Port of a fixed point MPEG2-AAC encoder on a ARM platform Romain Pagniez University College Dublin Information Hiding Laboratory Department of Computer Science Belfield, Dublin 4 – Ireland http://ihl.ucd.ie/ ⊲ UCD, August 2004
Overview � Introduction � Perceptual Audio Coding � Fixed Point Elements � Development Toolset � Implementation � Results � Summary ⊲ 1/22
Introduction: hardware encoding � MPEG2 AAC: state of the art in perceptual audio compression. It achieves a compression rate about 30% higher than mp3. Compressed stereo audio at 128 kbit/s is indistinguishable from the original 1.4 Mbit/s CD quality. � MPEG-like perceptual encoders are quite complex and involve a significant amount of calculations. � Computing the algorithm on a dedicated hardware chip could be an efficient solution allowing fast encoding at reduced cost. � Hardware encoding research is been conduced in the IHL on that specific subject and particularly highlights fixed point encoding. ⊲ 2/22
Introduction: main points of my work � Having the encoder properly working on a ARM platform. � Communication functions: � serial port of the board. � Ethernet port. � Double precision multiplication algorithm. ⊲ 3/22
Introduction: workflow AAC Specifications Floating Point Keith Cullen (PhD) Software Encoder Fixed Point Keith Cullen (PhD) Software Encoder Fixed Point Fixed Point My project Alexis Guerin (MSc) ARM Encoder FPGA Encoder ⊲ 4/22
Perceptual Audio Coding: Encoding Filterbank Digital Audio Bit / Noise Allocation Bitstream Encoded Time / Frequency Input and Coding Formatting Bitstream Mapping Ancillary Data Psychoacoustic (optional) Model � Filter bank: divides the input stream into multiple subbands of frequency. � Psychoacoustic model: simultaneously determines the overall masking threshold for each subband. � Allocation block: uses the masking threshold to decide how many bits should be used. � Bitstream formatting: multiplexes all the data to be transmitted. ⊲ 5/22
Perceptual Audio Coding: Threshold in Quiet 100 Threshold in Quiet 80 Sound Pressure Level (dB) 60 40 20 0 1 2 3 4 10 10 10 10 Frequency (Hz) ⊲ 6/22
Perceptual Audio Coding: Threshold in Quiet Amplitude Masking�Tone Masking�Threshold Masked�Tone Frequency ⊲ 7/22
Perceptual Audio Coding: Masking Level (dB) Frequency Time ⊲ 8/22
Fixed point WL 1 0 -1 -2 2 2 2 2 S IWL FWL � Fixed point representation virtually places a radix point somewhere in the middle of the digits and uses integer arithmetics. � This is equivalent to considering integers of portion of some unit. � For example, one might represent 1/100ths of a unit; with 4 decimal digits, 10.82 or 00.01 can be represented. � What is the more accurate position for the radix point ? ⊲ 9/22
Fixed point: range and error Range 4-bit Unsigned Step Size [0, 0.46875] 0.03125 [0, 0.93750] 0.06250 [0, 1.87500] 0.12500 [0, 3.75000] 0.25000 [0, 7.50000] 0.50000 [0, 15.00000] 1.00000 [0, 30.00000] 2.00000 ⊲ 10/22
Fixed point: optimal position � The optimal position of the radix point must be chosen considering precision and range of data. � The goal is to minimize error: overflow must be avoided and precision maximized. � Position of the binary point may vary along the encoding process. � Simulations must be carried out to determine the optimal position of each binary point. ⊲ 11/22
Development Toolset: development kit � EPXA1 development board: � EPXA1F484C device • ARM922T 32-bit RISC microprocessor • 100 k gates APEX 20KE FPGA � 32 Mo RAM � 8 Mo flash � 100 Mbit Ethernet � JTAG header � LCD display � Quartus II software � GNUpro compiler ⊲ 12/22
Development Toolset: development board ⊲ 13/22
Development Toolset: architecture Ethernet LCD LEDs AHB ARM PLD Switch etc. Serial Port � The PLD is the only interface of the ARM processor. � We must configure the FPGA. ⊲ 14/22
Development Toolset: flash programming Software Source Files To Quartus II Quartus II MegaWizard Plug-in Simulator or Software Builder Manager other EDA quartus_swb Simulation Tools System Build Descriptor File Simulator Initialisation Files From Quartus II Hardware Compiler (full compilation) Flash Programming Slave Binary File Image File ⊲ 15/22
Implementation: simulation files Simulation program running on a PC Audio data Fixed Point Simulated fixed AAC Encoder point environment AAC Compressed audio file ⊲ 16/22
Implementation: master slave architecture Master program running on a host PC Audio data Slave fixed point encoder running on the EPXA1 Communication Communication Fixed Point Functions Functions AAC Encoder AAC Compressed audio file ⊲ 17/22
Implementation: communication sequence From Host PC to Board From Board to Host PC Bit Rate (4 Bytes) Number of channels (4 Bytes) Sample Rate (4 Bytes) Bytes per sample (4 Bytes) Number of samples (4 Bytes) encode (2 Bytes) 1024 audio samples (mono - 1024 * 2 Bytes) or 2048 audio samples (stereo - 2048 * 2 Bytes) Size of Buffer (4 Bytes) Encoded Bitstream (size_of_buffer * 1 Byte) encode (2 Bytes) Size of Buffer (4 Bytes) Encoded Bitstream (size_of_buffer * 1 Byte) STOP (2 Bytes) Size of Buffer (4 Bytes) Encoded Bitstream (size_of_buffer * 1 Byte) ⊲ 18/22
Implementation: naive vs overlapped protocol EPXA1 EPXA1 Host Host Dev. Dev. PC PC Board Board AAC AAC Encoding Encoding AAC Encoding AAC Encoding AAC Encoding AAC Encoding AAC Time Encoding ⊲ 19/22
Results: communication vs computations � Naive implementation Proportion Real Time Communications 8.63 s 0.411 s/frame 48.6 % × 0.056 Computations 8.88 s 0.434 s/frame 51.4 % × 0.053 Total 17.51 s 0.845 s/frame 100 % × 0.027 � Communication overlapped with (faster) computations Proportion Real Time Communications 140 s 0.392 s/frame 100 % × 0.059 Computations 93 s 0.260 s/frame 66.3 % × 0.089 Total 140 s 0.392 s/frame 100 % × 0.059 ⊲ 20/22
Results: overlapped and high speed mult. � Encoding time for the communication overlapped with computations encoder (high speed multiplication) at 128 kbit/s. Encoding Time Real Time 86.1 ko 0.48 s 8.30 s 0.415 s/frame × 0.058 1.41 Mo 8.45 s 139.3 s 0.385 s/frame × 0.063 10.9 Mo 1 min 04 s 1065 s 0.384 s/frame × 0.060 ⊲ 21/22
Conclusion � The encoder works as expected � Communications on the serial port, even if slower the Ethernet, are sufficient to manage the encoding of a complete file ⊲ 22/22
Recommend
More recommend
