Texas Instruments, TMS320C6000 CPU and Instruction Set Reference Guide, June 2004, http://focus.ti.com/lit/ug/spru189f/spru189f. pdf. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
HDLGen: Architecture Description Language driven HDL - Generation For Pipelined (Correct)
.... automatic software toolkit generation, and design space exploration for a wide range (DSP, VLIW, EPIC, Superscalar) of programmable embedded systems (processor, co processor, and memory subsystem) The EXPRESSION ADL has been used to generate compiler, simulator, and assembler for the TI C6x [25], PowerPC [5] ARM [26] Hitachi SH3 [27] ST100 [28] Sun UltraSparc III [7] and MIPS R10K [6] architectures. The ADL can be used to perform top down validation of programmable embedded systems ( 15] 20] 17] In this paper, we demonstrate the capability of the framework to perform rapid ....
....and there are HDL implementations available for the DLX processor that we can use for comparison purposes. Second, it has many interesting features viz. fragmented pipelines, multi cycle units etc. that are representative of many commercial pipelined processor architectures such as TI C6x [25], PowerPC [5] and MIPS R10K [6] 8.1 Experimental Setup Figure 7 shows the DLX processor pipeline that we have captured in our framework. The DLX architecture has five pipeline stages: fetch, decode, execute, memory, and writeback. The execute stage has four parallel paths: integer ALU, 7 stage ....
Texas Instruments. TMS320C6201 CPU and Instruction Set Reference Guide, 1998.
An Innovative Low-Power High-Performance.. - Moreno, Zyuban.. (2003) (2 citations) (Correct)
.... and address units, respectively) Parallelism is achieved by a combination of multiple instructions operating on different registers, with the ability to allocate multiple data items on a single register [very long instruction words (VLIW) and SIMD with packed data] # The Texas Instruments C6x [4] is also a multiple issue, statically scheduled processor with a homogeneous register space partitioned among two clusters, in which heterogeneous functional units use only the registers available within the cluster. As in SC140, data parallelism is also achieved by a combination of multiple ....
Texas Instruments, Inc., TMS320C6000 CPU and Instruction Set Reference Guide, 2000; see http:// www-s.ti.com/sc/psheets/spru189f/spru189f.pdf.
An Innovative Low-Power High-Performance.. - Moreno, Zyuban.. (2002) (2 citations) (Correct)
.... its corresponding type (data units and address units, respectively) Parallelism is achieved by a combination of multiple instructions operating on different registers, with the ability to allocate multiple data items on a single register (VLIW and SIMD with packed data) Texas Instruments C6x [4] is also a multiple issue, statically scheduled processor with a homogeneous register space partitioned among two clusters, in which heterogeneous functional units use only the registers available within the cluster. As in SC140, data parallelism is also achieved by a combination of multiple ....
Texas Instruments, Inc., TMS320C6000 CPU and instruction set reference guide, 2000.
Parallel Interleaving On Parallel Dsp Architectures - Richter, Fettweis (2002) (Correct)
....Slice0 Slice1 Slice2 SliceP 2 SliceP 1 DSP Core AGU PCU Inter Connectivity Unit (ICU) Fig. 2. Block schematic of the parallel DSP architecture 2.2. Parallel DSP Architecture Parallel DSP architectures have become common as enabling hardware for demanding signal processing tasks [7] [8]. In this work a generic DSP architecture approach called Concept on Application Tailored Signal processors (CATS) followed at TU Dresden is applied [9] The concept has been proofed by a standard cell prototype [10] and its basic architecture is depicted in Fig. 2. As illustrated in the block ....
Texas Instruments, TMS320C6000 CPU and Instruction Set Reference Guide, Oct. 2000, Literature Number SPRU189F.
