Editors’ Foreword

Dear members of the SIGARCH and TCCA communities,

In 1998, in commemoration of the 25th anniversary of ISCA, Guri Sohi put together a volume of selected papers and author retrospectives from 1973 through 1995 (ISCA-1 through ISCA-22) with help from several program chairs and vice chairs for ISCA-15 through ISCA-21. As we celebrate ISCA’s 50th birthday this year, we wanted to compile a volume that would pick up where the first volume left off. We borrowed some parameters from Guri Sohi’s original effort: we excluded papers from the two most recent years, and we put together a small team of referees comprising program chairs from the last few ISCA conferences: David Brooks, Fred Chong, Lieven Eeckhout, Babak Falsafi, and Hillery Hunter. (Although Lizy John was the program chair for ISCA 2021, as co-editor of this volume, she only participated in coordinating the reviews, but not in the paper selection.)

We did not set out to select the “best” or “most influential” papers. Instead, we created a collection of significant and often memorable papers from 1996 through 2020 that would tell a story of how research at ISCA progressed over those twenty-five years, each accompanied by a retrospective from the authors. The resulting volume is necessarily an imperfect compilation, with many significant contributions to ISCA and sister conferences missing. Still, we believe it tells an exciting and meaningful story.

We steered paper selection as follows: We charged two referees with selecting papers from each five-year interval (a different pair for each interval). Thus, each referee was paired with one other referee for one five-year interval, and with an additional referee for a different five-year interval. For each five-year interval, we asked the pair responsible to set aside any paper for which either had a conflict of interest, roughly as defined by the ISCA-50 rules. We also excluded the SIGARCH/TCCA Influential ISCA Paper awardees from the selection process, as these would be automatically included in the retrospective.

In round 1, each referee tentatively selected about fifteen papers from each five-year interval assigned to them. Then, in round 2, referees met independently with their assigned partner for each five-year interval, discussed their individual choices, and came up with a joint selection of up to twenty papers. In round 3, we assigned each of the papers set aside as conflicts to a referee that did not have a conflict of interest and that had not been assigned the five-year interval that the paper belonged to. Papers for which one of us had a conflict were assigned by the other; there were no papers in the list for which we both had conflicts. Finally, in round 4, we repeated the process for the papers selected during round 3.

In all, every paper (1,077 total) was considered by two referees who did not have a conflict of interest, and every selected paper was picked by both referees, either through discussion (rounds 1-2) or sequentially (rounds 3-4). The final number of papers selected was 98. This is over twice the amount of papers included in Guri Sohi’s retrospective, which is primarily a reflection of the growth of our community in the intervening years. We then contacted the authors and asked them to write a retrospective for their papers.

We are incredibly grateful to David, Fred, Lieven, Babak, and Hillery for the tremendous effort they put into this endeavor, and to the authors for their enthusiasm and dedication in preparing their retrospectives. We hope the resulting volume may be an exciting read for older and younger generations of computer architects alike!

José F. Martínez, SIGARCH Executive Committee Member
Lizy K. John, TCCA Executive Committee Member

June 2023