C. J. Stephenson, "Fast fits," in Proceedings of the ACM 9th Symposium on Operating Systems, October 1983, pp. 30--32. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Automatic Compiler-Inserted Prefetching for Pointer-Based.. - Luk, Mowry (1999) (6 citations) (Correct)
....the parameters of our model. We use pixie [13] to instrument the optimized MIPS object files produced by the compiler, and pipe the resulting trace into our simulator. To avoid misses during the initialization of dynamicallyallocated objects, we used a modified version of the IRIX mallopt routine [14] whereby we prefetch allocated objects before they are initialized. Determining these prefetch addresses is straightforward, since objects of the same size are typically allocated from contiguous memory. This optimization alone led to over twofold speedups relative to using malloc for the majority ....
C. J. Stephenson, "Fast fits," in Proceedings of the ACM 9th Symposium on Operating Systems, October 1983, pp. 30--32.
Threads and Input/Output in the Synthesis Kernel - Massalin, Pu (1995) (59 citations) (Correct)
....are faster than traditional run time library routines. For example, naive implementations of memory allocation, block copy, and string comparison would have slowed down our system considerably. In Synthesis, the memory allocation routine is an executable data structure implementing a fast fit heap [6] with randomized traversal added. The block copy as used in read has been outlined in Section 6.2. The string comparison was mentioned as part of the open earlier in this section. 6.4 Kernel Size The Synthesis kernel is written in 68020 assembly language, which is used as a fast prototyping ....
C.J. Stephenson. Fast fits. In Proceedings of the Ninth ACM Symposium on Operating Systems Principles, pages 30--32, October 1983.
Compiler-Based Prefetching for Recursive Data Structures - Luk (1996) (89 citations) (Correct)
....files produced by the compiler, and pipe the resulting trace into our simulator. To minimize the impact of store stalls during the initialization of dynamically allocated objects, we use our own memory allocator for these experiments which is similar to mallopt provided in the Irix C library [19], but also contains built in prefetching to avoid such store misses. This optimization alone led to dramatic improvements (greater than two fold speedups) over using malloc for the majority of the applications particularly the ones that frequently allocate small objects. 0 20 40 ....
C. J. Stephenson. Fast fits. In Proceedings of the ACM 9th Symposium on Operating Systems, October 1983.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC