Copyright © 2008 Texas Instruments. All rights reserved. 1.Introduction 2.Real-Time System Design Considerations 3.Hardware Interrupts (HWI) 4.Software Interrupts (SWI) 5.Task Authoring (TSK) 6.Data Streaming (SIO) 7.Multi-Threading (CLK, PRD) 8.BIOS Instrumentation (LOG, STS, SYS, TRC) 9.Static Systems (GCONF, TCONF) 10.Cache (BCACHE) 11.Dynamic Systems (MEM, BUF) 12.Flash Programming (HexAIS, Flashburn) 13.Inter-Thread Communication (MSGQ,...) 14.DSP Algorithm Standard (XDAIS) 15.Input Output Mini-Drivers (IOM) 16.Direct Memory Access (DMA) 17.Review DSP/BIOS System Integration Workshop D SP TEXAS INSTRUMENTS TECHNOLOGY 1
C6000 Memory Considerations 1. Use internal RAM + Fastest, lowest power, best bandwidth − Limited amount of internal RAM available 2. Add external memory + Allows much greater code and data sizes − Much lower performance than internal memory access 3. Enable cache + Near optimal performance for loops and iterative data access + Improves speed, power, EMIF availability − No benefit for non-looping code or 1x used data 4. Use internal RAM and external memory + External memory for low demand or highly looped items + Internal memory for highest demand or DMA-shared memory 5. Tune code for Cache usage + Assure optimal fit to cache + Avoid CPU/DMA contention problems intro 1. IRAM 2. EMIF 3. Use Cache 4. IRAM+EMIF 5. Code Tune D SP TEXAS INSTRUMENTS TECHNOLOGY 2
C6000 Memory Considerations 1. Use internal RAM + Fastest, lowest power, best bandwidth − Limited amount of internal RAM available 2. Add external memory + Allows much greater code and data sizes − Much lower performance than internal memory access 3. Enable cache + Near optimal performance for loops and iterative data access + Improves speed, power, EMIF availability − No benefit for non-looping code or 1x used data 4. Use internal RAM and external memory + External memory for low demand or highly looped items + Internal memory for highest demand or DMA-shared memory 5. Tune code for Cache usage + Assure optimal fit to cache + Avoid CPU/DMA contention problems intro 1. IRAM 2. EMIF 3. Use Cache 4. IRAM+EMIF 5. Code Tune D SP TEXAS INSTRUMENTS TECHNOLOGY 3
Option 1 : Use Internal Memory When possible, place all code and data into internal RAM Select all internal memory to be mapped as RAM Add IRAM(s) to memory map Route code/data to IRAM(s) Ideal choice for initial code development Defines optimal performance possible Avoids all concerns of using external memory Fast and easy to do – just download and run from CCS In production systems Add a ROM type resource externally to hold code and initial data Use DMA (or CPU xfer) to copy runtime code/data to internal RAM Boot routines available on most TI DSPs Limited range Usually not enough IRAM for a complete system Often need to add external memory and route resources there D SP TEXAS INSTRUMENTS TECHNOLOGY 4
C6000 Internal Memory Topology L1P Controller CPU (SPLOOP) L1D Controller L1D RAM / Cache 32B 8B 32B L1P RAM / Cache 32B L2 Controller L2 ROM L2 IRAM / Cache Level 1 – or “L1” – RAM Highest performance of any memory in a C6000 system Two banks are provided L1P (for program) and L1D (for data) Single cycle memory with wide bus widths to the CPU Level 2 – or “L2” – RAM Second best performance in system, can approach single cycle in bursts Holds both code and data Usually larger than L1 resources Wide bus widths to CPU - via L1 controllers D SP TEXAS INSTRUMENTS TECHNOLOGY 5
Configure IRAM via GCONF To obtain maximum IRAM, zero the internal caches, which share this memory D SP TEXAS INSTRUMENTS TECHNOLOGY 6
Define IRAM Usage via GCONF D SP TEXAS INSTRUMENTS TECHNOLOGY 7
Define IRAM Usage via GCONF Here, L1D is used for the most critical storage, and all else is routed to L2 “IRAM”. A variety of options can be quickly tested, and the best kept in the final revision. D SP TEXAS INSTRUMENTS TECHNOLOGY 8
Sample of C6000 On-Chip Memory Options DeviceCPUL1PL1DL2$ C6416T C DM C C * Notes: Memory sizes are in KB Prices are 100pc volume 6747 also has 128KB of L3 IRAM D SP TEXAS INSTRUMENTS TECHNOLOGY 9
C6000 Memory Considerations 1. Use internal RAM + Fastest, lowest power, best bandwidth − Limited amount of internal RAM available 2. Add external memory + Allows much greater code and data sizes − Much lower performance than internal memory access 3. Enable cache + Near optimal performance for loops and iterative data access + Improves speed, power, EMIF availability − No benefit for non-looping code or 1x used data 4. Use internal RAM and external memory + External memory for low demand or highly looped items + Internal memory for highest demand or DMA-shared memory 5. Tune code for Cache usage + Assure optimal fit to cache + Avoid CPU/DMA contention problems intro 1. IRAM 2. EMIF 3. Use Cache 4. IRAM+EMIF 5. Code Tune D SP TEXAS INSTRUMENTS TECHNOLOGY 10
Option 2 : Use External Memory For larger systems, place code and data into external memory Define available external memories Route code/data to external memories Essential for systems with environments larger than available internal memory Allows systems with size range from Megs to Gigs Often realized when a build fails for exceeding internal memory range Avoids all concerns of using external memory Fast and easy to do – just download and run from CCS Reduced performance Off chip memory has wait states Lots of setup and routing time to get data on chip Competition for off-chip bus : data, program, DMA, … Increased power consumption D SP TEXAS INSTRUMENTS TECHNOLOGY 11
C6000 Memory Topology L1P Controller CPU (SPLOOP) L1D Controller L1D RAM / Cache 32B 8B 32B L1P RAM / Cache 32B L2 Controller L2 ROM L2 IRAM / Cache External Memory Controller External Memory 16B 4-8 B External memory interface has narrower bus widths CPU access to external memory costs many cycles Exact cycle count varies greatly depending on state of the system at the time D SP TEXAS INSTRUMENTS TECHNOLOGY 12
Define External Memory via GCONF D SP TEXAS INSTRUMENTS TECHNOLOGY 13
Define External Usage via GCONF D SP TEXAS INSTRUMENTS TECHNOLOGY 14
C6000 Memory Considerations 1. Use internal RAM + Fastest, lowest power, best bandwidth − Limited amount of internal RAM available 2. Add external memory + Allows much greater code and data sizes − Much lower performance than internal memory access 3. Enable cache + Near optimal performance for loops and iterative data access + Improves speed, power, EMIF availability − No benefit for non-looping code or 1x used data 4. Use internal RAM and external memory + External memory for low demand or highly looped items + Internal memory for highest demand or DMA-shared memory 5. Tune code for Cache usage + Assure optimal fit to cache + Avoid CPU/DMA contention problems intro 1. IRAM 2. EMIF 3. Use Cache 4. IRAM+EMIF 5. Code Tune D SP TEXAS INSTRUMENTS TECHNOLOGY 15
Option 3 : Use Cache & External Memory Improves peformance in code loops or re-used data values First access to external resource is ‘normal’ Subsequent accesses are from on-chip caches with: Much higher speed Lower power Reduced external bus contention Not helpful for non-looping code or 1x used data Cache holds recent data/code for re-use Without looping or re-access, cache cannot provide a benefit Not for use with ‘devices’ Inhibits re-reads from ADCs and writes to DACs Must be careful when CPU and DMA are active in the same RAMs Enabling the cache: Select maximum amounts of internal memory to be mapped as cache Remove IRAM(s) from memory map Route code/data to off-chip (or possible remaining onchip) resources Map off-chip memory as cachable D SP TEXAS INSTRUMENTS TECHNOLOGY 16
