Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Recent content by permute

  1. P

    AXI WR and RD channels access same address simultaneously

    This has also been a question of mine. IIRC, there are some priority and scheduling features from some of the extra AXI signals (eg, not the data/addr/response signals). For memory, you would want to ensure coherency for reading back just-written data, but you would also like to issue reads...
  2. P

    How to visualize Cyclic Prefix in OFDM system

    The fast explanation is that the FFT is a cyclic convolution. For example, people sometimes try to filter data by taking an N-point FFT adjusting coefficients, and then doing the inverse FFT. This would be nice if it always worked. But even a simple problem, like modeling a sample delay, is...
  3. P

    Signal over long wire-Active high or Low?

    The design is also affected by any extra needs for detection of the switch. For example, if you have a pullup resistor you can also place a resistor across the other end terminals. This would give a 3 level circuit, which would let you know if you have 1, 0, or invalid. Active high/low could...
  4. P

    Errors about Spartan6 BUFIO2

    BUFIO only drives IO logic. BUFR can be connected to the bufio, and can drive a region.
  5. P

    Architecture diferences in fpga(LUTs and FFs)

    Look at the CLB user guide for the parts you are interested in. These have changed over the years, and there are some extras in there as well (muxf7, muxf8, xorcy). The 7-series has 4 lut/slice, and 8 ff/slice with some restrictions on 4 of the ff's.
  6. P

    Expression evaluation in vhdl and verilog

    I don't know how /2**5 is done in Verilog. VHDL is consistent with algebra -- -(a/b) = (-a)/b = a/(-b), which implies some form of symmetric rounding. C does truncation (round to -inf). IIRC, verilog does the same.
  7. P

    Is FPGA a processor or controller?

    I think the OP is somewhat confused because he is viewing this from the wrong angle. He's using controller vs (or) processor as some basic level of complexity distinction. Eg, an application processor would be an ASIC that has some CPU, external memory, MMU with VM, page table, DMA, etc... A...
  8. P

    Interesting Digital Design question

    KaptainBug, this was last posted on 17th December 2006, 10:00. I doubt s0shinde even uses these forums anymore.
  9. P

    vhdl programming doubt

    The minimum PLL internal frequency is too high. maximum division is 128. 400*128 < 80000. 80000 < 400000000. (I don't remember the exact min PLL freq, but I don't think any DCM/MMCM/PLL ever had a min frequency under 100khz) There are two real solutions. The first is to run the logic at a...
  10. P

    Incomplete sensitivity list, allthough using always @ (*)

    which line is in error? The warning says something greater than 18, while the posted code shows 18 lines. Are you sure you are using the correct file for synthesis?
  11. P

    shift operator in vhdl

    function rotate_right (signal d_in:std_logic_vector)return std_logic_vector is variable b : std_logic_vector(d_in'length-1 downto 0); begin b := d_in; -- this normalizes the range return b(0) & b(b'high downto 1); end rotate_right; It is important to normalize the inputs to a function...
  12. P

    Memory Limitations of FPGA

    Many of the ML algorithms can be trained one (or a few) test samples at a time. The result is a set of parameters that can then be used to classify samples one (or a few) at a time. These don't have a large memory requirement. Nonparametric estimators (eg, k-nearest) do have potentially large...
  13. P

    add and subtract and multiply 4 bits "help"

    While I almost never agree with TD on this subject, this is one of the times I do. Comparisons and multiplication are different for unsigned vs signed, so there is value in using signed vs unsigned. If you are unhappy with the types, you can always use casting, extra signals, variables, etc...
  14. P

    When to use Block RAM

    Look at the SLICEM configuration. a depth of 16 is nice because it is a 4b address, so the addressing can be done in one slice. A depth of 16 or 32 allows a 6b/slice configuration. 128b lines up well with a 1b/slice option. Thus all of these options allow rams to be made without needing...
  15. P

    When to use Block RAM

    For xilinx, you have three choices: 1.) registers only 2.) block ram 3.) distributed ram distributed ram works well in the 16-128 item range (1 slice). for 100 16b registers, I'd use distributed ram. You can infer either using similar constructs, so you can decide to use BRAM or...

Part and Inventory Search

Back
Top