[Openmp-commits] [PATCH] D75546: [libomptarget] Implement locks for amdgcn

Jon Chesterfield via Phabricator via Openmp-commits openmp-commits at lists.llvm.org
Thu Mar 5 09:50:51 PST 2020


JonChesterfield updated this revision to Diff 248515.
JonChesterfield added a comment.

- Warn instead of providing a partial implementation


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D75546/new/

https://reviews.llvm.org/D75546

Files:
  openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt
  openmp/libomptarget/deviceRTLs/amdgcn/src/amdgcn_locks.hip


Index: openmp/libomptarget/deviceRTLs/amdgcn/src/amdgcn_locks.hip
===================================================================
--- /dev/null
+++ openmp/libomptarget/deviceRTLs/amdgcn/src/amdgcn_locks.hip
@@ -0,0 +1,28 @@
+//===-- amdgcn_locks.hip - AMDGCN OpenMP GPU lock implementation -- HIP -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// A 'thread' maps onto a lane of the wavefront. This means a per-thread lock
+// cannot be implemented - if one thread gets the lock, it can't continue on to
+// the next instruction in order to do anything as the other threads are waiting
+// to take the lock.
+// These functions will be implemented to provide the documented semantics for
+// a SIMD => wavefront mapping once that is implemented.
+//
+//===----------------------------------------------------------------------===//
+
+#include "common/debug.h"
+
+static DEVICE void warn() {
+  PRINT0(LD_ALL, "Locks are not supported in this thread mapping model");
+}
+
+DEVICE void __kmpc_impl_init_lock(omp_lock_t *) { warn(); }
+DEVICE void __kmpc_impl_destroy_lock(omp_lock_t *) { warn(); }
+DEVICE void __kmpc_impl_set_lock(omp_lock_t *) { warn(); }
+DEVICE void __kmpc_impl_unset_lock(omp_lock_t *) { warn(); }
+DEVICE int __kmpc_impl_test_lock(omp_lock_t *lock) { warn(); }
Index: openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt
===================================================================
--- openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt
+++ openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt
@@ -56,6 +56,7 @@
 
 set(cuda_sources
   ${CMAKE_CURRENT_SOURCE_DIR}/src/amdgcn_smid.hip
+  ${CMAKE_CURRENT_SOURCE_DIR}/src/amdgcn_locks.hip
   ${CMAKE_CURRENT_SOURCE_DIR}/src/target_impl.hip
   ${devicertl_base_directory}/common/src/cancel.cu
   ${devicertl_base_directory}/common/src/critical.cu


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D75546.248515.patch
Type: text/x-patch
Size: 2087 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/openmp-commits/attachments/20200305/242bfe75/attachment.bin>


More information about the Openmp-commits mailing list