Name
Abstract | ||
|---|---|---|
This work proposes a new architecture and execution model called 2D-VLIW. This architecture adopts an execution model based on large pieces of computation running over a matrix of functional units connected by a set of local register spread across the matrix. Experiments using the Mediabench and SPECint00 programs and the Trimaran compiler show performance gains ranging from 5% to 63%, when comparing our proposal to an EPIC architecture with the same number of registers and functional units. We also show that the g721-enc program running on a 2D-VLIW 3脳3 matrix had a speedup of 1.37 over a 2脳2 matrix while the same program over the EPIC processor with 9 functional units had a speedup of 1.12 over an EPIC processor with 4 functional units. For some internal procedures from Mediabench and SPECint programs, the average 2D-VLIW OPC (operations per cycle) was up to 10 times greater than for the equivalent EPIC processor. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/ASAP.2006.1 | ASAP |
Keywords | Field | DocType |
execution model,functional unit,epic processor,new architecture,g721-enc program,trimaran compiler show performance,specint00 program,epic architecture,specint program,equivalent epic processor | Explicitly parallel instruction computing,Very long instruction word,Computer science,Matrix (mathematics),Parallel computing,Compiler,SPECint,Execution model,Computation,Speedup | Conference |
ISSN | ISBN | Citations |
2160-0511 | 0-7695-2682-9 | 4 |
PageRank | References | Authors |
0.46 | 7 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ricardo Santos | 1 | 4 | 0.46 |
| Rodolfo Azevedo | 2 | 271 | 30.84 |
| Guido Araujo | 3 | 40 | 5.23 |