AT32AP7001-ALUT Atmel, AT32AP7001-ALUT Datasheet - Page 25

• Manufacturer Part Number: AT32AP7001-ALUT
• Description: IC MCU 32BIT AVR32 208-LQFP
• Manufacturer: Atmel
• Series: AVR®32 AP7r

Specifications of AT32AP7001-ALUT

• Core Processor: AVR
• Core Size: 32-Bit
• Speed: 150MHz
• Connectivity: EBI/EMI, I²C, MMC, PS2, SPI, SSC, UART/USART, USB
• Peripherals: AC'97, DMA, I²C, POR, PWM, WDT
• Number Of I /o: 90
• Program Memory Type: ROMless
• Ram Size: 32K x 8
• Voltage - Supply (vcc/vdd): 1.65 V ~ 1.95 V
• Data Converters: D/A 2x16b
• Oscillator Type: Internal
• Operating Temperature: -40°C ~ 85°C
• Package / Case: 208-LQFP
• Data Bus Width: 32 bit
• Data Ram Size: 32 KB
• Interface Type: EBI, ISI, MCI, PS2, SPI, TWI, USB
• Maximum Clock Frequency: 150 MHz
• Number Of Programmable I/os: 90
• Number Of Timers: 3
• Maximum Operating Temperature: + 85 C
• Mounting Style: SMD/SMT
• Minimum Operating Temperature: - 40 C
• On-chip Dac: 16 bit, 1 Channel
• Package: 208PQFP
• Device Core: AVR32
• Family Name: AT32
• Maximum Speed: 150 MHz
• Operating Supply Voltage: 1.8 V
• For Use With: ATAVRONEKIT - KIT AVR/AVR32 DEBUGGER/PROGRMMRATNGW100 - KIT AVR32 NETWORK GATEWAYATSTK1000 - KIT STARTER FOR AVR32AP7000
• Lead Free Status / RoHS Status: Lead free / RoHS Compliant
• Eeprom Size: -
• Program Memory Size: -
• Lead Free Status / Rohs Status: Details

8. Pixel Coprocessor (PICO)
8.1
8.2
32015G–AVR32–09/09
Features
Description
Rev.: 1.0.0.0
•
•
•
•
•
•
The Pixel Coprocessor (PICO) is a coprocessor coupled to the AVR32 CPU through the TCB
(Tightly Coupled Bus) interface. The PICO consists of three Vector Multiplication Units (VMU0,
VMU1, VMU2), an Input Pixel Selector and an Output Pixel Inserter. Each VMU can perform a
vector multiplication of a 1x3 12-bit coefficient vector with a 3x1 8-bit pixel vector. In addition a
12-bit offset can be added to the result of this vector multiplication.
The PICO can be used for transforming the pixel components in a given color space (i.e. RGB,
YCrCb, YUV) to any other color space as long as the transformation is linear. The flexibility of
the Input Pixel Selector and Output Pixel Insertion logic makes it easy to efficiently support dif-
ferent pixel storage formats with regards to issues such as byte ordering of the color
components, if the color components constituting an image are packed/interleaved or stored as
separate images or if any of the color components are subsampled.
The three Vector Multiplication Units can also be connected together to form one large vector
multiplier which can perform a vector multiplication of a 1x9 12-bit coefficient vector with a 9x1 8-
bit pixel vector. This can be used to implement FIR filters, bilinear interpolations filters for
smoothing/scaling images etc. By allowing the outputs from the Vector Multiplication units to
accumulate it is also possible to extend the order of the filter to more than 9-taps.
The results from the VMUs are scaled and saturated back to unsigned 8-bit pixel values in the
Output Pixel Inserter.
Coprocessor coupled to the AVR32 CPU Core through the TCB Bus.
Three parallel Vector Multiplication Units (VMU) where each unit can:
Can be used for accelerating:
Flexible input Pixel Selector.
Flexible Output Pixel Inserter.
Configurable coefficients with flexible fixed-point representation.
– Multiply three pixel components with three coefficients.
– Add the products from the multiplications together.
– Accumulate the result or add an offset to the sum of the products.
– Image Color Space Conversion.
– Image filtering/scaling.
– MPEG-4/H.264 Quarter Pixel Motion Compensation.
– Can operate on numerous different image storage formats.
– Scales and saturates the results back to 8-bit pixel values.
– Supports packed and planar output formats.
• Configurable Conversion Coefficients.
• Supports packed and planar input and output formats.
• Supports subsampled input color spaces (i.e 4:2:2, 4:2:0).
• Configurable Filter Coefficients.
• Throughput of one sample per cycle for a 9-tap FIR filter.
• Can use the built-in accumulator to extend the FIR filter to more than 9-taps.
• Can be used for bilinear/bicubic interpolations.
AT32AP7001
25