Shared-memory multiprocessors should be designed to provide for correct execution of programs constructed according to a chosen program execution model. In this paper, we use dataflow signal graphs as a program execution model for programs structured as nests of (possibly recursive) functions, and using incremental arrays with I-structure semantics. We introduce a memory model for the memory system of a shared-memory multiprocessor that has synchronizing write and read operations, and discuss how it supports our program execution model. An implementation of the memory model is presented that includes caching of remote words. The relationship of our model to the Monsoon multiprocessor and other latency-tolerant multiprocessor architectures i...
Emerging multiprocessor architectures such as chip multiprocessors, embedded architectures, and mas...
Scalable shared-memory multiprocessors distribute mem-ory among the processors and use scalable inte...
. Data used by parallel programs can be divided into classes, based on how threads access it. For di...
Parallel systems that support the shared memory abstraction are becoming widely accepted in many are...
The memory consistency model (or memory model) of a shared-memory multiprocessor system influences ...
The most commonly assumed memory consistency model for shared-memory multiprocessors is Sequential C...
A wide variety of computer architectures have been proposed to exploit parallelism at different gran...
All methods of multi-processing need some form of processor to processor communication. In shared me...
Most current multiprocessor architectures and shared memory parallel program-ming languages are not ...
The transition from single processor to shared memory multi-processors (or shared memory multi-core ...
This paper presents a shared-memory model, data-race-free-1, that unifies four earlier models: weak ...
The memory consistency model of a shared-memory multiprocessor determines the extent to which memory...
We describe an efficient software cache consistency mechanism for shared memory multiprocessors that...
The memory consistency model supported by a multiprocessor architecture determines the amount of buf...
A memory model for a concurrent imperative programming language specifies which writes to shared var...
Emerging multiprocessor architectures such as chip multiprocessors, embedded architectures, and mas...
Scalable shared-memory multiprocessors distribute mem-ory among the processors and use scalable inte...
. Data used by parallel programs can be divided into classes, based on how threads access it. For di...
Parallel systems that support the shared memory abstraction are becoming widely accepted in many are...
The memory consistency model (or memory model) of a shared-memory multiprocessor system influences ...
The most commonly assumed memory consistency model for shared-memory multiprocessors is Sequential C...
A wide variety of computer architectures have been proposed to exploit parallelism at different gran...
All methods of multi-processing need some form of processor to processor communication. In shared me...
Most current multiprocessor architectures and shared memory parallel program-ming languages are not ...
The transition from single processor to shared memory multi-processors (or shared memory multi-core ...
This paper presents a shared-memory model, data-race-free-1, that unifies four earlier models: weak ...
The memory consistency model of a shared-memory multiprocessor determines the extent to which memory...
We describe an efficient software cache consistency mechanism for shared memory multiprocessors that...
The memory consistency model supported by a multiprocessor architecture determines the amount of buf...
A memory model for a concurrent imperative programming language specifies which writes to shared var...
Emerging multiprocessor architectures such as chip multiprocessors, embedded architectures, and mas...
Scalable shared-memory multiprocessors distribute mem-ory among the processors and use scalable inte...
. Data used by parallel programs can be divided into classes, based on how threads access it. For di...