================
@@ -845,10 +1128,41 @@ extern "C" int
__llvm_profile_hip_collect_device_data(void) {
return Ret;
}
-/* Interceptors for hipModuleLoad* / hipModuleUnload. Linux only. */
+/* Linux HIP interceptors. */
#if defined(__linux__) && !defined(_WIN32)
+typedef struct {
+ unsigned int x;
+ unsigned int y;
+ unsigned int z;
+} HipDim3;
+
+typedef void *HipFunction;
+typedef void *HipStream;
+
+static int recordHipLaunchResult(int Rc) {
+ if (Rc == 0)
+ markCurrentDeviceUsed();
+ return Rc;
+}
+
----------------
yxsamliu wrote:
Good point. I added tracking for the other HIP launch entry points, including
extended, cooperative, graph, stream-per-thread, and module launch APIs.
For launches with a stream, the runtime now uses hipStreamGetDevice to mark the
launched device. If that is not available, it falls back to the current device.
For multi-device launch APIs, it marks each launch parameter stream.
I also tested this on a multi-GPU machine with all devices visible. The runtime
collected from the launched device and skipped the unused device.
https://github.com/llvm/llvm-project/pull/202095
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
