The TMS320C64x™ DSPs) (including the SM32C64xT devices) are the highest-performance fixed-point DSP generation in the TMS320C6000™ DSP platform. The TMS320C64x™ (C64x™) device is based on the second-generation high-performance, advanced VelociTI™ very-long-instruction-word (VLIW) architecture (VelociTI.2™) developed by Texas Instruments (TI), making these DSPs an excellent choice for wireless infrastructure applications. The C64x™ is a code-compatible member of the C6000. DSP platform.

With performance of up to 8000 million instructions per second (MIPS) at a clock rate of 1 GHz, the C64x devices offer cost-effective solutions to high-performance DSP programming challenges. The C64x DSPs possess the operational flexibility of high-speed controllers and the numerical capability of array processors. The C64x™ DSP core processor has 64 general-purpose registers of 32-bit word length and eight highly independent functional units—two multipliers for a 32-bit result and six arithmetic logic units (ALUs)— with VelociTI.2™ extensions. The VelociTI.2™ extensions in the eight functional units include new instructions to accelerate the performance in key applications and extend the parallelism of the VelociTI™ architecture. The C64x can produce four 16-bit multiply-accumulates (MACs) per cycle for a total of 4000 million MACs per second (MMACS), or eight 8-bit MACs per cycle for a total of 8000 MMACS. The C64x DSP also has application-specific hardware logic, on-chip memory, and additional on-chip peripherals similar to the other C6000™ DSP platform devices.

The C6416T device has two high-performance embedded coprocessors [Viterbi Decoder Coprocessor (VCP) and Turbo Decoder Coprocessor (TCP)] that significantly speed up channel-decoding operations on-chip. The VCP operating at CPU clock divided-by-4 can decode over 833 7.95-Kbps adaptive multi-rate (AMR) [K = 9, R = 1/3] voice channels. The VCP supports constraint lengths K = 5, 6, 7, 8, and 9, rates R = 1/2, 1/3, and 1/4, and flexible polynomials, while generating hard decisions or soft decisions. The TCP operating at CPU clock divided-by-2 can decode up to sixty 384-Kbps or ten 2-Mbps turbo encoded channels (assuming 6 iterations). The TCP implements the max*log-map algorithm and is designed to support all polynomials and rates required by Third-Generation Partnership Projects (3GPP and 3GPP2), with fully programmable frame length and turbo interleaver. Decoding parameters such as the number of iterations and stopping criteria are also programmable. Communications between the VCP/TCP and the CPU are carried out through the EDMA controller.

The C64x uses a two-level cache-based architecture and has a powerful and diverse set of peripherals. The Level 1 program cache (L1P) is a 128K-bit direct mapped cache and the Level 1 data cache (L1D) is a 128K-bit 2-way set-associative cache. The Level 2 memory/cache (L2) consists of an 8M-bit memory space that is shared between program and data space. L2 memory can be configured as mapped memory or combinations of cache (up to 256K bytes) and mapped memory. The peripheral set includes three multichannel buffered serial ports (McBSPs); an 8-bit Universal Test and Operations PHY Interface for Asynchronous Transfer Mode (ATM) Slave [UTOPIA Slave] port; three 32-bit general-purpose timers; a user-configurable 16-bit or 32-bit host-port interface (HPI16/HPI32); a peripheral component interconnect (PCI); a general-purpose input/output port (GPIO) with 16 GPIO pins; and two glueless external memory interfaces (64-bit EMIFA and 16-bit EMIFB), both of which are capable of interfacing to synchronous and asynchronous memories and peripherals.

The C64x has a complete set of development tools which includes: an advanced C compiler with C64x-specific enhancements, an assembly optimizer to simplify programming and scheduling, and a Windows™ debugger interface for visibility into source code execution.

• Controlled Baseline
  • One Assembly/Test Site, One Fabrication Site
• Extended Temperature Performance of up to –40°C to 105°C
• Enhanced Diminishing Manufacturing Sources (DMS) Support
• Enhanced Product-Change Notification
• Qualification Pedigree
• Highest-Performance Fixed-Point DSPs
  • 1.67-/1.39-/1.17-/1-ns Instruction Cycle
  • 600-/720-/850-MHz, 1-GHz Clock Rate
  • Eight 32-Bit Instructions/Cycle
  • Twenty-Eight Operations/Cycle
  • 4800, 5760, 6800, 8000 MIPS
  • Fully Software-Compatible With C62x™
  • C6414/15/16 Devices Pin-Compatible
• VelociTI.2™ Extensions to VelociTI™ Advanced Very-Long-Instruction-Word (VLIW) TMS320C64x™ DSP Core
  • Eight Highly Independent Functional Units With VelociTI.2™ Extensions
  • Non-Aligned Load-Store Architecture
  • 64 32-Bit General-Purpose Registers
  • Instruction Packing Reduces Code Size
  • All Instructions Conditional
• VCP
  • Supports Over 833 7.95-Kbps AMR
  • Programmable Code Parameters
• TCP
  • Supports up to 10 2-Mbps or 60 384-Kbps 3GPP (6 Iterations)
  • Programmable Turbo Code and Decoding Parameters
• L1/L2 Memory Architecture
  • 128K-Bit (16K-Byte) L1P Program Cache (Direct Mapped)
  • 128K-Bit (16K-Byte) L1D Data Cache (2-Way Set-Associative)
  • 8M-Bit (1024K-Byte) L2 Unified Mapped RAM/Cache (Flexible Allocation)
• Two External Memory Interfaces (EMIFs)
  • One 64-Bit (EMIFA), One 16-Bit (EMIFB)
  • Glueless Interface to Asynchronous Memories and Synchronous Memories
  • 1280M-Byte Total Addressable External Memory Space
• Instruction Set Features
  • Byte-Addressable (8-/16-/32-/64-Bit Data)
  • 8-Bit Overflow Protection
  • Bit-Field Extract, Set, Clear
  • Normalization, Saturation, Bit-Counting
  • VelociTI.2™ Increased Orthogonality
• Enhanced Direct-Memory-Access (EDMA) Controller (64 Independent Channels)
• Host-Port Interface (HPI)
  • User-Configurable Bus Width (32-/16-Bit)
• 32-Bit/33-MHz, 3.3-V PCI Master/Slave Interface Conforms to PCI Specification 2.2
  • Three PCI Bus Address Registers
  • Four-Wire Serial EEPROM Interface
  • PCI Interrupt Request Under DSP Program Control
  • DSP Interrupt Via PCI I/O Cycle
• Three Multichannel Buffered Serial Ports
  • Direct Interface to T1/E1, MVIP, SCSA Framers
  • Up to 256 Channels Each
  • ST-Bus-Switching-, AC97-Compatible
  • Serial Peripheral Interface (SPI) Compatible (Motorola™)
• Three 32-Bit General-Purpose Timers
• UTOPIA [C6416T]
  • UTOPIA Level 2 Slave ATM Controller
  • 8-Bit Transmit and Receive Operations up to 50 MHz per Direction
  • User-Defined Cell Format up to 64 Bytes
• 16 General-Purpose I/O (GPIO) Pins
• IEEE-1149.1 (JTAG) Boundary-Scan-Compatible
• 532-Pin Ball Grid Array (BGA) Package (GLZ Suffix), 0.8-mm Ball Pitch

C62x, VelociTI.2, VelociTI, and TMS320C64x are trademarks of Texas Instruments. Motorola is a trademark of Motorola, Inc. Component qualification in accordance with JEDEC and industry standards to ensure reliable operation over an extended temperature range. This includes, but is not limited to, Highly Accelerated Stress Test (HAST) or biased 85/85, temperature cycle, autoclave or unbiased HAST, electromigration, bond intermetallic life, and mold compound life. Such qualification testing should not be viewed as justifying use of this component beyond specified performance and environmental limits. IEEE Standard 1149.1-1990 Standard-Test-Access Port and Boundary Scan Architecture. TMS320C6000, C64x, and C6000 are trademarks of Texas Instruments. Windows is a registered trademark of the Microsoft Corporation. Other trademarks are the property of their respective owners. These C64x™ devices have two EMIFs (64-bit EMIFA and 16-bit EMIFB). The prefix "A" in front of a signal name indicates it is an EMIFA signal whereas a prefix "B" in front of a signal name indicates it is an EMIFB signal. Throughout the rest of this document, in generic EMIF areas of discussion, the prefix "A" or "B" may be omitted from the signal name.