The Experts below are selected from a list of 123 Experts worldwide ranked by ideXlab platform
Yoshiharu Ishikawa - One of the best experts on this subject based on the ideXlab platform.
-
design and evaluation of signature File Organization incorporating vertical and horizontal decomposition schemes
Database and Expert Systems Applications, 1996Co-Authors: Hiroyuki Kitagawa, Noriyasu Watanabe, Yoshiharu IshikawaAbstract:Signature Files are known as promising facilities to speed up accesses to large information repositories in database and information retrieval systems. This paper presents a new signature File Organization method, named Partitioned Frame-Sliced Signature File (P-FSSF), and studies its performance. P-FSSF incorporates both vertical and horizontal decomposition schemes to reduce page accesses required to look up signatures. In addition, P-FSSF is flexible enough to have its concrete Organization tuned to real application environments. We develop formulas to estimate the retrieval cost of P-FSSF in the context of the general set-valued object retrieval. Also, formulas to tell the update and storage costs are derived. Then, the processing cost of P-FSSF is shown to be lower than the other existing signature File Organizations in general. We also show that Partitioned Bit-Sliced Signature File (P-BSSF), which is a special case of P-FSSF, is appropriate Organization in most probable cases through the study of the optimal parameter values for P-FSSF.
-
DEXA - Design and Evaluation of Signature File Organization Incorporating Vertical and Horizontal Decomposition Schemes
Lecture Notes in Computer Science, 1996Co-Authors: Hiroyuki Kitagawa, Noriyasu Watanabe, Yoshiharu IshikawaAbstract:Signature Files are known as promising facilities to speed up accesses to large information repositories in database and information retrieval systems. This paper presents a new signature File Organization method, named Partitioned Frame-Sliced Signature File (P-FSSF), and studies its performance. P-FSSF incorporates both vertical and horizontal decomposition schemes to reduce page accesses required to look up signatures. In addition, P-FSSF is flexible enough to have its concrete Organization tuned to real application environments. We develop formulas to estimate the retrieval cost of P-FSSF in the context of the general set-valued object retrieval. Also, formulas to tell the update and storage costs are derived. Then, the processing cost of P-FSSF is shown to be lower than the other existing signature File Organizations in general. We also show that Partitioned Bit-Sliced Signature File (P-BSSF), which is a special case of P-FSSF, is appropriate Organization in most probable cases through the study of the optimal parameter values for P-FSSF.
M. Valero - One of the best experts on this subject based on the ideXlab platform.
-
a content aware integer register File Organization
International Symposium on Computer Architecture, 2004Co-Authors: Gonzalez Gonzalez, A. Cristal, Alexander Veidenbaum, D. Ortega, M. ValeroAbstract:A register File is a critical component of a modernsuperscalar processor.It has a large number of entriesand read/write ports in order to enable high levels ofinstruction parallelism.As a result, the register File'sarea, access time, and energy consumption increasedramatically, significantly affecting the overallsuperscalar processor's performance and energyconsumption.This is especially true in 64-bitprocessors.This paper presents a new integer register FileOrganization, which reduces energy consumption,area, and access time of the register File with a minimal effect on overall IPC.This is accomplished byexpoiting a new concept, partial value locality, whichis defined as occurence of mutiple live valueinstances identical in a subset of their bits.A possibleimplementation of the new register File is describedand shown to obtain proposed optimized register Filedesigns.Overall, an energy reduction of over 50%, a18% decreas in area, and a 15% reduction in the accesstime are achieved in the new register File.Theenergy and area savings are achieved with a 1.7%reduction in IPC for integer applications and anegligible 0.3% in numerical applications, assumingthe same clock frequency.A performance increase ofup to 13% is possible if the clcok frequency can beincreases due to a reduction in the register File accesstime.This approach enables other, very promisingoptimizations, three of which are outlined in the paper.
-
A content aware integer register File Organization
Proceedings. 31st Annual International Symposium on Computer Architecture 2004., 1Co-Authors: Ruben Gonzalez, Alexander Veidenbaum, A. Cristal, D. Ortega, M. ValeroAbstract:A register File is a critical component of a modern superscalar processor. It has a large number of entries and read/write ports in order to enable high levels of instruction parallelism. As a result, the register File's area, access time, and energy consumption increase dramatically, significantly affecting the overall superscalar processor's performance and energy consumption. This is especially true in 64-bit processors. This paper presents a new integer register File Organization, which reduces energy consumption, area, and access time of the register File with a minimal effect on overall IPC. This is accomplished by exploiting a new concept, partial value locality, which is defined as occurrence of multiple live value instances identical in a subset of their bits. A possible implementation of the new register File is described and shown to obtain proposed optimized register File designs. Overall, an energy reduction of over 50%, a 18% decrease in area, and a 15% reduction in the access time are achieved in the new register File. The energy and area savings are achieved with a 1.7% reduction in IPC for integer applications and a negligible 0.3% in numerical applications, assuming the same clock frequency. A performance increase of up to 13% is possible if the clock frequency can be increases due to a reduction in the register File access time. This approach enables other, very promising optimizations, three of which are outlined in the paper.Peer ReviewedPostprint (published version
-
IPDPS - Hierarchical clustered register File Organization for VLIW processors
Proceedings International Parallel and Distributed Processing Symposium, 1Co-Authors: Javier Zalamea, Josep Llosa, Eduard Ayguadé, M. ValeroAbstract:Technology projections indicate that wire delays will become one of the biggest constraints in future microprocessor designs. To avoid long wire delays and therefore long cycle times, processor cores must be partitioned into components so that most of the communication is done locally. In this paper, we propose a novel register File Organization for VLIW cores that combines clustering with a hierarchical register File Organization. Functional units are organized in clusters, each one with a local first level register File. The local register Files are connected to a global second level register File, which provides access to memory. All intercluster communications are done through the second level register File. This paper also proposes MIRS-HC, a novel modulo scheduling technique that simultaneously performs instruction scheduling, cluster selection, inserts communication operations, performs register allocation and spill insertion for the proposed Organization. The results show that although more cycles are required to execute applications, the execution time is reduced due to a shorter cycle time. In addition, the combination of clustering and hierarchy provides a larger design exploration space that trades-off performance and technology requirements.
Fazli Can - One of the best experts on this subject based on the ideXlab platform.
-
analysis of multiterm queries in a dynamic signature File Organization
International ACM SIGIR Conference on Research and Development in Information Retrieval, 1993Co-Authors: Deniz Aktug, Fazli CanAbstract:Our analysis combines the concerns of signature extraction and signature File Organization which have usually been treated as separate issues. We also relax the uniform frequency and single term query assumptions and provide a comprehensive analysis for multiterm query environments where terms can be classified based on their query and database occurrence frequencies. The performance of three superimposed signature generation schemes is explored as they are applied to one dynamic signature File Organization based on linear hashing: Linear Hashing with Superimposed Signatures (LHSS). First scheme (SM) allows all terms set the same number of bits regardless of their discriminatory power whereas the second and third methods (MMS and MMM) emphasize the terms with high query and low database occurrence frequencies. Of these three schemes, only MMM takes the probability distribution of the number of query terms into account in finding the optimal mapping strategy. Derivation of performance evaluation formulas is provided together with the results of various experimental settings. Suggestions as to how to implement the given techniques in real life cases are also provided. Results indicate that MMM outperforms the other methods as the gap between the discriminatory power of the terms gets larger. The absolute value of the savings provided by MMM reach a maximum for the high query weight case. However, the extra savings decline sharply for high weight and moderately for the low weight queries with the increase in database size.
-
SIGIR - Analysis of multiterm queries in a dynamic signature File Organization
Proceedings of the 16th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '93, 1993Co-Authors: Deniz Aktug, Fazli CanAbstract:Our analysis combines the concerns of signature extraction and signature File Organization which have usually been treated as separate issues. We also relax the uniform frequency and single term query assumptions and provide a comprehensive analysis for multiterm query environments where terms can be classified based on their query and database occurrence frequencies. The performance of three superimposed signature generation schemes is explored as they are applied to one dynamic signature File Organization based on linear hashing: Linear Hashing with Superimposed Signatures (LHSS). First scheme (SM) allows all terms set the same number of bits regardless of their discriminatory power whereas the second and third methods (MMS and MMM) emphasize the terms with high query and low database occurrence frequencies. Of these three schemes, only MMM takes the probability distribution of the number of query terms into account in finding the optimal mapping strategy. Derivation of performance evaluation formulas is provided together with the results of various experimental settings. Suggestions as to how to implement the given techniques in real life cases are also provided. Results indicate that MMM outperforms the other methods as the gap between the discriminatory power of the terms gets larger. The absolute value of the savings provided by MMM reach a maximum for the high query weight case. However, the extra savings decline sharply for high weight and moderately for the low weight queries with the increase in database size.
