From 6cb214748d6ec3a61fdc35ee27f9a90d170dd242 Mon Sep 17 00:00:00 2001
From: Axel Huebl <axel.huebl@plasma.ninja>
Date: Thu, 6 Oct 2022 21:02:57 -0700
Subject: [PATCH] fix: NVCC 11.4.0 - 11.8.0 host bug workaround (#4220)

* Work-Around: NVCC 11.4.0 - 11.8.0

Adds a targeted NVCC work around for limited number of CUDA
releases. Fixed in NVCC development.

* style: pre-commit fixes

* CI: Bump CTK Version 11.2 -> 11.7

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
---
 .github/workflows/ci.yml    |  4 ++--
 include/pybind11/pybind11.h | 17 +++++++++++++++++
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index fe57e7ce..99caabf0 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -324,8 +324,8 @@ jobs:
   # Testing NVCC; forces sources to behave like .cu files
   cuda:
     runs-on: ubuntu-latest
-    name: "🐍 3.8 • CUDA 11.2 • Ubuntu 20.04"
-    container: nvidia/cuda:11.2.2-devel-ubuntu20.04
+    name: "🐍 3.10 • CUDA 11.7 • Ubuntu 22.04"
+    container: nvidia/cuda:11.7.0-devel-ubuntu22.04
 
     steps:
     - uses: actions/checkout@v3
diff --git a/include/pybind11/pybind11.h b/include/pybind11/pybind11.h
index c889dc41..3f6e27b7 100644
--- a/include/pybind11/pybind11.h
+++ b/include/pybind11/pybind11.h
@@ -1578,6 +1578,22 @@ public:
         return *this;
     }
 
+// Nvidia's NVCC is broken between 11.4.0 and 11.8.0
+//   https://github.com/pybind/pybind11/issues/4193
+#if defined(__CUDACC__) && (__CUDACC_VER_MAJOR__ == 11) && (__CUDACC_VER_MINOR__ >= 4)            \
+    && (__CUDACC_VER_MINOR__ <= 8)
+    template <typename T, typename... Extra>
+    class_ &def(const T &op, const Extra &...extra) {
+        op.execute(*this, extra...);
+        return *this;
+    }
+
+    template <typename T, typename... Extra>
+    class_ &def_cast(const T &op, const Extra &...extra) {
+        op.execute_cast(*this, extra...);
+        return *this;
+    }
+#else
     template <detail::op_id id, detail::op_type ot, typename L, typename R, typename... Extra>
     class_ &def(const detail::op_<id, ot, L, R> &op, const Extra &...extra) {
         op.execute(*this, extra...);
@@ -1589,6 +1605,7 @@ public:
         op.execute_cast(*this, extra...);
         return *this;
     }
+#endif
 
     template <typename... Args, typename... Extra>
     class_ &def(const detail::initimpl::constructor<Args...> &init, const Extra &...extra) {