Preamble “Post-amble” Block Execution: 3 Detail Observing Block Observing Block “Post-amble” “Post-amble” 3 Observing Block Observing Block ok Measurement Set ready “Post-amble” EVLA Data Processing PDR Observing Observing Block Block Observing Observing Block Block Failed! Preamble “Post-amble” Preamble ok ?4 5 Preamble ready Preamble Observing Observing Block Block Observing Observing Block Block Observing Block Observing Block Measurement Set “Post-amble” “Post-amble” Preamble Preamble “Post-amble” Measurement Set “Post-amble” “Post-amble” “Post-amble” July 18 - 19, 2002 2 2 Observing Observing Block Block Block Observing Observing Observing Block Block ok Archive: Preamble Observing Block Observing Block 34 ready Preamble “Post-amble” 1 3 Observing Block Observing Observing Block Block Observing Block Observing Observing Block Block ready Preamble Execution: Preamble ready Observing Observing Block Block Observing Observing Block Block Preamble Observing Block Observing Block 22 “Post-amble” “Post-amble” Preamble Preamble 1 “Post-amble” Preamble Input Queue: ok Measurement Set Boyd Waters 13
View full slide show




Transparent Scalability  Hardware is free to assign blocks to any SM (processor)  A kernel scales across any number of parallel processors Device Kernel grid Device Block 0 Block 1 Block 2 Block 3 Block 0 Block 1 Block 4 Block 5 Block 6 Block 7 Block 2 Block 3 Block 4 Block 5 Block 6 Block 7 26 time Block 0 Block 1 Block 2 Block 3 Block 4 Block 5 Block 6 Block 7 Each block can execute in any order relative to other blocks.
View full slide show




Transparent Scalability Hardware is free to assign blocks to any processor at any time  A kernel scales across any number of parallel processors Device Device Kernel grid Block 0 Block 1 Block 2 Block 3 Block 0 Block 2 Block 1 Block 3 Block 4 Block 5 Block 6 Block 7  Block 4 Block 5 Block 6 Block 7 time Block 0 Block 1 Block 2 Block 3 Block 4 Block 5 Block 6 Block 7 Each block can execute in any CUDA Tools and Threads – Slide order relative 69
View full slide show




Block Execution Observing Block Observing Block 3 “Post-amble” Preamble Observing Block Observing Block “Post-amble” Preamble Observing Block Observing Block “Post-amble” EVLA Data Processing PDR Preamble Observing Observing Block Block Observing Observing Block Block “Post-amble” Observing Block Observing Block Preamble “Post-amble” 2 2 3 “Post-amble” July 18 - 19, 2002 “Post-amble” Observing Block Observing Block Preamble Preamble 1 “Post-amble” Preamble Execution: Observing Block Observing Block Preamble Observing Block Observing Block 2 “Post-amble” Preamble 1 “Post-amble” Preamble Input Queue: Observing Block Observing Block Boyd Waters 12
View full slide show




Reducing Memory Overhead    Sub-block 0 Protect two I-blocks with one signature Signature produced by XORing signatures of all sub-blocks Need both blocks to calculate signature, other block may or may not be in cache Miss on Condition Action Block A Block B in cache Fetch block A and Signature Block B not in cache Fetch blocks A and B (stored in IOB) and Signature Block B Block A in cache Fetch block B and Signature Block A not in cache Fetch A, B, and Signature Sub-block 1 Block A Sub-block 2 Sub-block 3 Block B Signature Instruction Opportunity Buffer Tag I-block Valid Flag 0 1 ... m-1 22
View full slide show




Fully Associative Cache 5-bitoffset offsetsupports supports 5-bit 32bytes bytesper perblock block 32 Fully-associative cache does not need Set Index field. Index=0 corresponding to one set. Address Addressisispartitioned partitionedinto into • Block address • Block address • Block offset which identifies the data • Block offset which identifies the data within withinthe theblock block • Block can go anywhere in the cache • Block can go anywhere in the cache • Must examine all blocks • Must examine all blocks • Each cache block has a Tag • Each cache block has a Tag • Tag is compared to block number • Tag is compared to block number • If one of the blocks has Tag=Block # • If one of the blocks has Tag=Block # we wehave haveaahit hit • Need a comparator per cache block • Need a comparator per cache block • Comparisons performed in parallel • Comparisons performed in parallel • • Spring 2016, arz CPE555A – Real-Time Embedded Systems Stevens Institute of Technology 42
View full slide show




Block vs Stream Ciphers  block ciphers process messages in blocks, each of which is then en/decrypted  like a substitution on very big characters  64-bits or more  stream ciphers process messages a bit or byte at a time when en/decrypting  many current ciphers are block ciphers  broader range of applications
View full slide show




 Principles of Ciphers    Chapter 8 Cryptograhic Building Blocks Most ciphers are block ciphers: they are defined to take as input a plaintext block of a certain fixed size, typically 64 to 128 bits. Using a block cipher to encrypt each block independently—known as electronic codebook (ECB) mode encryption—has the weakness that a given plaintext block value will always result in the same ciphertext block. Hence recurring block values in the plaintext are recognizable as such in the ciphertext, making it much easier for a cryptanalyst to break the cipher. 16
View full slide show




Block-Based Scheduler Telescope sees ONE BLOCK AT A TIME: Block Queue Observing Block Observing Block “Post-amble” Preamble “Post-amble” Preamble “Post-amble” Preamble Observing Block Observing Block Observing Block Observing Block Implications: “ready for next block” •Simplifies the telescope state data “here it is” “Post-amble” Preamble Telescope Observing Block Observing Block July 18 - 19, 2002 •Telescope reports block execution status back to the block queue •All “observing logic” is maintained by the Block Queue EVLA Data Processing PDR Boyd Waters 11
View full slide show




DMA Transfer Modes   Single/Repeated single modes: each byte/word transfer requires a separate trigger Block/Repeated block modes: a transfer of a complete block of data occurs after one trigger   CPU is halted until the complete block has been transferred Burst-block/Repeated burst-block modes: transfers are block transfers with CPU activity interleaved.  CPU executes 2 MCLK cycles after every four byte/word transfers of the block resulting in 20% CPU execution capacity CPE 323 7
View full slide show




Les dimensions opérationnelles du CDMT Dimension Gé n érale Te chnique Organisatione ll e Documentation Portée • • Type budgétaire • Niveau du gouve rnemen t Horizon Cadre m acroé conom iqu e des opé rations fiscales (MFF) Cadre des dépen ses sectorie ll es (SE F) Fixation des priorités budgé taires Organisation du pe rsonne l de ge stion • D iff usion documen taire Suivi et sources du financemen t Elements clefs Ven til ation par secteu r Sépa ration des dépen ses par budget de fonctionnemen t et budget de capital Ven til ation des projets par qualité (écon om ique , fonctionne ll e, géog raphique , program ma tion) Niveau – central,rég ional,local(ycomp risle s proportions partagées ) • • • L’é chéance des projets par année budgétaire Ven til ation du cadre quantitatif Ven til ation du contenu (prévisions, cibles, plafonds et contraintes au niveau m acroé conom ique et au niveaux sectorie ls) • • Articulation du cadre politique et stratégoqie Ven til ation des dépense s par source du financem ent des projets existants e t pour des projets proposés sous le CD MT • Articulation de l’ encadre m ent budgétaire (ve ntilation des proje ts par rubrique et l es dates comp rises) Docum entation des étapes d’adoption et d’autorisation Articulation des rôle s par el gouve rnemen t cen tral ainsi que ces des organisme s sectorie ls Organigram me de la structure du pe rsonnelCD MT Ven til ation des étape s du program m e CDMT des réforme s Articulation des rôle s des organisme s de la socié té civil e Docum entation des m odalité s de com mun ication et de diffusion aux niveaux interne s et externe s Suivi des activité s sectorie ll es par mi nistè re Articulation du niveau d’autonomi e sectorie ll e Suivi des budgéts par des mi nistè res par secteur e t par tranche budgé taire Ven til ation des program m es de forma tion CDMT • • • • • • • • • •
View full slide show




Symmetric-Key Cryptology Also known as single-key, private-key, one-key and secret-key Method of encoding where both the sender and receiver of a message hold the same key which is needed to decode the message, and involving the use of block ciphers and stream ciphers. Encoding through Block Ciphers – Uses a fixed-length groups of bits, known as a block. Will take a plaintext as an input and using a secret key encode the text, and output ciphertext of the same bit size as the input Encoding through Stream Ciphers - plaintext digits are encrypted one at a time, with the transformation of successive digits varying during the encryption
View full slide show




Chapter 8 Cryptograhic Building Blocks  Symmetric Key Ciphers   NIST also standardized the cipher Triple DES (3DES), which leverages the cryptanalysis resistance of DES while in effect increasing the key size. A 3DES key has 168 (= 3256) independent bits, and is used as three DES keys;    let’s call them DES-key1, DES-key2, and DES-key3. 3DES-encryption of a block is performed by first DESencrypting the block using DES-key1, then DES-decrypting the result using DES-key2, and finally DES-encrypting that result using DES-key3. Decryption involves decrypting using DES-key3, then encrypting using DES-key2, then decrypting using DES-key1 22
View full slide show