Coursehero >> California >> Berkeley >> CS 150

Course Hero has millions of student submitted documents similar to the one below including study guides, homework solutions, papers, exam answer keys and textbook solutions.

- EECS150 Digital Design Lecture 17 Memory 2 October 22, 2002 John Wawrzynek Fall 2002 EECS150 Lec17-mem2 Page 1 SDRAM Recap General Characteristics Optimized for high density and therefore low cost/bit Special fabrication process usually on a separate chip from processor Needs periodic refresh (in most applications) Relatively slow because: High capacity leads to large cell arrays with high word- and bit-line capacitance Complex read/write cycle. Read needs precharge and write-back word line DRAM bit cell bit line Multiple clock cycles per read or write access Multiple reads and writes are often grouped together to amortize overhead. Referred to as bursting . Fall 2002 EECS150 Lec17-mem2 Page 2 Functional Block Diagram 8 Meg x 16 SDRAM Fall 2002 EECS150 Lec17-mem2 Page 3 SDRAM Details Multiple banks of cell arrays are used to reduce access time: Each bank is 4K rows by 512 columns by 16 bits (for our part) ACTIVE command opens a row for operation transfers the contents of the entire to a row buffer Read and Write operations as split into RAS (row access) followed by CAS (column access) These operations are controlled by sending commands Commands are sent using the RAS, CAS, CS, & WE pins. Subsequent READ or WRITE commands modify the contents of the row buffer. For burst reads and writes during READ or WRITE the starting address of the block is supplied. Burst length is programmable as 1, 2, 4, 8 or a full page (entire row) with a burst terminate option. Address pins are time multiplexed During RAS operation, address lines select the bank and row During CAS operation, address lines select the column. Special commands are used for initialization (burst options etc.) A burst operation takes 4 + n cycles (for n words) Page 4 Fall 2002 EECS150 Lec17-mem2 READ burst (with auto precharge) Fall 2002 EECS150 Lec17-mem2 Page 5 WRITE burst (with auto precharge) See datasheet for more details. Fall 2002 Verilog simulation models available. Page 6 EECS150 Lec17-mem2 First-in-first-out (FIFO) Memory Used to implement queues. These find common use in computers and communication circuits. Generally, used for rate matching data producer and consumer: stating state after write after read Producer can perform many writes without consumer performing any reads (or vis versa). However, of because finite buffer size, on average, need equal number of reads and writes. Typical uses: interfacing I/O devices. Example network interface. Data bursts from network, then processor bursts to memory buffer (or reads one word at a time from interface). Operations not synchronized. Example: Audio output. Processor produces output samples in bursts (during process swap-in time). Audio DAC clocks it out at constant sample rate. Page 7 Fall 2002 EECS150 Lec17-mem2 FIFO Interfaces DIN RST CLK WE FULL HALF FULL EMPTY RE FIFO Address pointers pointers are used internally to keep next write position and next read position into a dualport memory. write ptr read ptr DOUT After write or read operation, FULL and EMPTY indicate status of buffer. Used by external logic to control own reading from or writing to the buffer. FIFO resets to EMPTY state. HALF FULL (or other indicator of partial fullness) is optional. Fall 2002 If pointers equal after write FULL: write ptr read ptr If pointers equal after read EMPTY: write ptr read ptr EECS150 Lec17-mem2 Page 8 FIFO Implementation Details Assume, dual-port memory with asynchronous read, synchronous write. Binary counter for each of read and write address. CEs controlled by WE and RE. Equal comparator to see when pointers match. Flip-flop each for FULL and EMPTY flags: WE RD equal EMPTYi FULLi 0 0 0 0 0 0 0 1 EMPTYi-1 FULLi-1 0 1 0 0 0 0 1 1 1 0 1 0 0 0 0 1 0 1 0 1 1 1 0 0 0 1 1 1 EMPTYi-1 FULLi-1 With this memory, read happens before write. Therefore if WE and RD are asserted: When FULL, correct operation will happen. When EMPTY, would like to write before read. Correct this case with a bypass mux: DIN DOUT 1 0 Da memory block Db EMPTY RD WR Fall 2002 EECS150 Lec17-mem2 Page 9 Xilinx BlockRam Versions Our simple version has latency problems. FULL and EMPTY signals are asserted near the end of the clock period. Xilinx version solves this by predicting when full or empty will be asserted on next write/read operation. Also uses BlockRam with synchronous reads. Available on Xilinx website along with app note application note. These are linked to our page. Two versions available. Easy to modify to change the width if necessary. Will use the cc (common clock) version for checkpoint 2. Can use the ic (independent clock) version later for bridging network to video. Fall 2002 EECS150 Lec17-mem2 Page 10

Find millions of documents here - Study Guides, Homework Solutions, Papers, Exam Answer Keys and more. Course Hero has millions of course related materials that will enable you to learn better, faster and get an A in all your courses.
Below is a small sample set of documents: