User Tools

Site Tools


excite_information_and_results

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

excite_information_and_results [2010/09/17 10:56]
janders
excite_information_and_results [2010/12/15 15:53]
Line 1: Line 1:
-====== eXCite version: 4.1p (p1) ====== 
- 
- 
- 
-eXCite is a commercial HLS tool, developed by a company called Y explorations (spawned from UC Irvine) [website: http://​www.yxi.com/​]. ​ The tool is known to work for all of the CHStone benchmarks, and results are discussed in the CHStone paper [accessible from: http://​www.ertl.jp/​chstone/​].  ​ 
- 
- 
-eXCite / Cyclone II Implementation Results (July 5, 2010, updated: July 6, 2010, updated: July 7, 2010, updated: July 26, 2010) 
- 
-Notes: 
- 
-  * Results for the four "​df"​ circuits are included, however, the circuits are not functionally correct. ​ UPDATE: 2 of the 4 "​df"​ circuits are now working -- input/​golden vectors were improperly synthesized by eXCite, fixed manually; problem in 64 bit comparison in eXCite synthesis results, fixed manually. ​ UPDATE (July 26: all CHStone circuits are working correctly now after fixes in incorrect Verilog produced by eXCite. 
-  * Mapping doing using Quartus 9.1 SP 2 
-  * For the "​mips"​ benchmark, there are three versions: 1) default options of eXCite ("​mips"​),​ 2) resource-limited allocation in eXCite ("​mips_slow"​),​ 3) best-performance option in excite ("​mips_fast"​) 
-  * Cyclone II speed grade for all implementations:​ -6 
- 
- 
-| CIRCUIT | # LEs | # registers | # mem bits | # mults | Frequency (MHz) | Cycles | Notes | 
-| adpcm | 12280 | 4585 | 6572 | 28 | 24.92 | 21992 | | 
-| aes | 22594 | 3332 | 18688 | 0 | 38.12 | 55679 | | 
-| blowfish | 18559 | 1674 | 33944 | 0 | 33.73 | 209614 | | 
-| dfadd | 4437 | 1138 | 0 | 0 | 21.81 | 370 | 0 errors | 
-| dfdiv | 5206 | 1260 | 0 | 32 | 38.33 | 2029 | 0 errors | 
-| dfmul | 3148 | 553 | 0 | 32 | 45.93 | 223 | 0 errors | 
-| dfsin | 17040| 4086 | 0 | 38| 31.66 | 49709 | 0 errors | 
-| gsm | 5275 | 1358 | 3280 | 2 | 31.5 | 5739 | | 
-| jpeg | 30420 | 4205 | 105278 | 20 | 22.66 | 3248488 | | 
-| mips | 1957 | 436 | 3072 | 8 | 64.1 | 4344 | | 
-| mips_fast | 2012 | 435 | 3072 | 8 | 88.99 | 4344 | | 
-| mips_slow | 2144 | 735 | 4352 | 8 | 55.87 |21460 | | 
-| motion | 7209 | 1118 | 16384 | 0 | 42.35 | 2268 | | 
-| sha | 12089 | 1320 | 3072 | 0 | 55.82 | 238009 | | 
- 
-Power results 
- 
-IMPORTANT NOTE: All simulations were at 10 MHz, EXCEPT for AES which was at 25 MHz. 
-http://​www.eecg.utoronto.ca/​~janders/​eXCite_power/​ 
- 
-The results for the "​new"​ Quartus settings are at: http://​www.eecg.utoronto.ca/​~janders/​eXCite_new_flow ​ -- note that we must use the old data for the jpeg benchmark, as it does not fit into the largest Cyclone II with the new settings. 
  
excite_information_and_results.txt ยท Last modified: 2010/12/15 15:53 (external edit)