Increasing TLB reach using superpages backed by shadow memory

ABSTRACT

The amount of memory that can be accessed without causing a TLB fault, the reach of a TLB, is failing to keep pace with the increasingly large working sets of applications. We propose to extend TLB reach via a novel Memory Controller TLB (MTLB) that lets us aggressively create superpages from non-contiguous, unaligned regions of physical memory. This flexibility increases the OS's ability to use superpages on arbitrary application data. The MTLB supports shadow pages, regions of physical address space for which the MTLB remaps accesses to "real" physical pages. The MTLB preserves per-base-page referenced and dirty bits, which enables the OS to swap shadow-backed superpages a page at a time, unlike conventional superpages. Simulation of five applications, including two SPECint95 benchmarks, demonstrated that a modest-sized MTLB improves performance of applications with moderate-to-high TLB miss rates by 5-20%. Simulation also showed that this mechanism can more than double the effective reach of a processor TLB with no modification to the processor MMU.

REFERENCES

• 1: Brian N. Bershad , Dennis Lee , Theodore H. Romer , J. Bradley Chen, Avoiding conflict misses dynamically in large direct-mapped caches, Proceedings of the sixth international conference on Architectural support for programming languages and operating systems, p.158-170, October 05-07, 1994, San Jose, California, United States
• 2: W. Bryg, K. Chan, and N. Fiduccia. A high-performance, low-cost multiprocessor bus for workstations and midrange servers. Hewlett-Packard Journal, 47(1):18-24, February 1996.
• 3: Satish Chandra , James R. Larus , Anne Rogers, Where is time spent in message-passing and shared-memory programs?, Proceedings of the sixth international conference on Architectural support for programming languages and operating systems, p.61-73, October 05-07, 1994, San Jose, California, United States
• 4: J. Bradley Chen , Anita Borg , Norman P. Jouppi, A simulation based study of TLB performance, Proceedings of the 19th annual international symposium on Computer architecture, p.114-123, May 19-21, 1992, Queensland, Australia
• 5: John H. Edmondson , Paul I. Rubinfeld , Peter J. Bannon , Bradley J. Benschneider , Debra Bernstein , Ruben W. Castelino , Elizabeth M. Cooper , Daniel E. Dever , Dale R. Donchin , Timothy C. Fischer , Anil K. Jain , Shekhar Mehta , Jeanne E. Meyer , Ronald P. Preston , Vidya Rajagopalan , Chandrasekhara Somanathan , Scott A. Taylor , Gilbert M. Wolrich, Internal organization of the Alpha 21164, a 300-MHz 64-bit quad-issue CMOS RISC microprocessor, Digital Technical Journal, v.7 n.1, p.119-135, Jan. 1995
• 6: L. Gwennap. Hp pumps up pa-8x00 family. Microprocessor Report, 10(14), October 1994.
• 7: T. Hotchkiss, N. Marschke, and R. McClosky. A new memory system design for commercial and technical computing products. Hewlett-Packard Journal, 47(1):44-51, February 1996.
• 8: http : //www. cs. utah. edu/projects/impulse.
• 9: lntel Corporation. Pentium Pro Family Developer's Manual, January 1996.
• 10: Jerry Huck , Jim Hays, Architectural support for translation table management in large address space machines, Proceedings of the 20th annual international symposium on Computer architecture, p.39-50, May 16-19, 1993, San Diego, California, United States
• 11: Norman P. Jouppi, Improving direct-mapped cache performance by the addition of a small fully-associative cache and prefetch buffers, Proceedings of the 17th annual international symposium on Computer Architecture, p.364-373, May 28-31, 1990, Seattle, Washington, United States
• 12: Gerry Kane, PA-RISC 2.0 architecture, Prentice-Hall, Inc., Upper Saddle River, NJ, 1996
• 13: S. A. Mckee , W. A. Wulf, Access ordering and memory-conscious cache utilization, Proceedings of the 1st IEEE Symposium on High-Performance Computer Architecture, p.253, January 22-25, 1995
• 14: MIPS Technologies Inc. MIPS RIO000 Microprocessor User's Manual Version 2.0, December 1996.
• 15: Madhusudhan Talluri , Mark D. Hill, Surpassing the TLB performance of superpages with less operating system support, Proceedings of the sixth international conference on Architectural support for programming languages and operating systems, p.171-182, October 05-07, 1994, San Jose, California, United States
• 16: Madhusudhan Talluri , Shing Kong , Mark D. Hill , David A. Patterson, Tradeoffs in supporting two page sizes, Proceedings of the 19th annual international symposium on Computer architecture, p.415-424, May 19-21, 1992, Queensland, Australia
• 17: Sharon E. Perl , Richard L. Sites, Studies of Windows NT performance using dynamic execution traces, Proceedings of the second USENIX symposium on Operating systems design and implementation, p.169-183, October 29-November 01, 1996, Seattle, Washington, United States
• 18: Theodore H. Romer , Wayne H. Ohlrich , Anna R. Karlin , Brian N. Bershad, Reducing TLB and memory overhead using online superpage promotion, Proceedings of the 22nd annual international symposium on Computer architecture, p.176-187, June 22-24, 1995, S. Margherita Ligure, Italy
• 19: Steven Cameron Woo , Moriyoshi Ohara , Evan Torrie , Jaswinder Pal Singh , Anoop Gupta, The SPLASH-2 programs: characterization and methodological considerations, Proceedings of the 22nd annual international symposium on Computer architecture, p.24-36, June 22-24, 1995, S. Margherita Ligure, Italy

INDEX TERMS

Primary Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.2 Storage Management
          Subjects: Virtual memory

Additional Classification:
  D. Software
  D.2 SOFTWARE ENGINEERING

General Terms:
Performance