[llvm] [NVPTX] Add ELF flags for Nvidia cubin files (PR #75624)

[Joseph Huber via llvm-commits]

https://github.com/jhuber6 created https://github.com/llvm/llvm-project/pull/75624

Summary:
Nvidia uses ELF as its file format for cubin files. This patch adds
support to allow detecting the architecture using the ELF flags only.
This will be used in the offloading runtime in the future.

These values are completely undocumented. They were determined by
manually modifying the ELF header of the cubin and checking the output
of the `nvisasm` tool.


>From 0949378201d835c89091cceaedb346901be783ed Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Fri, 15 Dec 2023 10:55:57 -0600
Subject: [PATCH] [NVPTX] Add ELF flags for Nvidia cubin files

Summary:
Nvidia uses ELF as its file format for cubin files. This patch adds
support to allow detecting the architecture using the ELF flags only.
This will be used in the offloading runtime in the future.

These values are completely undocumented. They were determined by
manually modifying the ELF header of the cubin and checking the output
of the `nvisasm` tool.
---
 llvm/include/llvm/BinaryFormat/ELF.h | 43 ++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index da38f6ef064f95..0f968eac36e72f 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -846,6 +846,49 @@ enum {
 #include "ELFRelocs/AMDGPU.def"
 };
 
+// NVPTX specific e_flags.
+enum : unsigned {
+  // Processor selection mask for EF_CUDA_SM* values.
+  EF_CUDA_SM = 0xff,
+
+  // SM based processor values.
+  EF_CUDA_SM20 = 0x14,
+  EF_CUDA_SM21 = 0x15,
+  EF_CUDA_SM30 = 0x1e,
+  EF_CUDA_SM32 = 0x20,
+  EF_CUDA_SM35 = 0x23,
+  EF_CUDA_SM37 = 0x25,
+  EF_CUDA_SM50 = 0x32,
+  EF_CUDA_SM52 = 0x34,
+  EF_CUDA_SM53 = 0x35,
+  EF_CUDA_SM60 = 0x3c,
+  EF_CUDA_SM61 = 0x3d,
+  EF_CUDA_SM62 = 0x3e,
+  EF_CUDA_SM70 = 0x46,
+  EF_CUDA_SM72 = 0x48,
+  EF_CUDA_SM75 = 0x4b,
+  EF_CUDA_SM80 = 0x50,
+  EF_CUDA_SM86 = 0x56,
+  EF_CUDA_SM87 = 0x57,
+  EF_CUDA_SM89 = 0x59,
+  // The sm_90a variant uses the same machine flag.
+  EF_CUDA_SM90 = 0x5a,
+
+  // Unified texture binding is enabled.
+  EF_CUDA_TEXMODE_UNIFIED = 0x100,
+  // Independent texture binding is enabled.
+  EF_CUDA_TEXMODE_INDEPENDANT = 0x200,
+  // The target is using 64-bit addressing.
+  EF_CUDA_64BIT_ADDRESS = 0x400,
+  // Set when using the sm_90a processor.
+  EF_CUDA_ACCELERATORS = 0x800,
+  // Undocumented software feature.
+  EF_CUDA_SW_FLAG_V2 = 0x1000,
+
+  // Virtual processor selection mask for EF_CUDA_VIRTUAL_SM* values.
+  EF_CUDA_VIRTUAL_SM = 0xff0000,
+};
+
 // ELF Relocation types for BPF
 enum {
 #include "ELFRelocs/BPF.def"