C6000 Memory Topology L1P Controller CPU (SPLOOP) L1D Controller L1D RAM / Cache 32B 8B 32B L1P RAM / Cache 32B L2 Controller L2 ROM L2 IRAM / Cache External Memory Controller External Memory 16B 4-8 B Caches automatically collect data and code brought in from EMIF If requested again, caches provide the information, saving many cycles over repeated EMIF activity Writes to external memory are also cached to reduce cycles and free EMIF for other usage Writeback occurs when a cache needs to mirror new addresses Write buffers on EMIF reduce need for waiting by CPU for writes D SP TEXAS INSTRUMENTS TECHNOLOGY 17
Configure Cache via GCONF For best cache results, maximize the internal cache sizes D SP TEXAS INSTRUMENTS TECHNOLOGY 18
Memory Attribute Registers : MARs Start AddressEnd AddressSizeSpace 0x x42FF FFFF16MBCS2_ 0x x44FF FFFF16MBCS3_ 0x x46FF FFFF16MBCS4_ 0x x48FF FFFF16MBCS5_ 0x x8FFF FFFF256MBDDR2 MARMAR AddressEMIF Address Range 660x – 42FF FFFF 1280x – 80FF FFFF 1290x – 81FF FFFF 1300x – 82FF FFFF 1310x C – 83FF FFFF 1320x – 84FF FFFF 1330x – 85FF FFFF 1340x – 86FF FFFF 1350x C – 87FF FFFF 256 MAR bits define cache-ability of 4G of addresses as 16MB groups Many 16MB areas not used by chip or present on given board Example: Usable 6437 EMIF addresses at right EVM6437 memory is: 128MB of DDR2 starting at 0x FLASH, NAND Flash, or SRAM (selected via jumpers) in CS2_ space at 0x Note: with the C64+ program memory is always cached regardless of MAR settings D SP TEXAS INSTRUMENTS TECHNOLOGY 19
Configure MAR via GCONF MAR66, turned ‘on’ D SP TEXAS INSTRUMENTS TECHNOLOGY 20
BCACHE API IRAM modes and MAR can be set in code via BCACHE API In projects where GCONF is not being used To allow active run-time reconfiguration option Cache Size Management BCACHE_getSize(*size) rtn sizes of all caches BCACHE_setSize(*size) set sizes of all caches MAR Bit Management marVal = BCACHE_getMar(base) rtn mar val for given address BCACHE_setMar(base, length, 0/1) set mars stated address range typedef struct BCACHE_Size { BCACHE_L1_Size l1psize ; BCACHE_L1_Size l1dsize ; BCACHE_L2_Size l2size ; } BCACHE_Size ; #L1(kB)L2 (kB) D SP TEXAS INSTRUMENTS TECHNOLOGY 21
C6000 Memory Considerations 1. Use internal RAM + Fastest, lowest power, best bandwidth − Limited amount of internal RAM available 2. Add external memory + Allows much greater code and data sizes − Much lower performance than internal memory access 3. Enable cache + Near optimal performance for loops and iterative data access + Improves speed, power, EMIF availability − No benefit for non-looping code or 1x used data 4. Use internal RAM and external memory + External memory for low demand or highly looped items + Internal memory for highest demand or DMA-shared memory 5. Tune code for Cache usage + Assure optimal fit to cache + Avoid CPU/DMA contention problems intro 1. IRAM 2. EMIF 3. Use Cache 4. IRAM+EMIF 5. Code Tune D SP TEXAS INSTRUMENTS TECHNOLOGY 22
Option 4 : IRAM & Cache Ext’l Memory Let some IRAM be Cache to improve external memory performance First access to external resource is ‘normal’ Subsequent access from on-chip caches – better speed, power, EMIF loading Keep some IRAM as normal addressed internal memory Most critical data buffers (optimal performance in key code) Target for DMA arrays routed to/from peripherals (2x EMIF savings) Internal program RAM Must be initialized via DMA or CPU before it can be used Provides optimal code performance Setting the internal memory properties: Select desired amounts of internal memory to be mapped as cache Define remainder as IRAM(s) in memory map Route code/data to desired on and off chip memories Map off-chip memory as cachable To determine optimal settings Profile and/or use STS on various settings to see which is best Late stage tuning process when almost all coding is completed D SP TEXAS INSTRUMENTS TECHNOLOGY 23