Optimizing a 3D Image Reconstruction Algorithm.. - Aa, Eeckhout.. (Correct)
....is calculated. 3 Architectures In this section, we briefly describe the architectures of the Texas Instruments TMS320C67 and the Alpha 21164 on which the optimizations for the 3D image reconstruction algorithm were done. 3. 1 Texas Instruments TMS320C6701 The Texas Instruments TMS320C6701 [SPRU189D, 1999] C67) is a 32 bit floating point VLIW DSP processor which is capable of executing at most eight 32 bit instructions per cycle at a clock rate of 167 MHz. Six of these eight instruction slots can be filled with floating point operations. The processor has 32 general purpose registers and is ....
....: O; j m; j ) Y; after transformation X1; for (i = O; i n; i ) for(j: O; j m; j ) Y; X2; Figure 8: Filling up branch delay slots. pipelines of the floating point functional units are much deeper (up to 10 execution stages versus 5 stages for integer operations [SPRU189D, 1999] Fixed point variables have the same or better precision than their floating point counterparts with the same number of bits, but their dynamic range is limited. In cases where the actual range of the variable was limited, we could replace the use of floating point variables by integer ....
Texas Instruments. TMS320C6000 CPU and instruction set refer- ence guide. Manual number SPRU189D.
Coprosessor Codesign for Programmable Architectures - Mishra, Rousseau, Dutt.. (Correct)
....support new operation(s) However, the last two options are feasible only when the modification in the processor core is possible without violating area, timing and power constraints. The first one is the only alternative when processor does not support certain operations e. g, division in TI C6x ([20]) To evaluate the effect of using coprocessor, designers need to perform design space exploration. However, to enable rapid design space exploration there is a need for (i) describing 3 the embedded system (processor, coprocessor, memory subsystem) in higher level of abstraction, and (ii) ....
....its match to the target applications. 4 Coprocessor description in EXPRESSION In order to explicitly describe the coprocessor in EXPRESSION, we need to capture both the structure and behavior of the coprocessor. We illustrate how we capture coprocessor description in EXPRESSION using the TI C6x [20] architecture. Figure 2 shows a simplified model of the TI C6211 architecture. The pipeline paths are shown using solid lines whereas the data transfer paths are shown using dotted lines. The TI C6211 is an 8 way VLIW DSP processor with a deep pipeline, composed of 4 fetch stages (PG, PS, PR, PW) ....
Texas Instruments. TMS320C6201 CPU and Instruction Set Reference Guide, 1998.
Enhancing Loop Buffering of Media and Telecommunications.. - Sias, Hunter, Hwu (2001) (2 citations) (Correct)
....von Neumann architecture, specially tailored complex instruction sets are being replaced with deeply pipelined, statically scheduled LIW and VLIW designs, allowing greater throughput and generality with lower hardware overhead. Given the impact of proportionally long (generally 3 to 5 cycle [8]) branch penalties on the performance of tight DSP loops, architects have also begun to include forms of conditional execution and loop support into their instruction sets. Consensus on the best implementation has not yet been reached. Texas Instruments C6x line, one of the first DSP families ....
....into their instruction sets. Consensus on the best implementation has not yet been reached. Texas Instruments C6x line, one of the first DSP families to adopt a VLIW style and a 32 bit datapath, architects eight issue slots and provides for operation execution to be guarded by condition codes [8]. Four bits of each opcode indicate which of five condition registers guards the instruction and whether a zero or a non zero value causes the instruction to be nullified. The C6x line exposes five branch delay slots rather than incorporating a special mechanism for zero overhead looping, the ....
Texas Instruments Incorporated, TMS320C6000 CPU and Instruction Set Reference Guide, Mar. 1999.
Floating-Point to Fixed-Point Compilation and Embedded.. - Aamodt (2001) (Correct)
....on most desktop systems. It is probably for these reasons that the original implementors of UTDSP did not include an extended precision accumulator. It is interesting to note that the Texas Instruments TMS320C62x xed point VLIW digital signal processor also lacks dedicated accumulator bu ers [Tex99a] On the other hand, while sporting a 32 bit datapath and register le, the C62x only provides 16 16 bit integer multiplication operations. One way to interpret this is that to solve the allocation problem, the designers of the C62x made all the registers double precision. In this case ....
Texas Instruments. TMS320C6000 CPU and Instruction Set Reference Guide, March 1999. Literature Number: SPRU189D.
Memory Aware Compilation Through Accurate Timing Extraction - Grun, Dutt, Nicolau (2000) (1 citation) (Correct)
....based on the Texas Instruments TMS320C6201VLIW DSP, with one IBM0316409C synchronous DRAM [11] block exhibiting page mode and burstmode access, and 2 banks. The TIC6201 is an integer point 8way VLIW processor, with no data cache, as explained earlier. The External Memory Interface (EMIF) [20] allows the processor to program information regarding the memory modules attached, and control them through a set of control registers. We assume the SDRAM has the capability to precharge a specific memory blank (using the DEAC command) or both memory banks at the same time (using the DCAB ....
Texas Instruments. TMS320C6201 CPU and Instruction Set Reference Guide.
Reduced Code Size Modulo Scheduling in the Absence of.. - Llosa, Freudenberger (2002) (1 citation) Self-citation (Instruction) (Correct)
No context found.
Texas Instruments. TMS320C6000 CPU and instruction set reference guide. March 1999.
Static Resource Models For Code-Size Efficient Embedded.. - Zhao, Mesman, Basten (2002) Self-citation (Instruction) (Correct)
No context found.
Texas Instruments, TMS320C6000 CPU and instruction set reference guide,
ReXSim: A Retargetable Framework for Instruction-Set.. - Reshadi, Mishra.. (2003) Self-citation (Instruction) (Correct)
....an embedded application can be implemented on a variety of different architectures including microprocessors, DSPs and reconfigurable platforms. Besides, there are emerging architectures with combined features of classical architectures such as DSP, VLIW and Superscalar. For example, the TI C6x #[19] family combines DSP and VLIW features and the Intel Itanium combines features of VLIW and superscalar architectures. To enable rapid design space exploration of such architectures, designers need a way of specifying a wide variety of processor memory features and automatic generation of ....
Texas Instruments, TMS320C6201 CPU and Instruction Set Reference Guide, 1998.
Partitioning Variables across Register Windows to.. - Ravindran.. (2005) (Correct)
No context found.
Texas Instruments, TMS320C6000 CPU and Instruction Set Reference Guide, June 2004, http://focus.ti.com/lit/ug/spru189f/spru189f. pdf.
Automatic Formal Veri - Cation For Scheduled (Correct)
No context found.
Texas Instruments. TMS320C6000 CPU and Instruction Set Reference Guide, October 2000. Literature Number SPRU189F.
Data- and Task Parallel Image Processing on a Mixed.. - Caarls, Jonker.. (2004) (Correct)
No context found.
Texas Instruments. TMS320C6000 CPU and Instruction Set Reference Guide, September 2000.
Loop Fusion for Clustered VLIW Architectures - Yi Qian Science (Correct)
No context found.
Texas Instruments. TMS320C6000 CPU and Instruction Set Reference Guide, 2000. literature number SPRU189.
Optimizing Loop Performance for Clustered VLIW Architectures - Qian, Carr, Sweany (2002) (2 citations) (Correct)
No context found.
Texas Instruments. TMS320C6000 CPU and Instruction Set Reference Guide, 2000. literature number SPRU189.
RuDRA: A Reactive Dissipation Reducing Architecture - Rodrigues (2003) (Correct)
No context found.
Texas Instruments Inc. TMS320C6000 CPU and instruction set reference guide, 2000.
Programming The Sandbridge Multithreaded Processor - Sanjay Jinturkar John (2003) (Correct)
No context found.
Texas Instruments, "TMS320C6000 CPU and Instruction Set Reference guide, Oct 2000 .
Architecture Description Language driven Validation of Dynamic - Behavior In Pipelined (Correct)
No context found.
Texas Instruments. TMS320C6201 CPU and Instruction Set Reference Guide, 1998.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC