From 9e18b6a0f3ff154e71f2a7efbac331425e1ad46d Mon Sep 17 00:00:00 2001
From: Tianlei Wu <tlwu@microsoft.com>
Date: Tue, 4 Feb 2025 11:47:02 -0800
Subject: [PATCH] [CUDA] Update nvcc flags (#23572)

### Description
(1) Remove `if (CMAKE_CUDA_COMPILER_VERSION VERSION_GREATER_EQUAL 11)`
since build requires cuda >= 11.4.
(2) Add sm_86 and sm_89 since we generate SASS code for specified cuda
architectures only. This change could support popular consumer GPUs
(like RTX 30X0 and RTX 40X0).
(3) Add sm_120 to support Blackwell GPUs (like RTX 50X0 etc).
(4) Add `-Xfatbin=-compress-all` to reduce wheel size. When
CMAKE_CUDA_ARCHITECTURES is not specified, the linux wheel size built by
CUDA 12.8 is reduced 8% (from 324MB to 299MB).

### Motivation and Context

To support popular consumer GPUs (RTX 30x0, 40x0, 50x0) in the default
setting. Reduce binary size.

Note that the default sm settings does not impact official released
binary. ORT official released binary are built with augmentation like
CMAKE_CUDA_ARCHITECTURES=75;80;90, which has both SASS (real) and PTX
(virtual) by default. See
https://cmake.org/cmake/help/latest/prop_tgt/CUDA_ARCHITECTURES.html for
more info.
---
 cmake/CMakeLists.txt | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/cmake/CMakeLists.txt b/cmake/CMakeLists.txt
index 962b42c190..c1a171fba0 100644
--- a/cmake/CMakeLists.txt
+++ b/cmake/CMakeLists.txt
@@ -1517,35 +1517,33 @@ if (onnxruntime_USE_CUDA)
       set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_53,code=sm_53") # TX1, Nano
       set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_62,code=sm_62") # TX2
       set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_72,code=sm_72") # AGX Xavier, NX Xavier
-      if (CMAKE_CUDA_COMPILER_VERSION VERSION_GREATER_EQUAL 11)
-        set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_87,code=sm_87") # AGX Orin, NX Orin
-      endif()
+      set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_87,code=sm_87") # AGX Orin, NX Orin
     else()
-      # the following compute capabilities are removed in CUDA 11 Toolkit
-      if (CMAKE_CUDA_COMPILER_VERSION VERSION_LESS 11)
-        set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_30,code=sm_30") # K series
-      endif()
       if (CMAKE_CUDA_COMPILER_VERSION VERSION_LESS 12)
         # 37, 50 still work in CUDA 11 but are marked deprecated and will be removed in future CUDA version.
         set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_37,code=sm_37") # K80
         set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_50,code=sm_50") # M series
       endif()
+      # Note that we generate SASS code for specified cuda architectures. It does not support forward compatibility.
+      # To add PTX for future GPU architectures >= XX, append -gencode=arch=compute_XX,code=compute_XX.
       set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_52,code=sm_52") # M60
       set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_60,code=sm_60") # P series
       set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_70,code=sm_70") # V series
       set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_75,code=sm_75") # T series
-      if (CMAKE_CUDA_COMPILER_VERSION VERSION_GREATER_EQUAL 11)
-        set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_80,code=sm_80") # A series
-      endif()
+      set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_80,code=sm_80") # A series
+      set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_86,code=sm_86")
+      set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_89,code=sm_89")
       if (CMAKE_CUDA_COMPILER_VERSION VERSION_GREATER_EQUAL 12)
         set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_90,code=sm_90") # H series
+        if (CMAKE_CUDA_COMPILER_VERSION VERSION_GREATER_EQUAL 12.8)
+          set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_120,code=sm_120") # B series
+        endif()
       endif()
     endif()
   endif()
+  set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Xfatbin=-compress-all")
   set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --expt-relaxed-constexpr")
-  if (CMAKE_CUDA_COMPILER_VERSION VERSION_GREATER_EQUAL 11)
-    set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --Werror default-stream-launch")
-  endif()
+  set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --Werror default-stream-launch")
   if (NOT WIN32)
     list(APPEND CUDA_NVCC_FLAGS --compiler-options -fPIC)
   endif()