Loading...
Please wait, while we are loading the content...
Similar Documents
DynaSpAM: Dynamic Spatial Architecture Mapping using Out of Order Instruction Schedules
| Content Provider | CiteSeerX |
|---|---|
| Author | Liu, Feng Ahn, Heejin Beard, Stephen R. Oh, Taewook August, David I. |
| Abstract | Spatial architectures are more efficient than traditional Out-of-Order (OOO) processors for computationally intensive pro-grams. However, spatial architectures require mapping a program, either statically or dynamically, onto the spatial fabric. Static methods can generate efficient mappings, but they cannot adapt to changing workloads and are not compat-ible across hardware generations. Current dynamic methods are adaptive and compatible, but do not optimize as well due to their limited use of speculation and small mapping scopes. To overcome the limitations of existing dynamic map-ping methods for spatial architectures, while minimizing the inefficiencies inherent in OOO superscalar processors, this pa-per presents DynaSpAM (Dynamic Spatial Architecture Map-ping), a framework that tightly couples a spatial fabric with an OOO pipeline. DynaSpAM coaxes the OOO processor into producing an optimized mapping with a simple modification to the processor’s scheduler. The insight behind DynaSpAM is that today’s powerful OOO processors do for themselves most of the work necessary to produce a highly optimized mapping for a spatial architecture, including aggressively speculating control and memory dependences, and scheduling instructions using a large window. Evaluation of DynaSpAM shows a ge-omean speedup of 1.42 × for 11 benchmarks from the Rodinia benchmark suite with a geomean 23.9 % reduction in energy consumption compared to an 8-issue OOO pipeline. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Spatial Architecture Order Instruction Schedule Dynamic Spatial Architecture Mapping Optimized Mapping Spatial Fabric Energy Consumption Traditional Out-of-order Static Method Memory Dependence Ooo Pipeline Ge-omean Speedup Limited Use Processor Scheduler Small Mapping Scope Rodinia Benchmark Suite Powerful Ooo Processor Simple Modification Dynamic Map-ping Method 8-issue Ooo Pipeline Ooo Superscalar Processor Efficient Mapping Hardware Generation Large Window Intensive Pro-grams Current Dynamic Method Ooo Processor Pa-per Present Dynaspam Dynamic Spatial Architecture Map-ping |
| Content Type | Text |
