Just to add true data for my GCN 2.0 theory.
The Sea Inlands ISA Manual (GCN2): http://developer.amd.com/wordpress/media/2013/02/AMD_Sea_Islands_Instruction_Set_Architecture.pdf
Important differences between S.I. and C.I. GPUs
•Multi queue compute * EIGHT queues and EIGHT ACEs is what the PS4 GPU have *
Lets multiple user-level queues of compute workloads be bound to the device and processed simultaneous. Hardware supports up to eight compute pipelines with up to eight queues bound to each pipeline.
•System unified addressing * That's the HSA present in PS4 GPU to share memory with CPU *
Allows GPU access to process coherent address space.
•Device unified addressing * Again. That's the HSA present in PS4 GPU to share memory with CPU *
Lets a kernel view LDS and video memory as a single addressable memory. It also adds shader instructions, which provide access to “flat” memory space.
•Memory address watch * I don't know if PS4 GPU have that *
Lets a shader determine if a region of memory has been accessed.
•Conditional debug * PS4 GPU don't need that... that's for debbugers *
Adds the ability to execute or skip a section of code based on state bits under control of debugger software. This feature adds two bits of state to each wavefront; these bits are initialized by the state register values set by the debugger, and they can be used in conditional branch instructions to skip or execute debug-only code in the kernel.
•Support for unaligned memory accesses * I don't know if PS4 GPU have that *
•Detection and reporting of violations in memory accesses * I don't know if PS4 GPU have that *
My comments in BLUE.
