, gfx1013, gfx10-3-generic, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx11-generic, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx12-generic, gfx1200, gfx1201, amdgcnspirv{{$}}
+
+// RUN: not %clang_cc1 -triple r600--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix R600
+// R600: error: unknown target CPU 'not-a-cpu'
+// R600-NEXT: note: valid target CPU values are: r600, rv630, rv635, r630, rs780, rs880, rv610, rv620, rv670, rv710, rv730, rv740, rv770, cedar, palm, cypress, hemlock, juniper, redwood, sumo, sumo2, barts, caicos, aruba, cayman, turks{{$}}
+
+// RUN: not %clang_cc1 -triple amdgcn--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AMDGCN
+// AMDGCN: error: unknown target CPU 'not-a-cpu'
+// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx1200, gfx1201, gfx9-generic, gfx10-1-generic, gfx10-3-generic, gfx11-generic, gfx12-generic{{$}}
+
+// 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'
+// WEBASM-NEXT: note: valid target CPU values are: mvp, bleeding-edge, generic{{$}}
+
+// RUN: not %clang_cc1 -triple systemz--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix SYSTEMZ
+// SYSTEMZ: error: unknown target CPU 'not-a-cpu'
+// SYSTEMZ-NEXT: note: valid target CPU values are: arch8, z10, arch9, z196, arch10, zEC12, arch11, z13, arch12, z14, arch13, z15, arch14, z16{{$}}
+
+// RUN: not %clang_cc1 -triple sparc--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix SPARC
+// SPARC: error: unknown target CPU 'not-a-cpu'
+// SPARC-NEXT: note: valid target CPU values are: v8, supersparc, sparclite, f934, hypersparc, sparclite86x, sparclet, tsc701, v9, ultrasparc, ultrasparc3, niagara, niagara2, niagara3, niagara4, ma2100, ma2150, ma2155, ma2450, ma2455, ma2x5x, ma2080, ma2085, ma2480, ma2485, ma2x8x, leon2, at697e, at697f, leon3, ut699, gr712rc, leon4, gr740{{$}}
+
+// RUN: not %clang_cc1 -triple sparcv9--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix SPARCV9
+// SPARCV9: error: unknown target CPU 'not-a-cpu'
+// SPARCV9-NEXT: note: valid target CPU values are: v9, ultrasparc, ultrasparc3, niagara, niagara2, niagara3, niagara4{{$}}
+
+// RUN: not %clang_cc1 -triple powerpc--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix PPC
+// PPC: error: unknown target CPU 'not-a-cpu'
+// PPC-NEXT: note: valid target CPU values are: generic, 440, 450, 601, 602, 603, 603e, 603ev, 604, 604e, 620, 630, g3, 7400, g4, 7450, g4+, 750, 8548, 970, g5, a2, e500, e500mc, e5500, power3, pwr3, power4, pwr4, power5, pwr5, power5x, pwr5x, power6, pwr6, power6x, pwr6x, power7, pwr7, power8, pwr8, power9, pwr9, power10, pwr10, powerpc, ppc, ppc32, powerpc64, ppc64, powerpc64le, ppc64le, future{{$}}
+
+// RUN: not %clang_cc1 -triple mips--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix MIPS
+// MIPS: error: unknown target CPU 'not-a-cpu'
+// MIPS-NEXT: note: valid target CPU values are: mips1, mips2, mips3, mips4, mips5, mips32, mips32r2, mips32r3, mips32r5, mips32r6, mips64, mips64r2, mips64r3, mips64r5, mips64r6, octeon, octeon+, p5600{{$}}
+
+// RUN: not %clang_cc1 -triple lanai--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix LANAI
+// LANAI: error: unknown target CPU 'not-a-cpu'
+// LANAI-NEXT: note: valid target CPU values are: v11{{$}}
+
+// RUN: not %clang_cc1 -triple hexagon--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix HEXAGON
+// HEXAGON: error: unknown target CPU 'not-a-cpu'
+// HEXAGON-NEXT: note: valid target CPU values are: hexagonv5, hexagonv55, hexagonv60, hexagonv62, hexagonv65, hexagonv66, hexagonv67, hexagonv67t, hexagonv68, hexagonv69, hexagonv71, hexagonv71t, hexagonv73{{$}}
+
+// RUN: not %clang_cc1 -triple bpf--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix BPF
+// BPF: error: unknown target CPU 'not-a-cpu'
+// BPF-NEXT: note: valid target CPU values are: generic, v1, v2, v3, v4, probe{{$}}
+
+// RUN: not %clang_cc1 -triple avr--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AVR
+// AVR: error: unknown target CPU 'not-a-cpu'
+// AVR-NEXT: note: valid target CPU values are: avr1, at90s1200, attiny11, attiny12, attiny15, attiny28, avr2, at90s2313, at90s2323, at90s2333, at90s2343, attiny22, attiny26, at86rf401, at90s4414, at90s4433, at90s4434, at90s8515, at90c8534, at90s8535, avr25, ata5272, ata6616c, attiny13, attiny13a, attiny2313, attiny2313a, attiny24, attiny24a, attiny4313, attiny44, attiny44a, attiny84, attiny84a, attiny25, attiny45, attiny85, attiny261, attiny261a, attiny441, attiny461, attiny461a, attiny841, attiny861, attiny861a, attiny87, attiny43u, attiny48, attiny88, attiny828, avr3, at43usb355, at76c711, avr31, atmega103, at43usb320, avr35, attiny167, at90usb82, at90usb162, ata5505, ata6617c, ata664251, atmega8u2, atmega16u2, atmega32u2, attiny1634, avr4, atmega8, ata6289, atmega8a, ata6285, ata6286, ata6612c, atmega48, atmega48a, atmega48pa, ...
[truncated]

