Hi, What is the most efficient way to scale numbers into the range of -1, 1 in Verilog using Cyclone II? That is the fastest code with least resources? are there any free IP cores from Altera or others which do so? I am currently doing it using the NIOS II processor (scaling and casting into fixed point), Is there any hardware solution? I have downloaded an IP core from IP genious which casts from FP to int, this will do the trick to convert to fixed point and shifting, all that remains now is the scaling?? thanks

--- Quote Start --- What is the most efficient way to scale numbers into the range of -1, 1 in Verilog using Cyclone II? --- Quote End --- You do not state the numeric format that you are using. The conversion of signed fixed-point B-bit integers to fractional integers is conceptual only, so no conversion is required. For example, a 3-bit signed integer has can represent the integer values -4, -3, -2, -1, 0, 1, 2, 3, with 2's compliment binary representation 100b, 101b, 110b, 111b, 001b, 010b, 011b. In fractional integer format, this is a Q2.0 number. You can divide this number by 2 to get a Q1.1 representation, i.e., -2.0, -1.5, -1.0, -0.5, 0, 0.5, 1.0, 1.5, or divide by 4 to get a Q0.2 representation, i.e., -1.0, -0.75, -0.50, -0.25, 0.0, 0.25, 0.50, 0.75. In all cases, the binary representation is the same (ok, there's a slight difference in that you can put a binary-point between the bits, but that does not exist in the hardware implementation). If you want a B-bit number to represent -1.0 to (almost) 1.0, then you just need to interpret it as a Q0.(B-1) fractional integer format number. It will have the range -1.0 to 1.0-1/(2^(B-1)). Cheers, Dave

Hi Dave, Thanks .. The thing is that I have a random Integer input in the 0 - 579 range, without any fractions, simply integers :) ...(xmin-xmax) This need be scaled to the -1 to 1 range (ymin-ymax) following this rule y = (ymax-ymin)*(x-xmin)/(xmax-xmin) + ymin; In my application it is: y = (2*x)/579-1 So based on what you said, to implement the above formula, all I need to do is shift my integer 10 bits to the right?? and then subtract one? Note that the following Hardware stages are in signed fixed point format with <S, M, N> = <1 sign,5 integer,10 fraction>, is the result readily available for use in the following stages?? or scaling is further needed? Thanks

Apologies to Dave if I understood the original post, you want 0~579 represented as -1 ~ +1 onto 16 bits signed. Here is my magic formula: y = x*113 - 32767 ... thats all Explanation: y = x * (2^16-1)/579 - 32767.5 = x*113 - 32767 accuracy is affected by value 113 and losing .5 of 32767.5 but can be improved by multiplying by larger than 113 then shift dividing.

--- Quote Start --- The thing is that I have a random Integer input in the 0 - 579 range, without any fractions, simply integers :) ...(xmin-xmax) This need be scaled to the -1 to 1 range --- Quote End --- What is the data being generated from? And what is being done to it afterwards? If the number is being filtered or processed, perhaps you don't need to change the input, but rather, change the filter gain, so that the filtered number has the right power levels. A method like the one Kaz suggested should work fine. If you want more accuracy in the least-significant bits, then as he suggests, just add more bits. If you can describe what you are doing, we can probably give you alternative solutions. Cheers, Dave

Hi, Sorry for late reply .. got busy with another HW problem! Well, the data represents the number of black pixels in certain zones in a binary image .. The data is an input to a neural network for classification which requires a normalized input in the range of -1 to 1! Well, i tried Kaz's method in C, the fixed point representation as displayed in hex format doesn't match the value!! What I did is multiply the floating point number by 1024 (10 bit fraction accuracy) and cast to integer .. it didn't match :S Thanks

Number Scaling | Altera Community

11 Replies

Altera_Forum
Honored Contributor
15 years ago
--- Quote Start ---

What is the most efficient way to scale numbers into the range of -1, 1 in Verilog using Cyclone II?
--- Quote End ---
You do not state the numeric format that you are using.

The conversion of signed fixed-point B-bit integers to fractional integers is conceptual only, so no conversion is required.

For example, a 3-bit signed integer has can represent the integer values -4, -3, -2, -1, 0, 1, 2, 3, with 2's compliment binary representation 100b, 101b, 110b, 111b, 001b, 010b, 011b. In fractional integer format, this is a Q2.0 number.

You can divide this number by 2 to get a Q1.1 representation, i.e., -2.0, -1.5, -1.0, -0.5, 0, 0.5, 1.0, 1.5, or divide by 4 to get a Q0.2 representation, i.e., -1.0, -0.75, -0.50, -0.25, 0.0, 0.25, 0.50, 0.75.

In all cases, the binary representation is the same (ok, there's a slight difference in that you can put a binary-point between the bits, but that does not exist in the hardware implementation).

If you want a B-bit number to represent -1.0 to (almost) 1.0, then you just need to interpret it as a Q0.(B-1) fractional integer format number. It will have the range -1.0 to 1.0-1/(2^(B-1)).

Cheers,
Dave

Forum Discussion

Number Scaling

11 Replies

Recent Discussions

Preconfiguration BSDL Editor for Agilex 7 with disabled F-Tiles

Fail to enumerate RTile PCIe in the AVSTx8 configuration

Agilex 5 HPS EMIF - Differential Pair Polarity Inversion Support

Boundary scan access to SDM pins on Agilex 7

vertical side marking on MAX10 UBGA169 package?