-
Notifications
You must be signed in to change notification settings - Fork 69
AMDBackend
Jin Wang edited this page Mar 27, 2015
·
1 revision
- AMD IL Intermediate representation in Ocelot
- PTX Re-structuring pass to express PTX programs only in terms of Hammock Graphs
- PTX to CAL translator
- AMD GPU Device using the new Device interface
- Complete the branch of ocelot with the new device interface
- Buying some AMD cards to test locally
- Assigning tasks to project members
- Implementing ATIGPUDevice::allocate and understanding how the CudaRuntime uses the MemoryAllocation abstract object.
- Implementing ATIGPUDevice::launch and creating ATIExecutableKernel (I ended up not creating an ATIExecutableKernel object yet. Instead, I am launching the kernel directly from ATIGPUDevice).
- Looking at Ocelot's test infrastructure. I want to write the first test case for the AMD Backend (vectorScale.cu).
- Starting to implement the PTXtoILTranslator.
- Looking at PTXtoLLVMTranslator and the way it works.
- UAV0 Memory manager. Handle the different semantics between cudaMalloc (returns a pointer) and calResAlloc (returns a handle)
- Use CB0 as the param memory
- Continue with PTXToILTranslator