llvmbot · 2024-10-11T17:49:40Z

@llvm/pr-subscribers-backend-nvptx

Author: Artem Belevich (Artem-B)

Changes

This is a copy of #97402, which is now ready to land.

Patch is 25.62 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/112028.diff

9 Files Affected:

(modified) clang/docs/ReleaseNotes.rst (+2)
(modified) clang/include/clang/Basic/BuiltinsNVPTX.def (+8-2)
(modified) clang/include/clang/Basic/Cuda.h (+3-1)
(modified) clang/lib/Basic/Cuda.cpp (+4)
(modified) clang/lib/Basic/Targets/NVPTX.cpp (+2)
(modified) clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp (+1)
(modified) clang/lib/Driver/ToolChains/Cuda.cpp (+3)
(added) clang/test/Misc/target-invalid-cpu-note.c (+96)
(modified) llvm/lib/Target/NVPTX/NVPTX.td (+3-2)

diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index 763bc3ac159322..1722397452a80a 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -612,6 +612,8 @@ CUDA/HIP Language Changes
 
 CUDA Support
 ^^^^^^^^^^^^
+- Clang now supports CUDA SDK up to 12.6
+- Added support for sm_100
 
 AIX Support
 ^^^^^^^^^^^
diff --git a/clang/include/clang/Basic/BuiltinsNVPTX.def b/clang/include/clang/Basic/BuiltinsNVPTX.def
index 6b7bce5bc00d4f..969dd9e41ebfa3 100644
--- a/clang/include/clang/Basic/BuiltinsNVPTX.def
+++ b/clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -27,8 +27,10 @@
 #pragma push_macro("SM_89")
 #pragma push_macro("SM_90")
 #pragma push_macro("SM_90a")
+#pragma push_macro("SM_100")
+#define SM_100 "sm_100"
 #define SM_90a "sm_90a"
-#define SM_90 "sm_90|" SM_90a
+#define SM_90 "sm_90|" SM_90a "|" SM_100
 #define SM_89 "sm_89|" SM_90
 #define SM_87 "sm_87|" SM_89
 #define SM_86 "sm_86|" SM_87
@@ -63,7 +65,9 @@
 #pragma push_macro("PTX83")
 #pragma push_macro("PTX84")
 #pragma push_macro("PTX85")
-#define PTX85 "ptx85"
+#pragma push_macro("PTX86")
+#define PTX86 "ptx86"
+#define PTX85 "ptx85|" PTX86
 #define PTX84 "ptx84|" PTX85
 #define PTX83 "ptx83|" PTX84
 #define PTX82 "ptx82|" PTX83
@@ -1086,6 +1090,7 @@ TARGET_BUILTIN(__nvvm_getctarank_shared_cluster, "iv*3", "", AND(SM_90,PTX78))
 #pragma pop_macro("SM_89")
 #pragma pop_macro("SM_90")
 #pragma pop_macro("SM_90a")
+#pragma pop_macro("SM_100")
 #pragma pop_macro("PTX42")
 #pragma pop_macro("PTX60")
 #pragma pop_macro("PTX61")
@@ -1108,3 +1113,4 @@ TARGET_BUILTIN(__nvvm_getctarank_shared_cluster, "iv*3", "", AND(SM_90,PTX78))
 #pragma pop_macro("PTX83")
 #pragma pop_macro("PTX84")
 #pragma pop_macro("PTX85")
+#pragma pop_macro("PTX86")
diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index 83699f8897f663..a18e62620dd5d0 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -43,9 +43,10 @@ enum class CudaVersion {
   CUDA_123,
   CUDA_124,
   CUDA_125,
+  CUDA_126,
   FULLY_SUPPORTED = CUDA_123,
   PARTIALLY_SUPPORTED =
-      CUDA_125, // Partially supported. Proceed with a warning.
+      CUDA_126, // Partially supported. Proceed with a warning.
   NEW = 10000,  // Too new. Issue a warning, but allow using it.
 };
 const char *CudaVersionToString(CudaVersion V);
@@ -78,6 +79,7 @@ enum class OffloadArch {
   SM_89,
   SM_90,
   SM_90a,
+  SM_100,
   GFX600,
   GFX601,
   GFX602,
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index faf3878f064d20..72d9bd89c36e71 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -43,6 +43,7 @@ static const CudaVersionMapEntry CudaNameVersionMap[] = {
     CUDA_ENTRY(12, 3),
     CUDA_ENTRY(12, 4),
     CUDA_ENTRY(12, 5),
+    CUDA_ENTRY(12, 6),
     {"", CudaVersion::NEW, llvm::VersionTuple(std::numeric_limits<int>::max())},
     {"unknown", CudaVersion::UNKNOWN, {}} // End of list tombstone.
 };
@@ -96,6 +97,7 @@ static const OffloadArchToStringMap arch_names[] = {
     SM(89),                          // Ada Lovelace
     SM(90),                          // Hopper
     SM(90a),                         // Hopper
+    SM(100),                         // Blackwell
     GFX(600),  // gfx600
     GFX(601),  // gfx601
     GFX(602),  // gfx602
@@ -221,6 +223,8 @@ CudaVersion MinVersionForOffloadArch(OffloadArch A) {
     return CudaVersion::CUDA_118;
   case OffloadArch::SM_90a:
     return CudaVersion::CUDA_120;
+  case OffloadArch::SM_100:
+    return CudaVersion::CUDA_126;
   default:
     llvm_unreachable("invalid enum");
   }
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 43b653dc52ce0d..88a0dbde52d52b 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -281,6 +281,8 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case OffloadArch::SM_90:
       case OffloadArch::SM_90a:
         return "900";
+      case OffloadArch::SM_100:
+        return "1000";
       }
       llvm_unreachable("unhandled OffloadArch");
     }();
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index c920d93957b16e..35ff75416cb776 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -2274,6 +2274,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(const OMPRequiresDecl *D) {
       case OffloadArch::SM_89:
       case OffloadArch::SM_90:
       case OffloadArch::SM_90a:
+      case OffloadArch::SM_100:
       case OffloadArch::GFX600:
       case OffloadArch::GFX601:
       case OffloadArch::GFX602:
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index 7a70cf1c5694fd..c1beca840dde5b 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -87,6 +87,8 @@ CudaVersion getCudaVersion(uint32_t raw_version) {
     return CudaVersion::CUDA_124;
   if (raw_version < 12060)
     return CudaVersion::CUDA_125;
+  if (raw_version < 12070)
+    return CudaVersion::CUDA_126;
   return CudaVersion::NEW;
 }
 
@@ -669,6 +671,7 @@ void NVPTX::getNVPTXTargetFeatures(const Driver &D, const llvm::Triple &Triple,
   case CudaVersion::CUDA_##CUDA_VER:                                           \
     PtxFeature = "+ptx" #PTX_VER;                                              \
     break;
+    CASE_CUDA_VERSION(126, 86);
     CASE_CUDA_VERSION(125, 85);
     CASE_CUDA_VERSION(124, 84);
     CASE_CUDA_VERSION(123, 83);
diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
new file mode 100644
index 00000000000000..92b28c9a165209
--- /dev/null
+++ b/clang/test/Misc/target-invalid-cpu-note.c
@@ -0,0 +1,96 @@
+// Use CHECK-NEXT instead of multiple CHECK-SAME to ensure we will fail if there is anything extra in the output.
+// RUN: not %clang_cc1 -triple armv5--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix ARM
+// ARM: error: unknown target CPU 'not-a-cpu'
+// ARM-NEXT: note: valid target CPU values are: arm8, arm810, strongarm, strongarm110, strongarm1100, strongarm1110, arm7tdmi, arm7tdmi-s, arm710t, arm720t, arm9, arm9tdmi, arm920, arm920t, arm922t, arm940t, ep9312, arm10tdmi, arm1020t, arm9e, arm946e-s, arm966e-s, arm968e-s, arm10e, arm1020e, arm1022e, arm926ej-s, arm1136j-s, arm1136jf-s, mpcore, mpcorenovfp, arm1176jz-s, arm1176jzf-s, arm1156t2-s, arm1156t2f-s, cortex-m0, cortex-m0plus, cortex-m1, sc000, cortex-a5, cortex-a7, cortex-a8, cortex-a9, cortex-a12, cortex-a15, cortex-a17, krait, cortex-r4, cortex-r4f, cortex-r5, cortex-r7, cortex-r8, cortex-r52, cortex-r52plus, sc300, cortex-m3, cortex-m4, cortex-m7, cortex-m23, cortex-m33, cortex-m35p, cortex-m55, cortex-m85, cortex-m52, cortex-a32, cortex-a35, cortex-a53, cortex-a55, cortex-a57, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-a710, cortex-x1, cortex-x1c, neoverse-n1, neoverse-n2, neoverse-v1, cyclone, exynos-m3, exynos-m4, exynos-m5, kryo, iwmmxt, xscale, swift{{$}}
+
+// RUN: not %clang_cc1 -triple arm64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AARCH64
+// AARCH64: error: unknown target CPU 'not-a-cpu'
+// AARCH64-NEXT: note: valid target CPU values are: a64fx, ampere1, ampere1a, ampere1b, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-a7, apple-a8, apple-a9, apple-m1, apple-m2, apple-m3, apple-m4, apple-s4, apple-s5, carmel, cobalt-100, cortex-a34, cortex-a35, cortex-a510, cortex-a520, cortex-a520ae, cortex-a53, cortex-a55, cortex-a57, cortex-a65, cortex-a65ae, cortex-a710, cortex-a715, cortex-a72, cortex-a720, cortex-a720ae, cortex-a725, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-r82, cortex-r82ae, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, cortex-x925, cyclone, exynos-m3, exynos-m4, exynos-m5, falkor, generic, grace, kryo, neoverse-512tvb, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-n3, neoverse-v1, neoverse-v2, neoverse-v3, neoverse-v3ae, oryon-1, saphira, thunderx, thunderx2t99, thunderx3t110, thunderxt81, thunderxt83, thunderxt88, tsv110{{$}}
+
+// RUN: not %clang_cc1 -triple arm64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_AARCH64
+// TUNE_AARCH64: error: unknown target CPU 'not-a-cpu'
+// TUNE_AARCH64-NEXT: note: valid target CPU values are: a64fx, ampere1, ampere1a, ampere1b, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-a7, apple-a8, apple-a9, apple-m1, apple-m2, apple-m3, apple-m4, apple-s4, apple-s5, carmel, cobalt-100, cortex-a34, cortex-a35, cortex-a510, cortex-a520, cortex-a520ae, cortex-a53, cortex-a55, cortex-a57, cortex-a65, cortex-a65ae, cortex-a710, cortex-a715, cortex-a72, cortex-a720, cortex-a720ae, cortex-a725, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-r82, cortex-r82ae, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, cortex-x925, cyclone, exynos-m3, exynos-m4, exynos-m5, falkor, generic, grace, kryo, neoverse-512tvb, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-n3, neoverse-v1, neoverse-v2, neoverse-v3, neoverse-v3ae, oryon-1, saphira, thunderx, thunderx2t99, thunderx3t110, thunderxt81, thunderxt83, thunderxt88, tsv110{{$}}
+
+// RUN: not %clang_cc1 -triple i386--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86
+// X86: error: unknown target CPU 'not-a-cpu'
+// X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, pantherlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, clearwaterforest, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4, geode{{$}}
+
+// RUN: not %clang_cc1 -triple x86_64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86_64
+// X86_64: error: unknown target CPU 'not-a-cpu'
+// X86_64-NEXT: note: valid target CPU values are: nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, pantherlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, clearwaterforest, knl, knm, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4{{$}}
+
+// RUN: not %clang_cc1 -triple i386--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_X86
+// TUNE_X86: error: unknown target CPU 'not-a-cpu'
+// TUNE_X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, pantherlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, clearwaterforest, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
+
+// RUN: not %clang_cc1 -triple x86_64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_X86_64
+// TUNE_X86_64: error: unknown target CPU 'not-a-cpu'
+// TUNE_X86_64-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, pantherlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, clearwaterforest, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
+
+// RUN: not %clang_cc1 -triple nvptx--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix NVPTX
+// NVPTX: error: unknown target CPU 'not-a-cpu'
+// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, sm_87, sm_89, sm_90, sm_90a, sm_100, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx9-generic, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx10-1-generic, gfx1010, gfx1011, gfx1012, gfx1013, gfx10-3-generic, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx11-generic, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx12-generic, gfx1200, gfx1201, amdgcnspirv{{$}}
+
+// RUN: not %clang_cc1 -triple r600--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix R600
+// R600: error: unknown target CPU 'not-a-cpu'
+// R600-NEXT: note: valid target CPU values are: r600, rv630, rv635, r630, rs780, rs880, rv610, rv620, rv670, rv710, rv730, rv740, rv770, cedar, palm, cypress, hemlock, juniper, redwood, sumo, sumo2, barts, caicos, aruba, cayman, turks{{$}}
+
+// RUN: not %clang_cc1 -triple amdgcn--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AMDGCN
+// AMDGCN: error: unknown target CPU 'not-a-cpu'
+// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx1200, gfx1201, gfx9-generic, gfx10-1-generic, gfx10-3-generic, gfx11-generic, gfx12-generic{{$}}
+
+// 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'
+// WEBASM-NEXT: note: valid target CPU values are: mvp, bleeding-edge, generic{{$}}
+
+// RUN: not %clang_cc1 -triple systemz--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix SYSTEMZ
+// SYSTEMZ: error: unknown target CPU 'not-a-cpu'
+// SYSTEMZ-NEXT: note: valid target CPU values are: arch8, z10, arch9, z196, arch10, zEC12, arch11, z13, arch12, z14, arch13, z15, arch14, z16{{$}}
