149dc17c90
*Lay foundation to batch packets efficiently for graphs *Dynamically copy packets with max threshold set with DEBUG_HIP_GRAPH_BATCH_SIZE, if not stagger packet copy with pow2 *Default threshold for DEBUG_HIP_GRAPH_BATCH_SIZE is 256 *If TS are not collected for a signal for reuse, create a new signal. This can potentially increase signal footprint if the handler doesn't run fast enough.
AMD CLR - Compute Language Runtimes
Caution
The clr repository is retired, please use the ROCm/rocm-systems repository for development. This
developbranch will only accept patch updates from a bot that mirrors clr-specific updates fromrocm-systemsinto here.
AMD CLR (Compute Language Runtime) contains source codes for AMD's compute languages runtimes: HIP and OpenCL™.