Select Desired IRAM Configuration DeviceCPUL1PL1DL2$ C6416T C DM C C * Notes: Memory sizes are in KB Prices are 100pc qty 6747 also has 128KB of L3 IRAM #L1(kB)L2 (kB) Define desired amount of IRAM to be cache (GCONF or BCACHE) Balance of available IRAM is ‘normal’ internal mapped-address RAM Any IRAM beyond cache limits are always address mapped RAM Single cycle access to L1 memories L2 access time can be as fast as single cycle Regardless of size, L2 cache is always 4 way associative 24
Set Cache Size via GCONF or BCACHE Cache Size Management BCACHE_getSize(*size) BCACHE_setSize(*size) typedef struct BCACHE_Size { BCACHE_L1_Size l1psize ; BCACHE_L1_Size l1dsize ; BCACHE_L2_Size l2size ; } BCACHE_Size ; #L1(kB)L2 (kB) D SP TEXAS INSTRUMENTS TECHNOLOGY 25
C64x+ L1D Memory Banks 512x32 Only one L1D access per bank per cycle Use DATA_MEM_BANK pragma to begin paired arrays in different banks Note: sequential data are not down a bank, instead they are along a horizontal line across across banks, then onto the next horizontal line Only even banks (0, 2, 4, 6) can be specified 512x32 Bank 0Bank 2Bank 4Bank 6 #pragma DATA_MEM_BANK(a, 4); short a[256]; #pragma DATA_MEM_BANK(x, 0); short x[256]; for(i = 0; i < count ; i++) { sum += a[i] * x[i]; } #pragma DATA_MEM_BANK(a, 4); short a[256]; #pragma DATA_MEM_BANK(x, 0); short x[256]; for(i = 0; i < count ; i++) { sum += a[i] * x[i]; } D SP TEXAS INSTRUMENTS TECHNOLOGY 26
C6000 Memory Considerations 1. Use internal RAM + Fastest, lowest power, best bandwidth − Limited amount of internal RAM available 2. Add external memory + Allows much greater code and data sizes − Much lower performance than internal memory access 3. Enable cache + Near optimal performance for loops and iterative data access + Improves speed, power, EMIF availability − No benefit for non-looping code or 1x used data 4. Use internal RAM and external memory + External memory for low demand or highly looped items + Internal memory for highest demand or DMA-shared memory 5. Tune code for Cache usage + Assure optimal fit to cache + Avoid CPU/DMA contention problems intro 1. IRAM 2. EMIF 3. Use Cache 4. IRAM+EMIF 5. Code Tune D SP TEXAS INSTRUMENTS TECHNOLOGY 27
5 : Tune Code for Cache Optimization Align key code and data for maximal cache usage Match code/data to fit cache lines fully – align to 128 bytes Clear caches when CPU and DMA are both active in a given memory Keep cache from presenting out-of-date values to CPU or DMA Size and align cache usage where CPU and DMA are both active Avoid risk of having neighboring data affected by cache clearing operations Freeze cache to maintain contents Lock in desired cache contents to maintain performance Ignore new collecting until cache is ‘thawed’ for reuse There are many ways in which caching can lead to data errors, however a few simple techniques provide the ‘cure’ for all these problems D SP TEXAS INSTRUMENTS TECHNOLOGY 28
Example of read coherency problem : 1. DMA collects Buf A 2. CPU reads Buf A, buffer is copied to Cache; DMA collects Buf B 3. CPU reads Buf B, buffer is copied to Cache; DMA collects Buf C over “A” 4. CPU reads Buf C… but Cache sees “A” addresses, provides “A” data – error! 5. Solution: Invalidate Cache range before reading new buffer Write coherency example : 1. CPU writes Buf A. Cache holds written data 2. DMA reads non-updated data from external memory – error! 3. Solution: Writeback Cache range after writing new buffer Program coherency : 1. Host processor puts new code into external RAM 2. Solution: Invalidate Program Cache before running new code Buf A Buf B Buf A Buf B DSP DMAA/D Cache Coherency Cache Ext’l RAM Note: there are NO coherency issues between L1 and L2 ! D SP TEXAS INSTRUMENTS TECHNOLOGY 29
Managing Cache Coherency blockPtr: start address of range to be invalidated byteCnt : number of bytes to be invalidated Wait: 1 = wait until operation is completed Cache BCACHE_inv(blockPtr, byteCnt, wait) InvalidateBCACHE_invL1pAll() CacheBCACHE_wb(blockPtr, byteCnt, wait) WritebackBCACHE_wbAll() Invalidate &BCACHE_wbInv(blockPtr, byteCnt, wait) WritebackBCACHE_wbInvAll() Sync to CacheBCACHE_wait() D SP TEXAS INSTRUMENTS TECHNOLOGY 30
