This article is being considered for deletion in accordance with Wikipedia's deletion policy. Please share your thoughts on the matter at this article's deletion discussion page. |
This article contains general information about field-programmable gate array (FPGA) devices from AMD Xilinx, based on official specifications.
The fields in the table listed below describe the following:
The model name of most devices has some indication of its size, but the exact scheme used has varied over time:
Generation | Family | Launch | Process | Internal operating voltage | Notes |
---|---|---|---|---|---|
XC2000 | XC2000 | 1985 | 2000nm [6] | 5V | The original FPGA family. This and a few following generations were originally called LCA (Logic Cell Array) devices, but later FPGA gradually became the preferred term. |
XC2000L | 1993 [7] | 3.3V | Low voltage version of XC2000 | ||
XC3000 | XC3000 | 1988 | 1200nm [6] | 5V | Improved logic cell, adds intra-FPGA tri-state bus support |
XC3000A | 1993 | 800nm [3] | XC3000 with more functionality | ||
XC3000L | 1993 | 3.3V | Low voltage version of XC3000A | ||
XC3100 | 1992 | 800nm [8] | 5V | Faster version of XC3000 | |
XC3100A | 1994 [9] | 500nm | Faster version of XC3000A | ||
XC3100L | 1995 [10] | 3.3V | Faster version of XC3000L | ||
XC4000 | XC4000 | 1991 | 5V | Improved logic cell, distributed RAM support, features carry chains and JTAG support | |
XC4000A | 1991 | 5V | XC4000 with fewer routing resources, small chips | ||
XC4000D | 1994 [11] | 5V | Same as XC4000, but with non-functional RAM | ||
XC4000H | 1993 | 5V | XC4000 with more, but less functional, IO cells (for higher pin count) | ||
XC4000E | 1995 [12] | 500nm [13] | 5V | XC4000 upgrade with more functionality | |
XC4000L | 1995 [10] | 3.3V | Low voltage version of XC4000E | ||
XC4000EX | 1996 [14] | 500nm | 5V | XC4000E upgrade with more routing resources, for larger devices | |
XC4000XL | 1997 | 350nm [15] | 3.3V | Low voltage version of XC4000EX | |
XC4000XLA | 1998 [16] | 350nm, [16] 250nm [15] | 3.3V | XC4000XL upgrade with more functionality | |
XC4000XV | 1998 | 250nm [15] | 2.5V | XC4000XLA variant with more routing resources (for large chips) | |
Spartan | 1998 | 500nm, 350nm [17] | 5V | Functionally identical to XC4000E, rebranded as low-end part | |
Spartan XL | 1998 [16] | 350nm, [16] 250nm [17] | 3.3V | Spartan upgrade with more functionality | |
XC5200 | XC5200 | 1994 | 600nm | 5V | A low end FPGA family with bare bones logic cells |
XC5200L | 500nm | 3.3V | Low voltage version of XC5200 | ||
XC6200 | 1995 [12] | 650nm | 5V | An unusual FPGA based on simple logic cells (not LUTs), meant to be used alongside a CPU and optimized for on-the-fly reconfiguration. The only FPGA to have a fully documented configuration format by Xilinx. | |
XC8100 | 1995 [12] | 5V or 3.3V | A very unusual sea-of-gates FPGA, using one-time-programmable antifuse storage for the configuration (instead of RAM). Quickly discontinued in 1996. [18] | ||
Virtex | Virtex | 1998 [19] | 220nm [13] | 2.5V | Improved LUT4-based logic cell, first Xilinx FPGA family to feature DLLs and block RAM |
Spartan-II | 2000 | Identical to Virtex, marketed as low-end part | |||
Virtex E | 1999 | 180nm | 1.8V | Virtex upgrade with more block RAM, more DLLs, and improved IO cells (with differential IO support) | |
Virtex EM | 2000 | Like Virtex E, but with more block RAM | |||
Spartan-IIE | 2001 [20] | Identical to Virtex E, but with some blocks disabled | |||
Virtex-II | Virtex-II | 2001 | 150nm | 1.5V | First Xilinx FPGA family to feature partial reconfiguration and hard multipliers, has DDR input/output support, DLLs have been replaced by much more functional DCMs |
Virtex-II Pro | 2002 | 130nm [21] | 1.2V | Virtex-II upgrade featuring first-generation multi-gigabit transceivers (3.125 Gbit/s, marketed as RocketIO™) and embedded PPC405 cores | |
Virtex-II Pro X | 2003 [22] | Virtex-II Pro with multi-gigabit transceiver upgrade (RocketIO X, 6.25 Gbit/s) | |||
Spartan-3 | Spartan-3 | 2003 | 90nm [17] | 1.2V | A low-end, simplified version of Virtex-II |
Spartan-3E | 2004 [23] | Spartan-3 upgrade with improved hard multipliers and DCMs, but fewer IO cells | |||
Spartan-3A | 2006 | Spartan-3E upgrade with improved block RAM (featuring byte enables) and IO cells | |||
Spartan-3AN | 2007 | Spartan-3A version with integrated SPI flash (as a separate die within the same package), requiring no external bitstream storage | |||
Spartan-3A DSP | Spartan-3A upgrade with new DSP cells (based on Virtex-5 but simplified) replacing the simplistic hard multipliers | ||||
Virtex-4 | 2004 | 90nm | 1.2V | Introduced DSP cells replacing the simple hard multipliers, added simple serdes functionality to all IO cells, improved partial reconfiguration support | |