+
+// RUN: not %clang_cc1 -triple sparc--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix SPARC
+// SPARC: error: unknown target CPU 'not-a-cpu'
+// SPARC-NEXT: note: valid target CPU values are: v8, supersparc, sparclite, f934, hypersparc, sparclite86x, sparclet, tsc701, v9, ultrasparc, ultrasparc3, niagara, niagara2, niagara3, niagara4, ma2100, ma2150, ma2155, ma2450, ma2455, ma2x5x, ma2080, ma2085, ma2480, ma2485, ma2x8x, leon2, at697e, at697f, leon3, ut699, gr712rc, leon4, gr740{{$}}
+
+// RUN: not %clang_cc1 -triple sparcv9--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix SPARCV9
+// SPARCV9: error: unknown target CPU 'not-a-cpu'
+// SPARCV9-NEXT: note: valid target CPU values are: v9, ultrasparc, ultrasparc3, niagara, niagara2, niagara3, niagara4{{$}}
+
+// RUN: not %clang_cc1 -triple powerpc--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix PPC
+// PPC: error: unknown target CPU 'not-a-cpu'
+// PPC-NEXT: note: valid target CPU values are: generic, 440, 450, 601, 602, 603, 603e, 603ev, 604, 604e, 620, 630, g3, 7400, g4, 7450, g4+, 750, 8548, 970, g5, a2, e500, e500mc, e5500, power3, pwr3, power4, pwr4, power5, pwr5, power5x, pwr5x, power6, pwr6, power6x, pwr6x, power7, pwr7, power8, pwr8, power9, pwr9, power10, pwr10, powerpc, ppc, ppc32, powerpc64, ppc64, powerpc64le, ppc64le, future{{$}}
+
+// RUN: not %clang_cc1 -triple mips--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix MIPS
+// MIPS: error: unknown target CPU 'not-a-cpu'
+// MIPS-NEXT: note: valid target CPU values are: mips1, mips2, mips3, mips4, mips5, mips32, mips32r2, mips32r3, mips32r5, mips32r6, mips64, mips64r2, mips64r3, mips64r5, mips64r6, octeon, octeon+, p5600{{$}}
+
+// RUN: not %clang_cc1 -triple lanai--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix LANAI
+// LANAI: error: unknown target CPU 'not-a-cpu'
+// LANAI-NEXT: note: valid target CPU values are: v11{{$}}
+
+// RUN: not %clang_cc1 -triple hexagon--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix HEXAGON
+// HEXAGON: error: unknown target CPU 'not-a-cpu'
+// HEXAGON-NEXT: note: valid target CPU values are: hexagonv5, hexagonv55, hexagonv60, hexagonv62, hexagonv65, hexagonv66, hexagonv67, hexagonv67t, hexagonv68, hexagonv69, hexagonv71, hexagonv71t, hexagonv73{{$}}
+
+// RUN: not %clang_cc1 -triple bpf--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix BPF
+// BPF: error: unknown target CPU 'not-a-cpu'
+// BPF-NEXT: note: valid target CPU values are: generic, v1, v2, v3, v4, probe{{$}}
+
+// RUN: not %clang_cc1 -triple avr--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AVR
+// AVR: error: unknown target CPU 'not-a-cpu'
+// AVR-NEXT: note: valid target CPU values are: avr1, at90s1200, attiny11, attiny12, attiny15, attiny28, avr2, at90s2313, at90s2323, at90s2333, at90s2343, attiny22, attiny26, at86rf401, at90s4414, at90s4433, at90s4434, at90s8515, at90c8534, at90s8535, avr25, ata5272, ata6616c, attiny13, attiny13a, attiny2313, attiny2313a, attiny24, attiny24a, attiny4313, attiny44, attiny44a, attiny84, attiny84a, attiny25, attiny45, attiny85, attiny261, attiny261a, attiny441, attiny461, attiny461a, attiny841, attiny861, attiny861a, attiny87, attiny43u, attiny48, attiny88, attiny828, avr3, at43usb355, at76c711, avr31, atmega103, at43usb320, avr35, attiny167, at90usb82, at90usb162, ata5505, ata6617c, ata664251, atmega8u2, atmega16u2, atmega32u2, attiny1634, avr4, atmega8, ata6289, atmega8a, ata6285, ata6286, ata6612c, atmega48, atmega48a, atmega48pa, ...
[truncated]

