llvm-project.git/libc/src/stdio/generic/vfprintf.cpp, branch users/nico/python-2 Unnamed repository; edit this file 'description' to name the repository. [libc] Implement (v|f)printf on the GPU (#96369) 2024-07-13T00:36:13+00:00 Joseph Huber huberjn@outlook.com 2024-07-13T00:36:13+00:00 40effc7af5679b7d54d3176a5eef2cdee1962ecd Summary: This patch implements the `printf` family of functions on the GPU using the new variadic support. This patch adapts the old handling in the `rpc_fprintf` placeholder, but adds an extra RPC call to get the size of the buffer to copy. This prevents the GPU from needing to parse the string. While it's theoretically possible for the pass to know the size of the struct, it's prohibitively difficult to do while maintaining ABI compatibility with NVIDIA's varargs. Depends on https://github.com/llvm/llvm-project/pull/96015. 
Summary:
This patch implements the `printf` family of functions on the GPU using
the new variadic support. This patch adapts the old handling in the
`rpc_fprintf` placeholder, but adds an extra RPC call to get the size of
the buffer to copy. This prevents the GPU from needing to parse the
string. While it's theoretically possible for the pass to know the size
of the struct, it's prohibitively difficult to do while maintaining ABI
compatibility with NVIDIA's varargs.

Depends on https://github.com/llvm/llvm-project/pull/96015.