Per Stenström; Michel Dubois; Manolis Katevenis; Rajiv Gupta; Theo Ungerer Springer-Verlag Berlin and Heidelberg GmbH & Co. KG (2008) Pehmeäkantinen kirja
Per Nilsson; Beth Birkenhain; Inger Edelfeldt; Peter Madsen; Johanna Nilsson; Ylva Karlsson; Walter Stenström Bokförlaget Semic (2018) Kovakantinen kirja
Koen De Bosschere; David Kaeli; Per Stenström; David Whalley; Theo Ungerer Springer-Verlag Berlin and Heidelberg GmbH & Co. KG (2007) Pehmeäkantinen kirja
Halla Sigurdardóttir; Magnus Myrberg; John Sjögren; Per Klingberg; Petra Carlsson; Björn Svärd; Anders Stenström Evangelium förlag (2014) Pehmeäkantinen kirja
1 2 Per Stenstro ..m and David Whalley 1 Chalmers University of Technology, Sweden 2 Florida State University, U.S.A. In January2007,the secondedition in the series of International Conferenceson High-Performance Embedded Architectures andCompilers (HiPEAC'2007)was held in Ghent,Belgium.We were fortunate to attract around70 submissions of whichonly19wereselected forpresentation.Amongthese,weaskedtheauthors ofthe?vemost highly rated contributionsto make extended versions ofthem. They all accepted to do that andtheirarticles appear in this section ofthe second volume. The?rstarticlebyKeramidas,Xekalakis,andKaxirasfocusesontheincreased power consumption in set-associativecaches.They presenta novel approach to reduce dynamicpower that leverages on the previously proposed cache decay approach that has been shown to reduce static (or leakage) power. In the secondarticlebyMagarajan,Gupta,andKrishnaswamythe focus ison techniques to encrypt data in memory to preservedata integrity. The problem with previous techniques is that the decryption latency ends up on the critical memory access path. Especially in embedded processors,caches are small and it isdi?cultto hide the decryption latency. The authors propose a compiler-based strategy that manages to reduce the impact of the decryption time signi?cantly. The thirdarticlebyKluyskensandEeckhoutfocusesondetailedarchitectural simulation techniques.It is well-known that they are ine?cientandaremedy to the problem isto use sampling.When usingsampling,onehastowarm up memory structures such as caches andbranch predictors.Thispaper introduces a noveltechnique calledBranchHistoryMatchingfore?cient warmupofbranch predictors. The fourth articlebyBhadauria,McKee,Singh, and Tyson focuses on static power consumptioninlarge caches.Theyintroduce a reuse-distance drowsy cache mechanism that issimpleas well as e?ective in reducingthestaticpower in caches.