github-actions · 2024-10-14T17:48:16Z

✅ With the latest revision this PR passed the C/C++ code formatter.

…rsions

jhuber6

I swear there's got to be a way to automate this.

This is a copy of llvm#97402(with minor updates), which is now ready to land. --------- Co-authored-by: Sergey Kozub <skozub@nvidia.com>

Artem-B requested review from jholewinski and sergey-kozub October 11, 2024 17:48

Artem-B force-pushed the sm_100 branch from 8f2122e to 5dac14a Compare October 11, 2024 18:02

sergey-kozub and others added 2 commits October 14, 2024 10:53

[CUDA] Add support for CUDA-12.6 and sm_100

17989b2

Use ptx 8.5 with cuda-12.6, and enable ptx 8.6 with the newer CUDA ve…

e80aec4

…rsions

Artem-B force-pushed the sm_100 branch from aee63ae to e80aec4 Compare October 14, 2024 17:59

Artem-B requested a review from jhuber6 October 14, 2024 18:31

jhuber6 approved these changes Oct 14, 2024

View reviewed changes

Artem-B merged commit 30a06e8 into llvm:main Oct 14, 2024
6 of 8 checks passed

EricWF pushed a commit to efcs/llvm-project that referenced this pull request Oct 22, 2024

[CUDA] Add support for CUDA-12.6 and sm_100 (llvm#112028)

a703c64

This is a copy of llvm#97402(with minor updates), which is now ready to land. --------- Co-authored-by: Sergey Kozub <skozub@nvidia.com>

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[CUDA] Add support for CUDA-12.6 and sm_100 #112028

[CUDA] Add support for CUDA-12.6 and sm_100 #112028

Artem-B commented Oct 11, 2024

llvmbot commented Oct 11, 2024 •

edited

Loading

llvmbot commented Oct 11, 2024

github-actions bot commented Oct 14, 2024 •

edited

Loading

jhuber6 left a comment

[CUDA] Add support for CUDA-12.6 and sm_100 #112028

[CUDA] Add support for CUDA-12.6 and sm_100 #112028

Conversation

Artem-B commented Oct 11, 2024

llvmbot commented Oct 11, 2024 • edited Loading

llvmbot commented Oct 11, 2024

github-actions bot commented Oct 14, 2024 • edited Loading

jhuber6 left a comment

Choose a reason for hiding this comment

llvmbot commented Oct 11, 2024 •

edited

Loading

github-actions bot commented Oct 14, 2024 •

edited

Loading