A Hierarchical Cache Coherent Protocol

As the number of processors in distributed-memory multiprocessors grows, efficiently supporting a shared-memory programming model becomes difficult. We have designed the Protocol for Hierarchical Directories (PHD) to allow shared-memory support for systems containing massive numbers of processors. PHD eliminates bandwidth problems by using a scalable network, decreases hot-spots by not relying on a single point to distribute blocks, and uses a scalable amount of space for its directories. PHD provides a shared-memory model by synthesizing a global shared memory from the local memories of processors. PHD supports sequentially consistent read, write, and test- and-set operations. This thesis also introduces a method of describing locality for hierarchical protocols and employs this method in the derivation of an abstract model of the protocol behavior. An embedded model, based on the work of Johnson[ISCA19], describes the protocol behavior when mapped to a k-ary n-cube. The thesis uses these two models to study the average height in the hierarchy that operations reach, the longest path messages travel, the number of messages that operations generate, the inter-transaction issue time, and the protocol overhead for different locality parameters, degrees of multithreading, and machine sizes. We determine that multithreading is only useful for approximately two to four threads; any additional interleaving does not decrease the overall latency. For small machines and high locality applications, this limitation is due mainly to the length of the running threads. For large machines with medium to low locality, this limitation is due mainly to the protocol overhead being too large. Our study using the embedded model shows that in situations where the run length between references to shared memory is at least an order of magnitude longer than the time to process a single state transition in the protocol, applications exhibit good performance. If separate controllers for processing protocol requests are included, the protocol scales to 32k processor machines as long as the application exhibits hierarchical locality: at least 22% of the global references must be able to be satisfied locally; at most 35% of the global references are allowed to reach the top level of the hierarchy.

An Interpolative Analytical Cache Model with Application to Performance-Power Design Space Exploration

Caches are known to consume up to half of all system power in embedded processors. Co-optimizing performance and power of the cache subsystems is therefore an important step in the design of embedded systems, especially those employing application specific instruction processors. In this project, we propose an analytical cache model that succinctly captures the miss performance of an application over the entire cache parameter space. Unlike exhaustive trace driven simulation, our model requires that the program be simulated once so that a few key characteristics can be obtained. Using these application-dependent characteristics, the model can span the entire cache parameter space consisting of cache sizes, associativity and cache block sizes. In our unified model, we are able to cater for direct-mapped, set and fully associative instruction, data and unified caches. Validation against full trace-driven simulations shows that our model has a high degree of fidelity. Finally, we show how the model can be coupled with a power model for caches such that one can very quickly decide on pareto-optimal performance-power design points for rapid design space exploration.

Failure-Oblivious Computing and Boundless Memory Blocks

Memory errors are a common cause of incorrect software execution and security vulnerabilities. We have developed two new techniques that help software continue to execute successfully through memory errors: failure-oblivious computing and boundless memory blocks. The foundation of both techniques is a compiler that generates code that checks accesses via pointers to detect out of bounds accesses. Instead of terminating or throwing an exception, the generated code takes another action that keeps the program executing without memory corruption. Failure-oblivious code simply discards invalid writes and manufactures values to return for invalid reads, enabling the program to continue its normal execution path. Code that implements boundless memory blocks stores invalid writes away in a hash table to return as the values for corresponding out of bounds reads. he net effect is to (conceptually) give each allocated memory block unbounded size and to eliminate out of bounds accesses as a programming error. We have implemented both techniques and acquired several widely used open source servers (Apache, Sendmail, Pine, Mutt, and Midnight Commander).With standard compilers, all of these servers are vulnerable to buffer overflow attacks as documented at security tracking web sites. Both failure-oblivious computing and boundless memory blocks eliminate these security vulnerabilities (as well as other memory errors). Our results show that our compiler enables the servers to execute successfully through buffer overflow attacks to continue to correctly service user requests without security vulnerabilities.

The M-Machine Multicomputer

The M-Machine is an experimental multicomputer being developed to test architectural concepts motivated by the constraints of modern semiconductor technology and the demands of programming systems. The M- Machine computing nodes are connected with a 3-D mesh network; each node is a multithreaded processor incorporating 12 function units, on-chip cache, and local memory. The multiple function units are used to exploit both instruction-level and thread-level parallelism. A user accessible message passing system yields fast communication and synchronization between nodes. Rapid access to remote memory is provided transparently to the user with a combination of hardware and software mechanisms. This paper presents the architecture of the M-Machine and describes how its mechanisms maximize both single thread performance and overall system throughput.