False Addresses Buffer Cache Lines False Address: ‘neighbor’ data in the cache but outside the buffer range Reading data from the buffer re-reads entire line If ‘neighbor’ data changed externally before CPU was done using prior state, old data will be lost/corrupted as new data replaces it Writing data to buffer will cause entire line to be written to external memory External neighbor memory could be overwritten with old data Coherence Side Effect – False Addresses False Address problems can be avoided by aligning the start and end of buffers on cache line boundaries Align memory on 128 byte boundaries Allocate memory in multiples of 128 bytes #defineBUF 128 #pragma DATA_ALIGN (in,BUF) shortin[2][20*BUF]; #defineBUF 128 #pragma DATA_ALIGN (in,BUF) shortin[2][20*BUF]; D SP TEXAS INSTRUMENTS TECHNOLOGY 31
Freezing cache prevents data that is currently cached from being evicted Cache Freeze Responds to read and write hits normally No updating of cache on miss Freeze supported on C64x+ L2/L1P/L1D Commonly used with Interrupt Service Routines so that one-use code does not replace realtime algo code Other cache modes: Normal, Bypass Cache Mode Management Mode = BCACHE_getMode(level) rtn state of specified cache oldMode = BCACHE_setMode(level, mode) set state of specified cache typedef enum { BCACHE_ NORMAL, BCACHE_ FREEZE, BCACHE_ BYPASS } BCACHE_Mode ; typedef enum { BCACHE_ L1D, BCACHE_ L1P, BCACHE_ L2 } BCACHE_Level ; Cache Freeze (C64x+) D SP TEXAS INSTRUMENTS TECHNOLOGY 32
BCACHE-Based Cache Setup Example This BCACHE example shows how to put the EVM 6437 in the default power-up mode. (Note: code such as this will required for stand-alone bootup where CCS GEL files are not present) #include "myWorkcfg.h“// most BIOS headers provided by config tool #include // headers for DSP/BIOS Cache functions #defineDDR2BASE 0x ; // size of DDR2 area on DM6437 EVM #defineDDR2SZ 0x07D00000; // size of external memory setCache() { struct BCACHE_Size cachesize;// L1 and L2 cache size struct cachesize.l1dsize = BCACHE_L1_32K;// L1D cache size 32k bytes cachesize.l1psize = BCACHE_L1_32K;// L1P cache size 32k bytes cachesize.l2size = BCACHE_L2_0K;// L2 cache size ZERO bytes BCACHE_ setSize (&cacheSize);// set the cache sizes BCACHE_ setMode (BCACHE_L1D, BCACHE_NORMAL);// set L1D cache mode to normal BCACHE_setMode(BCACHE_L1P, BCACHE_NORMAL);// set L1P cache mode to normal BCACHE_setMode(BCACHE_L2, BCACHE_NORMAL);// set L2 cache mode to normal BCACHE_ inv (DDR2BASE, DDR2SZ, TRUE);// invalidate DDR2 cache region BCACHE_ setMar (DDR2BASE,DDR2SZ,1);// set DDR2 to be cacheable } 33
4x B L1P Controller CPU (SPLOOP) L1D Controller L1D RAM / Cache External Memory Controller External Memory 32B 8B 2x 256 1K 32B 16B L1P RAM / Cache 64B 32B L2 Controller L2 ROM L2 IRAM / Cache 4-8 B C64+ Cache Controller Review Select how much IRAM and Cache is needed Enable caching via MARs Align to 128 Allocate in multiples of 128 Invalidate cache before reads from memory under external control Writeback cache after writing to RAM under external control D SP TEXAS INSTRUMENTS TECHNOLOGY 34
ti Technical Training Organization 35
C6000 Memory Considerations 1. Use internal RAM + Fastest, lowest power, best bandwidth − Limited amount of internal RAM available 2. Add external memory + Allows much greater code and data sizes − Much lower performance than internal memory access 3. Enable cache + Near optimal performance for loops and iterative data access + Improves speed, power, EMIF availability − No benefit for non-looping code or 1x used data 4. Use internal RAM and external memory + External memory for low demand or highly looped items + Internal memory for highest demand or DMA-shared memory 5. Tune code for Cache usage + Assure optimal fit to cache + Avoid CPU/DMA contention problems MainHighlight MainNormal SubHighlight SubNormal D SP TEXAS INSTRUMENTS TECHNOLOGY 36