Introduction to the HPI

www.ti.com

The HPI uses multiplexed operation, meaning the data bus carries both address and data. When the host drives an address on the bus, the address is stored in the address register (HPIA) in the HPI, so that the bus can then be used for data.

The HPI supports two interface modes: HPI16 and HPI32 mode. DSP selects either HPI16 or HPI32 mode via the HPI_WIDTH device configuration pin at reset.

16-bit multiplexed mode (HPI16). The HPI is called HPI16 when operating as a 16-bit wide host port. This mode is selected if the HPI_WIDTH configuration pin of the DSP is sampled low at reset. In this mode, a 16-bit data bus (HD[15:0]) carries both addresses and data. HPI16 combines successive 16-bit transfers to provide 32-bit data to the CPU. The halfword identification line (HHWIL) input is used on the HPI16 to identify the first or second half word of a word transfer.

32-bit multiplexed mode (HPI32). HPI operates in this mode as a 32-bit wide host port. This mode is selected if the HPI_WIDTH configuration pin of the DSP is sampled high at reset. In this mode, a 32-bit data bus (HD[31:0]) carries both addresses and data. HHWIL is not applicable for HPI32 mode.

The HPI contains two HPIAs (HPIAR and HPIAW), which can be used as separate address registers for read accesses and write accesses (for details, see Section 2).

A 32-bit control register (HPIC) is accessible by the DSP CPU and the host. The CPU can use HPIC to send an interrupt request to the host, to clear an interrupt request from the host, and to monitor the HPI. The host can use HPIC to configure and monitor the HPI, to send an interrupt request to the CPU, and to clear an interrupt request from the CPU.

Data flow between the host and the HPI uses a temporary storage register, the 32-bit data register (HPID). Data arriving from the host is held in HPID until the data can be stored elsewhere in the DSP. Data to be sent to the host is held in HPID until the HPI is ready to perform the transfer. When address autoincrementing is used, read and write FIFOs are used to store burst data. If autoincrementing is not used, the FIFO memory acts as a single register (only one location is used).

NOTE: To manage data transfers between HPID and the internal memory, the DSP contains dedicated HPI DMA logic. The HPI DMA logic is not programmable. It automatically stores or fetches data using the address provided by the host. The HPI DMA logic is independent of the EDMA3 controller included in the DSP.

In the DSP system, master and slave peripherals communicate with each other via the Switched Central Resource (SCR). By definition, master peripherals are capable of initiating read and write transfers in the system and may not solely rely on the EDMA3 controller for their data transfers. Slave peripherals rely on the EDMA3 controller to perform transfers. The HPI is a master peripheral; it uses its DMA logic to directly communicate with the rest of the system via the SCR and does not rely on the EDMA3 controller for its data transfers. Note that the HPI cannot access all DSP resources or peripherals; see the device-specific data manual for a list of resources accessible through the HPI.

1.1Summary of the HPI Registers

Table 1 summarizes the registers inside the HPI, including access permissions and access requirements from the perspective of the host and the DSP CPU. See Section 8 for detailed descriptions of all these registers. Section 2 describes the two address registers (HPIAW and HPIAR) and describes the two HPIA modes that determine how the host uses these registers.

The host can only access HPIC, HPIAW, HPIAR, and HPID. By driving specific levels on the HCNTL[1:0] signals, the host indicates whether it is performing an HPIC, HPIA, or HPID access. For an HPID access, the HCNTL signals also indicate whether or not the HPI should perform an automatic address increment after the access. Section 3.4 describes the effects of the HCNTL[1:0] signals. The HR/W signal indicates whether the host is reading or writing.

The DSP CPU cannot access HPID but has limited access to HPIC, HPIAR, and HPIAW. The CPU has full access to the power and emulation management register, which selects an emulation mode for the HPI.

HPI registers accessible by the CPU have an address in the DSP memory map. Table 1 shows the offset addresses for various HPI registers. See the device-specific data manual for the base addresses of the HPI registers.

8

Host Port Interface (HPI)

SPRUGK7A –March 2009 –Revised July 2010

Copyright © 2009–2010, Texas Instruments Incorporated

Page 8
Image 8
Texas Instruments TMS320C6457 manual Summary of the HPI Registers

TMS320C6457 specifications

The Texas Instruments TMS320C6457 is a high-performance digital signal processor (DSP) designed for demanding applications in telecommunications, industrial control, and video processing. As part of the TMS320C6000 family, the C6457 combines advanced features with impressive processing capabilities, making it a popular choice among developers looking for efficient and robust solutions.

One of the key features of the TMS320C6457 is its architecture, which is based on the super Harvard architecture. This design separates program and data memory paths, allowing for parallel instruction execution. The C6457 operates at clock speeds of up to 1 GHz, enabling it to deliver peak performance of over 6,000 MIPS (Million Instructions Per Second) and 12,000 MADDs (Multiply-Accumulate operations per second). Such high throughput makes the C6457 suitable for real-time processing applications that require rapid data handling.

The C6457 DSP integrates a rich set of on-chip resources, including up to 1MB of on-chip SRAM, which serves as a fast cache for data and instructions. The device features multiple high-speed interfaces, such as 10/100/1000 Ethernet, Serial RapidIO, and PCI-Express, facilitating seamless connectivity with other devices and systems. Furthermore, the TMS320C6457 supports various communication protocols, allowing it to adapt to a wide range of application scenarios.

In terms of power efficiency, the TMS320C6457 is designed with sophisticated power management features. It includes dynamic voltage and frequency scaling, which adjust power consumption based on workload requirements without compromising performance. This capability is particularly valuable in battery-operated devices or environments where thermal management is critical.

The TMS320C6457 also benefits from extensive software support, including the Texas Instruments DSP/BIOS real-time operating system and Code Composer Studio integrated development environment. Developers can leverage these tools for efficient code development, debugging, and system optimization. Additionally, Texas Instruments provides a range of libraries and algorithms optimized for the C6457, facilitating rapid application development.

Overall, the Texas Instruments TMS320C6457 DSP stands out due to its robust architecture, high processing capabilities, comprehensive connectivity options, and power management features. These attributes make it a versatile solution for a broad spectrum of applications in digital signal processing, where performance and efficiency are paramount. As technology continues to advance, the TMS320C6457 remains a relevant and potent option for developers seeking to push the boundaries of digital signal processing.