======================================================================================================
|
======================================================================================================
|
DP-ICSI log (C implementation of a fast logarithmic approximation unit based on ICSI log V2 0.6 Beta)
|
DP-ICSI log (C implementation of a fast logarithmic approximation unit based on ICSI log V2 0.6 Beta)
|
|
|
DP/SP LAU (FPGA unit that implements the ICSI log algorithm in VHDL)
|
DP/SP LAU (FPGA unit that implements the ICSI log algorithm in VHDL)
|
======================================================================================================
|
======================================================================================================
|
|
|
|
|
Version 0.2 beta
|
Version 0.2 beta
|
Build date: August 2nd, 2009
|
Build date: August 2nd, 2009
|
|
|
|
|
|
|
Introduction
|
Introduction
|
------------
|
------------
|
|
|
Software :
|
Software :
|
|
|
This package contains a C implementation of the ICSI logarithm approximation algorithm originally introduced in
|
This package contains a C implementation of the ICSI logarithm approximation algorithm originally introduced in
|
|
|
O.Vinyals, G.Friedland, A Hardware-Independent Fast Logarithm Approximation with Adjustable Accuracy.
|
O.Vinyals, G.Friedland, A Hardware-Independent Fast Logarithm Approximation with Adjustable Accuracy.
|
Tenth IEEE International Symposium on Multimedia, 2008. ISM 2008. pp. 61-65, December 2008.
|
Tenth IEEE International Symposium on Multimedia, 2008. ISM 2008. pp. 61-65, December 2008.
|
|
|
The new C function has been adjusted to support double precision inputs in contrast to the official implementation of the algorithm
|
The new C function has been adjusted to support double precision inputs in contrast to the official implementation of the algorithm
|
which supports only single precision. Furthermore, there is invalid input detection which makes the function fully compatible with
|
which supports only single precision. Furthermore, there is invalid input detection which makes the function fully compatible with
|
the IEEE 754 standard and the GNU library log() function.
|
the IEEE 754 standard and the GNU library log() function.
|
|
|
|
|
Hardware:
|
Hardware:
|
|
|
This package also contains a VHDL implementation of the ICSI logarithm approximation algorithm described in
|
This package also contains a VHDL implementation of the ICSI logarithm approximation algorithm described in
|
|
|
N. Alachiotis, A. Stamatakis: "Efficient Floating-Point Logarithm Unit for FPGAs". Accepted for publication at RAW workshop,
|
N. Alachiotis, A. Stamatakis: "Efficient Floating-Point Logarithm Unit for FPGAs". Accepted for publication at RAW workshop,
|
held in conjunction with IPDPS 2010, Atlanta, Georgia, April, 2010.
|
held in conjunction with IPDPS 2010, Atlanta, Georgia, April, 2010.
|
|
|
The SP-LAU (Single Precision Logarithm Approximation Unit) implements the algorithm and supports single precision inputs.
|
The SP-LAU (Single Precision Logarithm Approximation Unit) implements the algorithm and supports single precision inputs.
|
The DP-LAU (Double Precision Logarithm Approximation Unit) implements the algorithm and supports double precision inputs.
|
The DP-LAU (Double Precision Logarithm Approximation Unit) implements the algorithm and supports double precision inputs.
|
|
|
Both units support invalid input detection.
|
Both units support invalid input detection.
|
|
|
All implementations in this package calculate an approximation of the natural logarithm.
|
All implementations in this package calculate an approximation of the natural logarithm.
|
|
|
For more details about the software implementation see the respective readme file and paper for the ICSI log.
|
For more details about the software implementation see the respective readme file and paper for the ICSI log.
|
|
|
|
|
|
|
Package Structure
|
Package Structure
|
-----------------
|
-----------------
|
|
|
This package contains the following files and folder:
|
This package contains the following files and folder:
|
|
|
-README : This file
|
-README : This file
|
|
|
-DP-ICSILog/DP-ICSILog.c : C file that contains the adjusted for double precision implementation and an example of how to use the function.
|
-DP-ICSILog/DP-ICSILog.c : C file that contains the adjusted for double precision implementation and an example of how to use the function.
