[llvm] [ELF] handle new NVIDIA GPU variants. (PR #151604)

[Artem Belevich via llvm-commits]

https://github.com/Artem-B updated https://github.com/llvm/llvm-project/pull/151604

>From f396d5af7186fdde20155bedfd4fc47071ccc279 Mon Sep 17 00:00:00 2001
From: Artem Belevich <tra at google.com>
Date: Thu, 31 Jul 2025 13:50:14 -0700
Subject: [PATCH 1/3] [ELF] handle new NVIDIA GPU variants.

---
 llvm/include/llvm/BinaryFormat/ELF.h  | 3 +++
 llvm/lib/Object/ELFObjectFile.cpp     | 9 +++++++++
 llvm/tools/llvm-readobj/ELFDumper.cpp | 4 +++-
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index ad35d7f05d5da..749971e354f66 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -973,7 +973,10 @@ enum : unsigned {
 
   // SM based processor values.
   EF_CUDA_SM100 = 0x6400,
+  EF_CUDA_SM101 = 0x6500,
+  EF_CUDA_SM103 = 0x6700,
   EF_CUDA_SM120 = 0x7800,
+  EF_CUDA_SM121 = 0x7900,
 
   // Set when using an accelerator variant like sm_100a.
   EF_CUDA_ACCELERATORS = 0x8,
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index 0919c6aad74f2..aff047c297cc2 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -688,11 +688,20 @@ StringRef ELFObjectFileBase::getNVPTXCPUName() const {
   case ELF::EF_CUDA_SM100:
     return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_100a"
                                                           : "sm_100";
+  case ELF::EF_CUDA_SM101:
+    return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_101a"
+                                                          : "sm_101";
+  case ELF::EF_CUDA_SM103:
+    return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_103a"
+                                                          : "sm_103";
 
   // Rubin architecture.
   case ELF::EF_CUDA_SM120:
     return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_120a"
                                                           : "sm_120";
+  case ELF::EF_CUDA_SM121:
+    return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_121a"
+                                                          : "sm_121";
   default:
     llvm_unreachable("Unknown EF_CUDA_SM value");
   }
diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index 94ce38605f5c9..1321d594416c5 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1683,7 +1683,9 @@ const EnumEntry<unsigned> ElfHeaderNVPTXFlags[] = {
     ENUM_ENT(EF_CUDA_SM75, "sm_75"),   ENUM_ENT(EF_CUDA_SM80, "sm_80"),
     ENUM_ENT(EF_CUDA_SM86, "sm_86"),   ENUM_ENT(EF_CUDA_SM87, "sm_87"),
     ENUM_ENT(EF_CUDA_SM89, "sm_89"),   ENUM_ENT(EF_CUDA_SM90, "sm_90"),
-    ENUM_ENT(EF_CUDA_SM100, "sm_100"), ENUM_ENT(EF_CUDA_SM120, "sm_120"),
+    ENUM_ENT(EF_CUDA_SM100, "sm_100"), ENUM_ENT(EF_CUDA_SM101, "sm_101"),
+    ENUM_ENT(EF_CUDA_SM103, "sm_103"), ENUM_ENT(EF_CUDA_SM120, "sm_120"),
+    ENUM_ENT(EF_CUDA_SM121, "sm_121"),
 };
 
 const EnumEntry<unsigned> ElfHeaderRISCVFlags[] = {

>From ebfa74074792689c464acc84ef06661d09aab65d Mon Sep 17 00:00:00 2001
From: Artem Belevich <tra at google.com>
Date: Thu, 31 Jul 2025 15:37:40 -0700
Subject: [PATCH 2/3] correctly handle new GPU values

---
 llvm/tools/llvm-readobj/ELFDumper.cpp | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index 1321d594416c5..480d144a4a444 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -3661,8 +3661,11 @@ template <class ELFT> void GNUELFDumper<ELFT>::printFileHeaders() {
     ElfFlags = printFlags(e.e_flags, ArrayRef(ElfHeaderXtensaFlags),
                           unsigned(ELF::EF_XTENSA_MACH));
   else if (e.e_machine == EM_CUDA) {
+    unsigned Mask = e.e_ident[ELF::EI_ABIVERSION] == ELF::ELFABIVERSION_CUDA_V1
+                    ? ELF::EF_CUDA_SM
+                    : ELF::EF_CUDA_SM_MASK;
     ElfFlags = printFlags(e.e_flags, ArrayRef(ElfHeaderNVPTXFlags),
-                          unsigned(ELF::EF_CUDA_SM));
+                          Mask);
     if (e.e_ident[ELF::EI_ABIVERSION] == ELF::ELFABIVERSION_CUDA_V1 &&
         (e.e_flags & ELF::EF_CUDA_ACCELERATORS_V1))
       ElfFlags += "a";

>From 09812905f3f76c2b57678a6c9be1313188cfa3bd Mon Sep 17 00:00:00 2001
From: Artem Belevich <tra at google.com>
Date: Thu, 31 Jul 2025 15:39:04 -0700
Subject: [PATCH 3/3] clang-format

---
 llvm/tools/llvm-readobj/ELFDumper.cpp | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index 480d144a4a444..66153ad9c1336 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -3662,10 +3662,9 @@ template <class ELFT> void GNUELFDumper<ELFT>::printFileHeaders() {
                           unsigned(ELF::EF_XTENSA_MACH));
   else if (e.e_machine == EM_CUDA) {
     unsigned Mask = e.e_ident[ELF::EI_ABIVERSION] == ELF::ELFABIVERSION_CUDA_V1
-                    ? ELF::EF_CUDA_SM
-                    : ELF::EF_CUDA_SM_MASK;
-    ElfFlags = printFlags(e.e_flags, ArrayRef(ElfHeaderNVPTXFlags),
-                          Mask);
+                        ? ELF::EF_CUDA_SM
+                        : ELF::EF_CUDA_SM_MASK;
+    ElfFlags = printFlags(e.e_flags, ArrayRef(ElfHeaderNVPTXFlags), Mask);
     if (e.e_ident[ELF::EI_ABIVERSION] == ELF::ELFABIVERSION_CUDA_V1 &&
         (e.e_flags & ELF::EF_CUDA_ACCELERATORS_V1))
       ElfFlags += "a";