Predicting the performance of a 3D processor-memory chip stack

被引：32

作者：

Jacob, P ^{[1
]}

Erdogan, O ^{[1
]}

Zia, A ^{[1
]}

Belemjian, PM ^{[1
]}

Kraft, RP ^{[1
]}

McDonald, JF ^{[1
]}

机构：

[1] Rensselaer Polytech Inst, Dept Elect Comp & Syst Engn, Ctr Integrated Elect, Troy, NY 12181 USA

来源：

IEEE DESIGN & TEST OF COMPUTERS | 2005年 / 22卷 / 06期

关键词：

D O I：

10.1109/MDT.2005.151

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A primary bottleneck in the performance of a processor is in its communication with memory. By allowing the placement of processor and memory in adjacent layers, 3D design provides significant relief, reducing the communication latency. This article studies the impact of 3D design by comparing the cycles per instruction of such a design with various alternatives. © 2005 IEEE.

引用

页码：540 / 547

页数：8

共 11 条

[1] [Anonymous], ACM SIGARCH COMPUT A
[2] CARRINGTON L, 2005, P DEPT DEF HIGH PERF
[3] GARROU P, 2005, SEMICONDUCTOR INT
[4] Hennessy John L., 2003, COMPUTER ARCHITECTUR
[5] Impact of three-dimensional architectures on interconnects in gigascale integration
Joyner, JW
Venkatesan, R
Zarkesh-Ha, P
Davis, JA
Meindl, JD
[J]. IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2001, 9 (06) : 922 - 928
[6] A 533-MHz BiCMOS superscalar RISC microprocessor
Maier, CA
Markevitch, JA
Brashears, CS
Sippel, T
Cohen, ET
Blomgren, J
Ballard, JG
Pattin, J
Moldenhauer, V
Thomas, JA
Taylor, G
[J]. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1997, 32 (11) : 1625 - 1634
[7] MCDONALD JF, 2003, P 20 INT VLSI MULT I, P247
[8] A 32-word by 32-bit three-port bipolar register file implemented using a SiGe HBT BiCMOS technology
Steidl, SA
McDonald, JF
[J]. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2002, 37 (02) : 228 - 236
[9] Stroobandt D, 1997, IEICE T INF SYST, VE80D, P1024
[10] AN ANALYTICAL ACCESS TIME MODEL FOR ON-CHIP CACHE MEMORIES
WADA, T
RAJAN, S
PRZYBYLSKI, SA
[J]. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1992, 27 (08) : 1147 - 1156

← 1 2 →