|
|
|
-Virtex 5/SP-LAU : This folder contains the VHDL source files as well as .xco and .ngc files of the IPs that have been used to implement the single precision unit on Virtex 5.
|
-Virtex 5/SP-LAU : This folder contains the VHDL source files as well as .xco and .ngc files of the IPs that have been used to implement the single precision unit on Virtex 5.
|
|
|
-Virtex 5/DP-LAU : This folder contains the VHDL source files as well as .xco and .ngc files of the IPs that have been used to implement the double precision unit on Virtex 5.
|
-Virtex 5/DP-LAU : This folder contains the VHDL source files as well as .xco and .ngc files of the IPs that have been used to implement the double precision unit on Virtex 5.
|
|
|
-Virtex 4/SP-LAU : This folder contains the VHDL source files as well as .xco and .ngc files of the IPs that have been used to implement the single precision unit on Virtex 4.
|
-Virtex 4/SP-LAU : This folder contains the VHDL source files as well as .xco and .ngc files of the IPs that have been used to implement the single precision unit on Virtex 4.
|
|
|
-Virtex 4/DP-LAU : This folder contains the VHDL source files as well as .xco and .ngc files of the IPs that have been used to implement the double precision unit on Virtex 4.
|
-Virtex 4/DP-LAU : This folder contains the VHDL source files as well as .xco and .ngc files of the IPs that have been used to implement the double precision unit on Virtex 4.
|
|
|
-COE Files : This folder contains COE files to be used if one needs to adjust the accuracy of the unit.
|
-COE Files : This folder contains COE files to be used if one needs to adjust the accuracy of the unit.
|
|
|
-PAO Files : This folder contains PAO files that contain the Peripheral Analysis Order for the SP and DP LAUs.
|
-PAO Files : This folder contains PAO files that contain the Peripheral Analysis Order for the SP and DP LAUs.
|
|
|
|
|
|
|
|
|
Usage of the DP-ICSILog
|
Usage of the DP-ICSILog
|
-----------------------
|
-----------------------
|
|
|
|
|
The DP-ICSILog.c file contains the necessay global variables and functions that need to be
|
The DP-ICSILog.c file contains the necessay global variables and functions that need to be
|
called in order to use the DP-ICSILog function as well as an example.
|
called in order to use the DP-ICSILog function as well as an example.
|
|
|
|
|
|
|
Interface of the LAU
|
Interface of the LAU
|
--------------------
|
--------------------
|
|
|
The toplevel module of the LAU is sp_fp_log_v2 for the single precision logarithm approximation unit
|
The toplevel module of the LAU is sp_fp_log_v2 for the single precision logarithm approximation unit
|
and the dp_fp_log_v2 for double precison.
|
and the dp_fp_log_v2 for double precison.
|
|
|
sp/dp : Single Precision / Double Precision
|
sp/dp : Single Precision / Double Precision
|
fp : Floating Point
|
fp : Floating Point
|
log : Logarithm
|
log : Logarithm
|
V2 : Because the mantissa lookup table has been initialized using the respective function of the ICSILog V2 0.6 Beta software.
|
V2 : Because the mantissa lookup table has been initialized using the respective function of the ICSILog V2 0.6 Beta software.
|
(The Version 2 of this function doubled the precision of the unit comparing to Version 1)
|
(The Version 2 of this function doubled the precision of the unit comparing to Version 1)
|
|
|
The interface of the unit is defined as follows:
|
The interface of the unit is defined as follows:
|
|
|
entity sp_fp_log_v2/dp_fp_log_v2 is
|
entity sp_fp_log_v2/dp_fp_log_v2 is
|
Port ( rst : in STD_LOGIC; -- The reset signal
|
Port ( rst : in STD_LOGIC; -- The reset signal
|
clk : in STD_LOGIC; -- The clock signal
|
clk : in STD_LOGIC; -- The clock signal
|
valid_in: in STD_LOGIC; -- Signal that indicates valid number at the input port of the unit.
|
valid_in: in STD_LOGIC; -- Signal that indicates valid number at the input port of the unit.
|
input_val: STD_LOGIC_VECTOR(31/63 downto 0); -- The input number.
|
input_val: STD_LOGIC_VECTOR(31/63 downto 0); -- The input number.
