A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2014; you can also visit the original URL.
The file type is application/pdf.
Filters
Exploiting partial operand knowledge
2003
2003 International Conference on Parallel Processing, 2003. Proceedings.
Preserved Fulltext
This paper examines existing and new approaches for exploiting early partial knowledge of an instruction's input operands for overlapping the execution of dependent instructions and resolving unknown dependences ...
In particular, we study three applications of partial operand knowledge: disambiguating loads from earlier stores, performing partial tag matching in set-associative caches, and resolving mispredicted ...
Partial Operand Bypassing Recent designs have exploited partial operand knowledge exclusively through the technique of partial operand bypassing. ...
doi:10.1109/icpp.2003.1240601
dblp:conf/icpp/MestanL03
fatcat:6zzfyoulsre4tcu32xu6mgeloi
CORSAIR: A Smart Card for Public Key Cryptosystems
[chapter]
1991
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
This allows to compute XE mod M, with 512 bit operand& in less than 15 second (0.4 set for a signature). ...
Also, input operands must be padded with one null byte to allow for a correct last result byte. Exploiting this cell for a complete algorithm is also quite cumbersome. ...
Security applications must be designed to securely exploit the capabilities of the card. ...
doi:10.1007/3-540-38424-3_35
fatcat:to6b6bbaurf7nbf5r5c5hyaguq
Highly-Parallel Montgomery Multiplication for Multi-Core General-Purpose Microprocessors
[chapter]
2012
Computer and Information Sciences III
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
To our knowledge, this is the rst work that shows with actual implementation results that Montgomery multiplication can be practically parallelized on general-purpose multi-core processors. ...
Partial Product Accumulation on a 4-Core Processor: for i = 1 to log 2 s for j = 0 to s 2 i − 1 t j ← t j + t j+ s On a 4-core processor, for performing the integer multiplication A × B, the operand A ...
Fig. 5 . 5 Partial product computation and accumulation of the partial products for the integer multiplication A × B with 6 cores. ...
doi:10.1007/978-1-4471-4594-3_48
dblp:conf/iscis/BaktirS12
fatcat:mgr32ary4ndmfjj3ueojesooqi
Integrated temporal and spatial scheduling for extended operand clustered VLIW processors
2004
Proceedings of the first conference on computing frontiers on Computing frontiers - CF'04
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
operands from other clusters without any extra cost. ...
A scheduler is responsible for resolving the conflicting requirements of aggressively exploiting the parallelism offered by hardware and limiting the communication among clusters to available slots. ...
Exploiting this knowledge, our integrated scheduler is able to schedule all the instructions in three cycles in this example. ...
doi:10.1145/977091.977155
dblp:conf/cf/NagpalS04
fatcat:vb77pehtzrfcta325m2ffelie4
High Throughput Matrix-Matrix Multiplication between Asymmetric Bit-Width Operands
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
operands, they cannot exploit the benefit of narrow bit-width of one of the operands. ...
While existing SIMD matrix multiplication instructions for symmetric bit-width operands can support operands of mixed precision by zero- or sign-extending the narrow operand to match the size of the other ...
be able to exploit the narrower bit-width of the second operand for improving the MAC throughput of matrix multiply operation. ...
arXiv:2008.00638v1
fatcat:yhs3m5ih4zdsfa7745weieccsa
An Asynchronous Floating-Point Multiplier
2012
2012 IEEE 18th International Symposium on Asynchronous Circuits and Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2012; you can also visit the original URL.
The file type is application/pdf.
To our knowledge, this is the first detailed design of a high-performance asynchronous IEEE-754 compliant double-precision floating-point multiplier. ...
A higher radix array multiplier design with operand-dependent carrypropagation adder and low handshake overhead pipeline design is presented, which yields significant energy savings while preserving the ...
They produce a pre-determined fixed number of partial products, which greatly minimizes if not fully eliminates the opportunities for exploiting data dependent optimizations. ...
doi:10.1109/async.2012.19
dblp:conf/async/SheikhM12
fatcat:t5hagnecpndotc3sqzcwk37ksm
Derive
2000
SIGPLAN notices
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Derive automatically reverse-engineers instruction encoding knowledge from the assembler by feeding it permutations of instructions and doing equation solving on the output. ...
Users must typically specify thousands of details of instruction layout, such as opcode and eld locations values, legal operands, and jump o set encodings. ...
An example format to generate single-operand instructions on the x86 is: * list of registers * regs = eax, ebp, ebx, ecx, edi, edx, esi, esp; * partial list of single operand instructions * dec, inc, neg ...
doi:10.1145/351403.351409
fatcat:4326ebet5feo5hiytb5fop73s4
Derive
2000
Proceedings of the ACM SIGPLAN workshop on Dynamic and adaptive compilation and optimization - DYNAMO '00
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Derive automatically reverse-engineers instruction encoding knowledge from the assembler by feeding it permutations of instructions and doing equation solving on the output. ...
Users must typically specify thousands of details of instruction layout, such as opcode and eld locations values, legal operands, and jump o set encodings. ...
An example format to generate single-operand instructions on the x86 is: * list of registers * regs = eax, ebp, ebx, ecx, edi, edx, esi, esp; * partial list of single operand instructions * dec, inc, neg ...
doi:10.1145/351397.351409
dblp:conf/dynamo/EnglerH00
fatcat:z3xhk6kb3fgvdcyxny3slktsua
Behavior-level observability don't-cares and application to low-power behavioral synthesis
2009
Proceedings of the 14th ACM/IEEE international symposium on Low power electronics and design - ISLPED '09
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
Our algorithm exploits knowledge about select and Boolean instructions, and allows certain forms of other knowledge, once uncovered, to be considered for stronger observability conditions. ...
To the best of our knowledge, this is the first work to use a comprehensive behavioral-level observability analysis to guide optimizations in behavioral synthesis. ...
Acknowledgments This work is partially supported by SRC under Task 1879 and NSF under grant CNS-0725354. ...
doi:10.1145/1594233.1594266
dblp:conf/islped/CongLZ09
fatcat:zclnnere7vg23pjuj3qm2q4jby
Improving XOR-Dominated Circuits by Exploiting Dependencies between Operands
2007
2007 Asia and South Pacific Design Automation Conference
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2008; you can also visit the original URL.
The file type is application/pdf.
To our best knowledge, optimisations of the type we show for multiplier-like structures have never been reported-neither manually derived, in computer arithmetic literature, nor automatically derived, ...
We show that it optimises significantly the best parallel multipliers by exploiting complex dependencies between the addenda which escape known manual optimisations. ...
A much less evident example of dependencies among partial product bits is shown in Fig. 1(b) , where, exploiting the dependency among the bits, the expression for the 4 th sum bit can be simplified as ...
doi:10.1109/aspdac.2007.358052
dblp:conf/aspdac/VermaI07
fatcat:ee7ei5a2hzettn7duvgxhqwup4
Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
2022
Physical Review Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Partial differential equations (PDEs) are concise and understandable representations of domain knowledge, which are essential for deepening our understanding of physical processes and predicting future ...
We propose the symbolic genetic algorithm to discover open-form PDEs (SGA-PDE) directly from data without prior knowledge about the equation structure. ...
Much of the domain knowledge comes from the experience of experts and the theoretical research of scholars and is expressed as various theoretical models or empirical models mostly represented by partial ...
doi:10.1103/physrevresearch.4.023174
fatcat:ijzamr53ebb3liemcws5tdbvlq
A New Control Structure for Transformation-Based Generators
[chapter]
2000
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
The AOG system introduces a new control structure that allows differing kinds of knowledge (e.g., optimization knowledge) to be anticipated, placed where it will be needed, and triggered when the time ...
A serious problem of most transformation-based generators is that they are trying to achieve three mutually antagonistic goals simultaneously: 1) deeply factored operators and operands to gain the combinatorial ...
. • It uses tag-directed transformations to exploit knowledge and operations that are ill suited to pattern-directed transformations. • It stages transformation phases so that each is organized to achieve ...
doi:10.1007/978-3-540-44995-9_1
fatcat:46ytburlafh5thzauihsweoexu
Higher Radix Squaring Operations Employing Left-to-Right Dual Recoding
2009
2009 19th IEEE Symposium on Computer Arithmetic
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2012; you can also visit the original URL.
The file type is application/pdf.
For radix-8 design the 128-bit square of a 64-bit operand can be obtained from a consolidated partial square array of just 11 rows. ...
We introduce a novel left-to-right leading digit first dual recoding of an operand for the purpose of designing the squaring operation on that operand. ...
It follows that knowledge of the p-bit normalized operand x is sufficient to determine if the normalized rounded p-bit floating point square is exact except for the particular case where p is odd and = ...
doi:10.1109/arith.2009.34
dblp:conf/arith/Matula09
fatcat:g3zucnwvfjbwdgpaylvlx5tvma
Online Type-Directed Partial Evaluation
1997
BRICS Report Series
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In this experimental work, we extend type-directed partial evaluation (a.k.a. ...
The user can also specify how to residualize an operation, by pattern-matching over the operands. Operators may be pure or have a computational effect. ...
For an other example, in Sussman's Scheme-programming environment today, all primitive operators are instrumented to attempt algebraic simplifications over their operands. 3 To the best of our knowledge ...
doi:10.7146/brics.v4i53.19274
fatcat:f7awleju6fhpljel7cjcu7gfqy
Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Partial differential equations (PDEs) are concise and understandable representations of domain knowledge, which are essential for deepening our understanding of physical processes and predicting future ...
We propose the symbolic genetic algorithm (SGA-PDE) to discover open-form PDEs directly from data without prior knowledge about the equation structure. ...
Acknowledgements This work is partially funded by the Shenzhen Key Laboratory of Natural Gas Hydrates (Grant No. ...
arXiv:2106.11927v1
fatcat:3b77fga6anfdhb5jnupln3ymau
« Previous
Showing results 1 — 15 out of 6,864 results