Difference between revisions of "Arty S7"

From ScienceZero
Jump to: navigation, search
Line 37: Line 37:
  
  
 +
==FPGA DSP48E1 slice==
 +
* 25-bit pre-adder with D register to enhance the capabilities of the A path
 +
* INMODE control supports balanced pipelining when dynamically switching between multiply (A*B) and add operations (A:B)
 +
* 25 x 18 multiplier
 +
* 30-bit A input of which the lower 25 bits feed the A input of the multiplier, and the entire 30-bit input forms the upper 30 bits of the 48-bit A:B concatenate internal bus.
 +
* Cascading A and B input
 +
** Semi-independently selectable pipelining between direct and cascade paths
 +
** Separate clock enables two-deep A and B set of input registers
 +
* Independent C input and C register with independent reset and clock enable.
 +
* CARRYCASCIN and CARRYCASCOUT internal cascade signals to support 96-bit accumulators/adders/subtracters in two DSP48E1 slices
 +
* MULTSIGNIN and MULTSIGNOUT internal cascade signals with special OPMODE setting to support a 96-bit MACC extension
 +
* Single Instruction Multiple Data (SIMD) Mode for three-input adder/subtracter which precludes use of multiplier in first stage
 +
** Dual 24-bit SIMD adder/subtracter/accumulator with two separate CARRYOUT signals
 +
** Quad 12-bit SIMD adder/subtracter/accumulator with four separate CARRYOUT signals
 +
* 48-bit logic unit
 +
** Bitwise logic operations – two-input AND, OR, NOT, NAND, NOR, XOR, and XNOR
 +
** Logic unit mode dynamically selectable via ALUMODE
 +
* Pattern detector
 +
** Overflow/underflow support
 +
** Convergent rounding support
 +
** Terminal count detection support and auto resetting
 +
* Cascading 48-bit P bus supports internal low-power adder cascade
 +
** The 48-bit P bus allows for 12-bit/QUAD or 24-bit/DUAL SIMD adder cascade support
 +
* Optional 17-bit right shift to enable wider multiplier implementation
 +
* Dynamic user-controlled operating modes
 +
** 7-bit OPMODE control bus provides X, Y, and Z multiplexer select signals
 +
* Carry in for the second stage adder
 +
** Support for rounding
 +
** Support for wider add/subtracts
 +
** 3-bit CARRYINSEL multiplexer
 +
* Carry out for the second stage adder
 +
** Support for wider add/subtracts
 +
** Available for each SIMD adder (up to four)
 +
** Cascaded CARRYCASCOUT and MULTSIGNOUT allows for MACC extensions up to 96 bits
 +
* Optional input, pipeline, and output/accumulate registers
 +
* Optional control registers for control signals (OPMODE, ALUMODE, and CARRYINSEL)
 +
* Independent clock enable and resets for greater flexibility, with reset having priority.
 +
* To save power when the first stage multiplier is not being used, the USE_MULT attribute allows the customer to gate off internal multiplier logic.
 
   
 
   
  
 
[[Category:Computing]]
 
[[Category:Computing]]

Revision as of 17:19, 17 December 2018

  • 256 MB DDR3L memory and 16 MB Quad-SPI Flash
  • Arduino shield and Pmod connectors for adding-on hardware devices
  • Programmable from JTAG and Quad-SPI flash
  • 100 MHz & 12MHz external clocks
  • Internal ADC Dual-channel, 1 MSPS
XC7S50-1CSGA324C XC7S25-1CSGA324
Logic Slices 8150 3650
6-Input LUTs 32 600 14 600
Flip-Flops 65 200 29 200
Block RAM 337.5 KByte 202.5 KByte
DSP Slices 120 80
Clock resources 5 PLLs 3 PLLs


FPGA DSP48E1 slice

  • 25-bit pre-adder with D register to enhance the capabilities of the A path
  • INMODE control supports balanced pipelining when dynamically switching between multiply (A*B) and add operations (A:B)
  • 25 x 18 multiplier
  • 30-bit A input of which the lower 25 bits feed the A input of the multiplier, and the entire 30-bit input forms the upper 30 bits of the 48-bit A:B concatenate internal bus.
  • Cascading A and B input
    • Semi-independently selectable pipelining between direct and cascade paths
    • Separate clock enables two-deep A and B set of input registers
  • Independent C input and C register with independent reset and clock enable.
  • CARRYCASCIN and CARRYCASCOUT internal cascade signals to support 96-bit accumulators/adders/subtracters in two DSP48E1 slices
  • MULTSIGNIN and MULTSIGNOUT internal cascade signals with special OPMODE setting to support a 96-bit MACC extension
  • Single Instruction Multiple Data (SIMD) Mode for three-input adder/subtracter which precludes use of multiplier in first stage
    • Dual 24-bit SIMD adder/subtracter/accumulator with two separate CARRYOUT signals
    • Quad 12-bit SIMD adder/subtracter/accumulator with four separate CARRYOUT signals
  • 48-bit logic unit
    • Bitwise logic operations – two-input AND, OR, NOT, NAND, NOR, XOR, and XNOR
    • Logic unit mode dynamically selectable via ALUMODE
  • Pattern detector
    • Overflow/underflow support
    • Convergent rounding support
    • Terminal count detection support and auto resetting
  • Cascading 48-bit P bus supports internal low-power adder cascade
    • The 48-bit P bus allows for 12-bit/QUAD or 24-bit/DUAL SIMD adder cascade support
  • Optional 17-bit right shift to enable wider multiplier implementation
  • Dynamic user-controlled operating modes
    • 7-bit OPMODE control bus provides X, Y, and Z multiplexer select signals
  • Carry in for the second stage adder
    • Support for rounding
    • Support for wider add/subtracts
    • 3-bit CARRYINSEL multiplexer
  • Carry out for the second stage adder
    • Support for wider add/subtracts
    • Available for each SIMD adder (up to four)
    • Cascaded CARRYCASCOUT and MULTSIGNOUT allows for MACC extensions up to 96 bits
  • Optional input, pipeline, and output/accumulate registers
  • Optional control registers for control signals (OPMODE, ALUMODE, and CARRYINSEL)
  • Independent clock enable and resets for greater flexibility, with reset having priority.
  • To save power when the first stage multiplier is not being used, the USE_MULT attribute allows the customer to gate off internal multiplier logic.