Hiroyuki Kitagawa - One of the best experts on this subject based on the ideXlab platform.
-
design and evaluation of signature File Organization incorporating vertical and horizontal decomposition schemes
Database and Expert Systems Applications, 1996Co-Authors: Hiroyuki Kitagawa, Noriyasu Watanabe, Yoshiharu IshikawaAbstract:Signature Files are known as promising facilities to speed up accesses to large information repositories in database and information retrieval systems. This paper presents a new signature File Organization method, named Partitioned Frame-Sliced Signature File (P-FSSF), and studies its performance. P-FSSF incorporates both vertical and horizontal decomposition schemes to reduce page accesses required to look up signatures. In addition, P-FSSF is flexible enough to have its concrete Organization tuned to real application environments. We develop formulas to estimate the retrieval cost of P-FSSF in the context of the general set-valued object retrieval. Also, formulas to tell the update and storage costs are derived. Then, the processing cost of P-FSSF is shown to be lower than the other existing signature File Organizations in general. We also show that Partitioned Bit-Sliced Signature File (P-BSSF), which is a special case of P-FSSF, is appropriate Organization in most probable cases through the study of the optimal parameter values for P-FSSF.
-
DEXA - Design and Evaluation of Signature File Organization Incorporating Vertical and Horizontal Decomposition Schemes
Lecture Notes in Computer Science, 1996Co-Authors: Hiroyuki Kitagawa, Noriyasu Watanabe, Yoshiharu IshikawaAbstract:Signature Files are known as promising facilities to speed up accesses to large information repositories in database and information retrieval systems. This paper presents a new signature File Organization method, named Partitioned Frame-Sliced Signature File (P-FSSF), and studies its performance. P-FSSF incorporates both vertical and horizontal decomposition schemes to reduce page accesses required to look up signatures. In addition, P-FSSF is flexible enough to have its concrete Organization tuned to real application environments. We develop formulas to estimate the retrieval cost of P-FSSF in the context of the general set-valued object retrieval. Also, formulas to tell the update and storage costs are derived. Then, the processing cost of P-FSSF is shown to be lower than the other existing signature File Organizations in general. We also show that Partitioned Bit-Sliced Signature File (P-BSSF), which is a special case of P-FSSF, is appropriate Organization in most probable cases through the study of the optimal parameter values for P-FSSF.
Per Stenström - One of the best experts on this subject based on the ideXlab platform.
-
ICPP - A GPU Register File using Static Data Compression
2020Co-Authors: Alexandra Angerd, Erik Sintorn, Per StenströmAbstract:GPUs rely on large register Files to unlock thread-level parallelism for high throughput. Unfortunately, large register Files are power hungry, making it important to seek for new approaches to improve their utilization. This paper introduces a new register File Organization for efficient register-packing of narrow integer and floating-point operands designed to leverage on advances in static analysis. We show that the hardware/software co-designed register File Organization yields a performance improvement of up to 79%, and 18.6%, on average, at a modest output-quality degradation.
-
A GPU Register File using Static Data Compression
49th International Conference on Parallel Processing - ICPP, 2020Co-Authors: Alexandra Angerd, Erik Sintorn, Per StenströmAbstract:GPUs rely on large register Files to unlock thread-level parallelism for high throughput. Unfortunately, large register Files are power hungry, making it important to seek for new approaches to improve their utilization. This paper introduces a new register File Organization for efficient register-packing of narrow integer and floating-point operands designed to leverage on advances in static analysis. We show that the hardware/software co-designed register File Organization yields a performance improvement of up to 79%, and 18.6%, on average, at a modest output-quality degradation.