Thread Scheduling Mechanisms for Multiple-Context Parallel Processors

Scheduling tasks to efficiently use the available processor resources is crucial to minimizing the runtime of applications on shared-memory parallel processors. One factor that contributes to poor processor utilization is the idle time caused by long latency operations, such as remote memory references or processor synchronization operations. One way of tolerating this latency is to use a processor with multiple hardware contexts that can rapidly switch to executing another thread of computation whenever a long latency operation occurs, thus increasing processor utilization by overlapping computation with communication. Although multiple contexts are effective for tolerating latency, this effectiveness can be limited by memory and network bandwidth, by cache interference effects among the multiple contexts, and by critical tasks sharing processor resources with less critical tasks. This thesis presents techniques that increase the effectiveness of multiple contexts by intelligently scheduling threads to make more efficient use of processor pipeline, bandwidth, and cache resources. This thesis proposes thread prioritization as a fundamental mechanism for directing the thread schedule on a multiple-context processor. A priority is assigned to each thread either statically or dynamically and is used by the thread scheduler to decide which threads to load in the contexts, and to decide which context to switch to on a context switch. We develop a multiple-context model that integrates both cache and network effects, and shows how thread prioritization can both maintain high processor utilization, and limit increases in critical path runtime caused by multithreading. The model also shows that in order to be effective in bandwidth limited applications, thread prioritization must be extended to prioritize memory requests. We show how simple hardware can prioritize the running of threads in the multiple contexts, and the issuing of requests to both the local memory and the network. Simulation experiments show how thread prioritization is used in a variety of applications. Thread prioritization can improve the performance of synchronization primitives by minimizing the number of processor cycles wasted in spinning and devoting more cycles to critical threads. Thread prioritization can be used in combination with other techniques to improve cache performance and minimize cache interference between different working sets in the cache. For applications that are critical path limited, thread prioritization can improve performance by allowing processor resources to be devoted preferentially to critical threads. These experimental results show that thread prioritization is a mechanism that can be used to implement a wide range of scheduling policies.

ADAM: A Decentralized Parallel Computer Architecture Featuring Fast Thread and Data Migration and a Uniform Hardware Abstraction

The furious pace of Moore's Law is driving computer architecture into a realm where the the speed of light is the dominant factor in system latencies. The number of clock cycles to span a chip are increasing, while the number of bits that can be accessed within a clock cycle is decreasing. Hence, it is becoming more difficult to hide latency. One alternative solution is to reduce latency by migrating threads and data, but the overhead of existing implementations has previously made migration an unserviceable solution so far. I present an architecture, implementation, and mechanisms that reduces the overhead of migration to the point where migration is a viable supplement to other latency hiding mechanisms, such as multithreading. The architecture is abstract, and presents programmers with a simple, uniform fine-grained multithreaded parallel programming model with implicit memory management. In other words, the spatial nature and implementation details (such as the number of processors) of a parallel machine are entirely hidden from the programmer. Compiler writers are encouraged to devise programming languages for the machine that guide a programmer to express their ideas in terms of objects, since objects exhibit an inherent physical locality of data and code. The machine implementation can then leverage this locality to automatically distribute data and threads across the physical machine by using a set of high performance migration mechanisms. An implementation of this architecture could migrate a null thread in 66 cycles -- over a factor of 1000 improvement over previous work. Performance also scales well; the time required to move a typical thread is only 4 to 5 times that of a null thread. Data migration performance is similar, and scales linearly with data block size. Since the performance of the migration mechanism is on par with that of an L2 cache, the implementation simulated in my work has no data caches and relies instead on multithreading and the migration mechanism to hide and reduce access latencies.

Ameliorating the Overhead of Dynamic Optimization

Dynamic optimization has several key advantages. This includes the ability to work on binary code in the absence of sources and to perform optimization across module boundaries. However, it has a significant disadvantage viz-a-viz traditional static optimization: it has a significant runtime overhead. There can be performance gain only if the overhead can be amortized. In this paper, we will quantitatively analyze the runtime overhead introduced by a dynamic optimizer, DynamoRIO. We found that the major overhead does not come from the optimizer's operation. Instead, it comes from the extra code in the code cache added by DynamoRIO. After a detailed analysis, we will propose a method of trace construction that ameliorate the overhead introduced by the dynamic optimizer, thereby reducing the runtime overhead of DynamoRIO. We believe that the result of the study as well as the proposed solution is applicable to other scenarios such as dynamic code translation and managed execution that utilizes a framework similar to that of dynamic optimization.