[clang] bc1725e - [clang] convergent attribute does not require "all threads" (#135803)

[via cfe-commits]

Author: Sameer Sahasrabuddhe
Date: 2025-04-17T05:13:54Z
New Revision: bc1725ef3a2707c244d8c2a401d7545755f96cbd

URL: https://github.com/llvm/llvm-project/commit/bc1725ef3a2707c244d8c2a401d7545755f96cbd
DIFF: https://github.com/llvm/llvm-project/commit/bc1725ef3a2707c244d8c2a401d7545755f96cbd.diff

LOG: [clang] convergent attribute does not require "all threads" (#135803)

The documentation for the `convergent` attribute claims that OpenCL and
CUDA require "all threads" in a group to call the same convergent
operation. This is true only for OpenCL, and in general, the
`convergent` attribute is used in LLVM IR on operations that have no
such constraint.

Added: 
    

Modified: 
    clang/include/clang/Basic/AttrDocs.td

Removed: 
    


################################################################################
diff  --git a/clang/include/clang/Basic/AttrDocs.td b/clang/include/clang/Basic/AttrDocs.td
index 76f805ef373dd..29d1d2c69e824 100644
--- a/clang/include/clang/Basic/AttrDocs.td
+++ b/clang/include/clang/Basic/AttrDocs.td
@@ -1680,10 +1680,6 @@ translated into the LLVM ``convergent`` attribute, which indicates that the call
 instructions of a function with this attribute cannot be made control-dependent
 on any additional values.
 
-In languages designed for SPMD/SIMT programming model, e.g. OpenCL or CUDA,
-the call instructions of a function with this attribute must be executed by
-all work items or threads in a work group or sub group.
-
 This attribute is 
diff erent from ``noduplicate`` because it allows duplicating
 function calls if it can be proved that the duplicated function calls are
 not made control-dependent on any additional values, e.g., unrolling a loop