🚀 go-pugleaf

The following is a list of some of the most recent technical reports 
issued by Dr. Michel Dubois' research group which can be obtained
through anonymous ftp.

FTP site: 'usc.edu'
Location: pub/CENG
Format: PostScript/Compressed

For further information about the reports in this list contact
Luiz Barroso (barroso@paris.usc.edu). For information about other
USC CENG tech. reports please contact Mary Zittercob (zitterco@pollux.
usc.edu).

=========================================================================

Title: A Snooping Cache Coherence Protocol for a Ring Connected
       Multiprocessor
Authors: Luiz A. Barroso and Michel Dubois
Technical Report No. CENG-91-03

Abstract: The Express Ring is a new architecture under investigation at
the University of Southern California. Its main goal is to demonstrate
that a slotted unidirectional ring with very fast point-to-point
interconnections can be at least ten times faster than a shared bus, using
the same technology, and may be the topology of choice for future shared-
memory multiprocessors. In this paper we introduce the Express Ring
architecture and present a snooping cache coherence protocol for this
machine. This protocol shows how consistency of shared memory accesses can
be efficiently maintained in a ring-connected multiprocessor. We analyze
the proposed protocol and compare it to other more usual alternatives for
point-to-point connected machines, such as the SCI cache coherence
protocol and directory based protocols.
=========================================================================

Title: Cache Coherence on a Slotted Ring
Authors: Luiz A. Barroso and Michel Dubois
Updated version of CENG-91-03; appeared in ICPP'91
=========================================================================

Title: Delayed Consistency and Its Effects on the Miss Rate of Parallel
       Programs
Authors: Michel Dubois, Jin-Chin Wang, Luiz A. Barroso, Kangwoo Lee and
         Yang-Syau Chen
Technical Report No. CENG 92-11

Abstract: In cache based multiprocessors a protocol must maintain
coherence among replicated copies of shared writable data. In delayed
consistency protocols the effect of out-going and in-coming invalidations
or updates are delayed. Delayed coherence can reduce processor blocking
time as well as the effects of false sharing. In this paper, we introduce
several implementations of delayed consistency for cache-based systems in
the framework of a weakly-ordered consistency model. A performance
comparison of the delayed protocols with the corresponding On-the-Fly
(non-delayed) consistency protocol is made, through execution-driven
simulations of four parallel algorithms. The results show that, for
parallel programs in which false sharing is a problem, significant
reductions in the data miss rate of parallel programs can be obtained with
just a small increase in the cost and complexity of the cache system.
=========================================================================

Title: Cache Inclusion and Processor Sampling in Multiprocessor Simulations
Authors: Jacqueline Chame and Michel Dubois
Technical Report No. CENG 92-13

Abstract: The evaluation of cache-based systems demands careful
simulations of entire benchmarks. Simulation efficiency is essential to
realistic evaluations. For systems with large caches and large number of
processors, simulation is often too slow to be practical. In particular,
the optimized design of a cache for a multiprocessor is very complex with
current techniques.
This paper addresses these problems. First we introduce necessary and
sufficient conditions for cache inclusion in uniprocessors and in
multiprocessors with and without invalidations. Second, under cache
inclusion, we show that an accurate trace for a given processor or for a
cluster of processors can be extracted from a multiprocessor trace. With
this methodology, possible cache architectures for       a processor or for a
cluster of processors are evaluated independently of the rest of the
system, resulting in a drastic reduction of the trace length and
simulation complexity. Moreover, many important system-wide metrics can
be estimated with good accuracy by extracting the traces of a set of
randomly selected processors, an approach we call processor sampling. We
demonstrate the accuracy and efficiency of these techniques by applying
them to three 64-processor traces.
=========================================================================

Title: Improving the Performance of Data Caches in Systems with Large
       Miss Latencies
Authors: Koray Oner and Michel Dubois
Technical Report No. CENG 92-14
 
Abstract: With current and projected processor technologies, memory
accesses are quickly becoming a major bottleneck of modern computing
systems. Even with a good cache, the miss penalty can be so high that the
processor works at greatly reduced efficiency. Whereas stores can be
buffered in a store buffer to hide store miss penalties, loads cannot be
dealt with so easily because the processor needs the data returned by the
load.
In this paper we introduce a simple processor/cache architecture with
non-blocking loads. We then report results of trace-driven simulations
of several FORTRAN DO-Loops. We first show that the architecture is
ineffective unless loads can be hoisted away from the instructions that
need the returned value. We then apply load hoisting to the loops and
show the possible performance improvements for the systems with very
large load miss latencies.
=========================================================================

Title: The Performance of Cache-Coherent Ring-based Multiprocessors
Authors: Luiz Andre Barroso and Michel Dubois
Technical Report No. CENG-92-19
 
Abstract: Advances in circuit and integration technology are
continuously boosting the speed of microprocessors. One of the main
challenges presented by such developments is the effective use of
powerful microprocessors in shared memory multiprocessor configurations.
We believe that the interconnection problem is not solved even for small
scale shared memory multiprocessors, since shared buses are unlikely to
keep up with the memory bandwidth requirements of new microprocessors. In
this paper we extensively evaluate the performance of the slotted ring
interconnection as a replacement for buses in small to medium scale
shared memory systems and for processor clusters in hierarchical
massively parallel systems, using a hybrid methodology of analytical
models and trace-driven simulations. Snooping and directory-based
coherence protocols for the ring are compared in the context of
multitasking.
=========================================================================

Title: The Verification of Cache Coherence Protocols
Authors: Fong Pong and Michel Dubois
Technical Report No. CENG-92-20
 
Abstract: In this paper we introduce a verification technique for cache
coherence protocols at the behavior level. Protocols are specified by a
Finite State Machine (FSM) model. The global state space is the Cartesian
product of an arbitrary number of individual cache state spaces and is
symbolically expanded. A global FSM characterizing the protocol behavior
is built and protocol verification becomes equivalent to finding whether
or not the global FSM may enter erroneous states. State expansion only
takes a few steps, contrary to current approaches. The verification
procedure is applied to the verification of five existing protocols
=========================================================================

===========================================================================
Co-moderator:  Richard Golding, Computer & Information Sciences, UC Santa Cruz
	    compdoc-techreports-request@ftp.cse.ucsc.edu