|
valid_out : STD_LOGIC; -- Signal that indicates valid number at the output port of the unit.
|
valid_out : STD_LOGIC; -- Signal that indicates valid number at the output port of the unit.
|
output_val : STD_LOGIC_VECTOR(31/63 downto 0) -- The output number, the approximation of the logarithm of the input number.
|
output_val : STD_LOGIC_VECTOR(31/63 downto 0) -- The output number, the approximation of the logarithm of the input number.
|
);
|
);
|
end sp_fp_log_v2/dp_fp_log_v2;
|
end sp_fp_log_v2/dp_fp_log_v2;
|
|
|
|
|
|
|
Implementation Details
|
Implementation Details
|
----------------------
|
----------------------
|
|
|
The VHDL units have been designed using the Xilinx 10.1 Design Suite.
|
The VHDL units have been designed using the Xilinx 10.1 Design Suite.
|
|
|
ISE 10.1 was used to create the unit.
|
ISE 10.1 was used to create the unit.
|
|
|
Coregen was used to create all the IPs used in this unit.
|
Coregen was used to create all the IPs used in this unit.
|
|
|
The released LAUs use a mantissa lookup table with 4,096 entries.
|
The released LAUs use a mantissa lookup table with 4,096 entries.
|
|
|
Target devices are Virtex 4 and Virtex 5 FPGAs.
|
Target devices are Virtex 4 and Virtex 5 FPGAs.
|
|
|
One needs to change the IPs used in order to use the unit on any FPGA that meets the demands of number of block rams (This number
|
One needs to change the IPs used in order to use the unit on any FPGA that meets the demands of number of block rams (This number
|
depends on the desired accuracy and thus on the size of the mantissa lookup table) and number of DSP slices (3 DSP slices are occupied).
|
depends on the desired accuracy and thus on the size of the mantissa lookup table) and number of DSP slices (3 DSP slices are occupied).
|
|
|
One can use the coe files in the COE file folder to regenerate the mantissa lookup table for different accuracy and resources occupation.
|
One can use the coe files in the COE file folder to regenerate the mantissa lookup table for different accuracy and resources occupation.
|
|
|
Both units have a latency of 22 cycles (Virtex 5) and 28 cycles (Virtex 4) which is the same irrespective of the size of the mantissa lookup table used and thus the accuracy.
|
Both units have a latency of 22 cycles (Virtex 5) and 28 cycles (Virtex 4) which is the same irrespective of the size of the mantissa lookup table used and thus the accuracy.
|
|
|
The released units occupy 2% of the hardware resources on the Virtex 5 SX95T FPGA and can operate with the following clock frequencies
|
The released units occupy 2% of the hardware resources on the Virtex 5 SX95T FPGA and can operate with the following clock frequencies
|
as they were reported by the static timing report:
|
as they were reported by the static timing report:
|
|
|
353.4 MHz for the SP-LAU on the V5SX95T-2 and
|
353.4 MHz for the SP-LAU on the V5SX95T-2 and
|
320.6 MHz for the DP-LAU on the V5SX95T-2 .
|
320.6 MHz for the DP-LAU on the V5SX95T-2 .
|
|
|
|
|
|
|
Verification Details
|
Verification Details
|
--------------------
|
--------------------
|
|
|
Modelsim 6.3f was used for extensive post place and route simulations.
|
Modelsim 6.3f was used for extensive post place and route simulations.
|
|
|
The development board HTG-V5-PCIE by HiTech Global populated with a V5SX95T-1 FPGA was used to verify the LAUs.
|
The development board HTG-V5-PCIE by HiTech Global populated with a V5SX95T-1 FPGA was used to verify the LAUs.
|
|
|
ChiScope Pro Analyzer was used for advanced on-chip debugging and verification of the units.
|
ChiScope Pro Analyzer was used for advanced on-chip debugging and verification of the units.
|
|
|
|
|
|
|
|
|
|
|
IP Configuration Details for the Virtex 5 LAUs
|
IP Configuration Details for the Virtex 5 LAUs
|
----------------------------------------------
|
----------------------------------------------
|
|
|
The IPs used for the implementations are the following:
|
The IPs used for the implementations are the following:
|
(The configuration options that are not mentioned were not selected.)
|
(The configuration options that are not mentioned were not selected.)
|
|
|
|
|
comp_eq_000000000000 :
|
comp_eq_000000000000 :
|
|
|
Comparator ,
|
Comparator ,
|
Operation :A=B,
|
Operation :A=B,
|
Data Type: Unsigned,
|
Data Type: Unsigned,
|
Input Width: 12,
|
Input Width: 12,
|
Port B Constant: 000000000000,
|
Port B Constant: 000000000000,
|
Pipeline Stages: 0,
|
Pipeline Stages: 0,
|
Output Options:Registered Output,
|
Output Options:Registered Output,
|
Synchronous Settings: Clear
|
Synchronous Settings: Clear
|
|
|
|
|
comp_eq_000000000000000 :
|
comp_eq_000000000000000 :
|
|
|
Comparator ,
|
Comparator ,
|
Operation :A=B,
|
Operation :A=B,
|
Data Type: Unsigned,
|
Data Type: Unsigned,
|
Input Width: 15,
|
Input Width: 15,
|
Port B Constant: 000000000000000,
|
Port B Constant: 000000000000000,
|
Pipeline Stages: 0,
|
Pipeline Stages: 0,
|
Output Options:Registered Output,
|
Output Options:Registered Output,
|
Synchronous Settings: Clear
|
Synchronous Settings: Clear
|
|
|
|
|
comp_eq_8ones :
|
comp_eq_8ones :
|
|
|
Comparator ,
|
Comparator ,
|
Operation :A=B,
|
Operation :A=B,
|
Data Type: Unsigned,
|
Data Type: Unsigned,
|
Input Width: 8,
|
Input Width: 8,
|
Port B Constant: 11111111,
|
Port B Constant: 11111111,
|
Pipeline Stages: 0,
|
Pipeline Stages: 0,
|
Output Options:Registered Output,
|
Output Options:Registered Output,
|
Synchronous Settings: Clear
|
Synchronous Settings: Clear
|
|
|
|
|
comp_eq_11ones :
|
comp_eq_11ones :
|
|
|
Comparator ,
|
Comparator ,
|
Operation :A=B,
|
Operation :A=B,
|
Data Type: Unsigned,
|
Data Type: Unsigned,
|
Input Width: 11,
|
Input Width: 11,
|
Port B Constant: 11111111111,
|
Port B Constant: 11111111111,
|
Pipeline Stages: 0,
|
Pipeline Stages: 0,
|
Output Options:Registered Output,
|
Output Options:Registered Output,
|
Synchronous Settings: Clear
|
Synchronous Settings: Clear
|
|
|
|
|
comp_eq_22zeros :
|
comp_eq_22zeros :
|
|
|
Comparator ,
|
Comparator ,
|
Operation :A=B,
|
Operation :A=B,
|
Data Type: Unsigned,
|
Data Type: Unsigned,
|
Input Width: 22,
|
Input Width: 22,
|
Port B Constant: 00000...0000,
|
Port B Constant: 00000...0000,
|
Pipeline Stages: 0,
|
Pipeline Stages: 0,
|
Output Options:Registered Output,
|
Output Options:Registered Output,
|
Synchronous Settings: Clear
|
Synchronous Settings: Clear
|
|
|
|
|
comp_eq_51zeros :
|
comp_eq_51zeros :
|
|
|
Comparator ,
|
Comparator ,
|
Operation :A=B,
|
Operation :A=B,
|
Data Type: Unsigned,
|
Data Type: Unsigned,
|
Input Width: 51,
|
Input Width: 51,
|
Port B Constant: 00000...0000,
|
Port B Constant: 00000...0000,
|
Pipeline Stages: 0,
|
Pipeline Stages: 0,
|
Output Options:Registered Output,
|
Output Options:Registered Output,
|
Synchronous Settings: Clear
|
Synchronous Settings: Clear
|
|
|
|
|
comp_eq_111111 :
|
comp_eq_111111 :
|
|
|
Comparator ,
|
Comparator ,
|
Operation :A=B,
|
Operation :A=B,
|
Data Type: Unsigned,
|
Data Type: Unsigned,
|
Input Width: 6,
|
Input Width: 6,
|
Port B Constant: 111111,
|
Port B Constant: 111111,
|
Pipeline Stages: 0,
|
Pipeline Stages: 0,
|
Output Options:Registered Output,
|
Output Options:Registered Output,
|
Synchronous Settings: Clear
|
Synchronous Settings: Clear
|
|
|
|
|
comp_eq_111111111 :
|
comp_eq_111111111 :
|
|
|
Comparator ,
|
Comparator ,
|
Operation :A=B,
|
Operation :A=B,
|
Data Type: Unsigned,
|
Data Type: Unsigned,
|
Input Width: 9,
|
Input Width: 9,
|
Port B Constant: 111111111,
|
Port B Constant: 111111111,
|
Pipeline Stages: 0,
|
Pipeline Stages: 0,
|
Output Options:Registered Output,
|
Output Options:Registered Output,
|
Synchronous Settings: Clear
|
Synchronous Settings: Clear
|
|
|
|
|
exp_lut_MEM :
|
exp_lut_MEM :
|
|
|
Block Memory Generator,
|
Block Memory Generator,
|
Memory Type: Single Port ROM,
|
Memory Type: Single Port ROM,
|
Read Width: 9
|
Read Width: 9
|
Read Depth: 128
|
Read Depth: 128
|
|
|
|
|
mant_lut_MEM :
|
mant_lut_MEM :
|
|
|
Block Memory Generator,
|
Block Memory Generator,
|
Memory Type: Single Port ROM,
|
Memory Type: Single Port ROM,
|
Read Width: 27
|
Read Width: 27
|
Read Depth: 4096 (depends on the desired accuracy)
|
Read Depth: 4096 (depends on the desired accuracy)
|
|
|
|
|
All the registers used are RAM-based Shift Registers. The width and depth of each register is indicated by the name.
|
All the registers used are RAM-based Shift Registers. The width and depth of each register is indicated by the name.
|
For example: reg_1b_1c is a register of 1 bit and 1 clock latency.
|
For example: reg_1b_1c is a register of 1 bit and 1 clock latency.
|
|
|
|
|
sp_fp_add:
|
sp_fp_add:
|
|
|
Floating Point,
|
Floating Point,
|
Operation Selection: Add,
|
Operation Selection: Add,
|
Precision: Single,
|
Precision: Single,
|
Architecture Optimization: High Speed,
|
Architecture Optimization: High Speed,
|
Family Optimizations: Full Usage,
|
Family Optimizations: Full Usage,
|
Latency and Rate Configuration: Use Maximum Latency
|
Latency and Rate Configuration: Use Maximum Latency
|
|
|
|
|
sp_fp_mult:
|
sp_fp_mult:
|
|
|
Floating Point,
|
Floating Point,
|
Operation Selection: Multiply,
|
Operation Selection: Multiply,
|
Precision: Single,
|
Precision: Single,
|
Architecture Optimization: High Speed,
|
Architecture Optimization: High Speed,
|
Family Optimizations: Medium Usage,
|
Family Optimizations: Medium Usage,
|
Latency and Rate Configuration: Use Maximum Latency
|
Latency and Rate Configuration: Use Maximum Latency
|
|
|
|
|
Note:
|
Note:
|
The Coregen Project Settings were changed from Virtex 5 to Virtex 4 and all the above IPs were regenerated under the current project settings,
|
The Coregen Project Settings were changed from Virtex 5 to Virtex 4 and all the above IPs were regenerated under the current project settings,
|
except only for the RAM-based Shift Registers that operate in parallel with the sp_fp_add and sp_fp_mult IPs. In this case the depth (clock delay)
|
except only for the RAM-based Shift Registers that operate in parallel with the sp_fp_add and sp_fp_mult IPs. In this case the depth (clock delay)
|
was changed according to the latency of the sp_fp_add and sp_fp_mult IPs.
|
was changed according to the latency of the sp_fp_add and sp_fp_mult IPs.
|
|
|
|
|
|
|
Authors and Contact Details
|
Authors and Contact Details
|
---------------------------
|
---------------------------
|
|
|
Nikos Alachiotis alachiot@in.tum.de
|
Nikos Alachiotis alachiot@in.tum.de
|
Alexandros Stamatakis stamatak@in.tum.de
|
Alexandros Stamatakis stamatak@in.tum.de
|
|
|
|
|
|
|
Copyright
|
Copyright
|
---------
|
---------
|
|
|
These programs are free software; you can redistribute it and/or modify
|
These programs are free software; you can redistribute it and/or modify
|
it under the terms of the GNU General Public License as published by
|
it under the terms of the GNU Lesser General Public License as published by
|
the Free Software Foundation; either version 2 of the License, or
|
the Free Software Foundation; either version 2 of the License, or
|
(at your option) any later version.
|
(at your option) any later version.
|
|
|
The programs are distributed in the hope that they will be useful,
|
The programs are distributed in the hope that they will be useful,
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
GNU General Public License for more details.
|
GNU General Public License for more details.
|
|
|
|
|
Further Information
|
Further Information
|
-------------------
|
-------------------
|
|
|
The FPGA units SP-LAU and DP-LAU are exact implementations of the SP-ICSILog and the DP-ICSILog algorithms respectively.
|
The FPGA units SP-LAU and DP-LAU are exact implementations of the SP-ICSILog and the DP-ICSILog algorithms respectively.
|
Furthermore there is support for invalid input detection like nan, inf, -inf or zero.
|
Furthermore there is support for invalid input detection like nan, inf, -inf or zero.
|
|
|
For more information on the LAU see the paper:
|
For more information on the LAU see the paper:
|
|
|
N. Alachiotis, A. Stamatakis: "Efficient Floating-Point Logarithm Unit for FPGAs". Accepted for publication at RAW workshop,
|
N. Alachiotis, A. Stamatakis: "Efficient Floating-Point Logarithm Unit for FPGAs". Accepted for publication at RAW workshop,
|
held in conjunction with IPDPS 2010, Atlanta, Georgia, April, 2010.
|
held in conjunction with IPDPS 2010, Atlanta, Georgia, April, 2010.
|
|
|
For more information on the ICSI log algorithm see the paper:
|
For more information on the ICSI log algorithm see the paper:
|
|
|
O.Vinyals, G.Friedland, A Hardware-Independent Fast Logarithm Approximation with Adjustable Accuracy.
|
O.Vinyals, G.Friedland, A Hardware-Independent Fast Logarithm Approximation with Adjustable Accuracy.
|
Tenth IEEE International Symposium on Multimedia, 2008. ISM 2008. pp. 61-65, December 2008.
|
Tenth IEEE International Symposium on Multimedia, 2008. ISM 2008. pp. 61-65, December 2008.
|
|
|
or/and download the official single precision C implementation from:
|
or/and download the official single precision C implementation from:
|
|
|
http://linux.softpedia.com/get/Programming/Libraries/ICSILog-41333.shtml
|
http://linux.softpedia.com/get/Programming/Libraries/ICSILog-41333.shtml
|
|
|
|
|
Citation
|
Citation
|
--------
|
--------
|
|
|
By using this component you agree to cite it as: "Efficient Floating-Point Logarithm Unit for FPGAs", by Nikos Alachiotis and Alexandros Stamatakis, accapted for publication at RAW workhsop, held in conjunction with IPDPS 2010.
|
By using this component you agree to cite it as: "Efficient Floating-Point Logarithm Unit for FPGAs", by Nikos Alachiotis and Alexandros Stamatakis, accapted for publication at RAW workhsop, held in conjunction with IPDPS 2010.
|
|
|
|
|
Release Notes
|
Release Notes
|
------------
|
------------
|
|
|
Version : 0.2 beta
|
Version : 0.2 beta
|
Build date : September 20th, 2009
|
Build date : September 20th, 2009
|
* support for Virtex 4 FPGAs as well
|
* support for Virtex 4 FPGAs as well
|
* FPGA verification
|
* FPGA verification
|
|
|
Version : 0.1 beta
|
Version : 0.1 beta
|
Build date : August 2nd, 2009
|
Build date : August 2nd, 2009
|
* support for Virtex 5 FPGAs only
|
* support for Virtex 5 FPGAs only
|
* Tested by using extensive post place and route simulations.
|
* Tested by using extensive post place and route simulations.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|