Virtex-4 LX | The base "logic optimized" version | ||||
Virtex-4 SX | DSP-optimized version of Virtex-4: identical functionality to LX, but with much higher DSP-to-logic ratio | ||||
Virtex-4 FX | Virtex-4 with embedded hard PPC405 cores, Ethernet MAC blocks, and multi-gigabit transceivers (6.5 Gbit/s) | ||||
Virtex-5 | 2006 | 65nm | 1.0V | Introduced new LUT6-based logic cells, new block RAM cells (36kbit, splittable to 2×18kbit), new DSP cells; added new PLL blocks in addition to DCM blocks | |
Virtex-5 LX | The base "logic optimized" version | ||||
Virtex-5 LXT | Adds multi-gigabit transceiver support on top of LX (RocketIO GTP transceivers, 3.75 Gbit/s); also adds hard PCI Express (Gen1 ×8) and gigabit Ethernet MAC blocks | ||||
Virtex-5 SXT | DSP-optimized version of Virtex-5: identical functionality to LXT, but with much higher DSP-to-logic ratio | ||||
Virtex-5 FXT | Virtex-5 with GTX transceivers (6.5 Gbit/s) and hard PPC440 cores | ||||
Virtex-5 TXT | 2009 | Transceiver-optimized version of Virtex-5: has large amount of GTX transceivers (no PPC cores) | |||
Virtex-6 | 2009 | 40nm | 0.9V or 1.0V | Replaces DCM blocks with MMCM blocks (which are an improved version of the existing PLL blocks), minor improvements to logic, DSP, block RAM, and IO cells | |
Virtex-6 LX | The base "logic optimized" version | ||||
Virtex-6 LXT | Adds multi-gigabit transceiver support on top of LX (GTX transceivers, up to 6.6 Gbit/s); also adds hard PCI Express (Gen2 ×8) and gigabit Ethernet MAC blocks | ||||
Virtex-6 SXT | DSP-optimized version of Virtex-6; identical functionality to LXT, but with much higher DSP-to-logic ratio | ||||
Virtex-6 HXT | Transceiver-optimized version of Virtex-6: replaces GTX transceivers with GTH transceivers (11.2 Gb/s) | ||||
Virtex-6 CXT | Identical to LXT, but with some transceivers and hard PCI Express / Ethernet MAC blocks disabled | ||||
Spartan-6 | Spartan-6 LX | 2009 | 45nm | 1.0V or 1.2V | A low-end family built from an amalgamation of Spartan-3A and Virtex-6 features; has a LUT6-based logic cell, slightly improved Spartan-3A DSP cell, 18kbit block RAMs (splittable into 2×9kbit), improved DCM blocks, PLL blocks, IO blocks with serdes support; also has a new hard memory controller block |
Spartan-6 LXT | Spartan-6 version with multi-gigabit transceivers (GTP, 3.2 Gbit/s) and hard PCI Express (Gen 1 ×1) block | ||||
7 Series | 2010 | 28nm | 0.9V, 0.95V, or 1.0V | A successor to the Virtex-6 family, with several separately-marketed sub-families that are made from essentially identical cells with a few exceptions; the IO cells have been split into two variants: HR (high range, 3.3V capable cells) and HP (high performance, 1.8V capable cells with DCI functionality) | |
Spartan 7 | 2017 | Low-end logic-optimized parts, feature HRIO and no special blocks; several parts are identical to Artix parts with transceivers disabled | |||
Artix-7 | 2010 | Low-end parts, feature HRIO, GTP transceivers (6.6 Gbit/s), PCI-Express hard block (Gen 2.1 ×4) | |||
Kintex-7 | 2010 | Middle-end parts, feature HRIO and sometimes HPIO, GTX transceivers (12.5 Gbit/s), PCI-Express hard block (Gen 2.1 ×8) | |||
Virtex-7 | 2010 | High-end parts, feature HPIO and sometimes HRIO, GTX or GTH transceivers (13.1 Gbit/s), PCI-Express hard block (Gen 2.1 ×8 or Gen 3 ×8) | |||
Virtex-7 3D | 2011 | First FPGA made of multiple die in one package, using a special interposer die for very fast and wide inter-die interconnect, essentially presenting as a single unified device made of several "super logic regions" (SLRs) | |||
Virtex-7 HT | 2012 | Virtex-7 3D version that also adds special ultra-high-speed GTZ transceivers (28.05 Gbit/s) via a separate die in the same package | |||
Zynq-7000 | 2011 | An ARM Cortex-A9 based system on a chip integrated with an Artix-7 or a Kintex-7 FPGA on a single die | |||
UltraScale | 2013 [24] | 20nm | 0.9V, 0.95V, or 1.0V | A successor to 7 Series focused on scalability; features a new distributed clock distribution system as well as upgraded logic, DSP, and block RAM cells; hard blocks include the GTH transceivers (16.3 Gbit/s), GTY transceivers (30.5 Gbit/s), PCI Express (Gen3 ×8) blocks, 100G Ethernet MAC, 150G Interlaken blocks | |
Kintex UltraScale | 2013 | Middle-end parts | |||
Virtex UltraScale | 2014 | High-end parts | |||
UltraScale+ | 2015 | 16nm | 0.72V, 0.85V, or 0.9V | An UltraScale upgrade with faster GTY transceivers (32.75 Gbit/s) and improved hard blocks (PCI Express Gen3 ×16 or Gen4 ×8); HR IO is gone and replaced with simpler HD (High Density) IO; some parts feature new UltraRAM (288kbit RAM) blocks | |
Artix UltraScale+ | 2021 | Low-end parts | |||
Kintex UltraScale+ | 2015 | Middle-end parts | |||
Virtex UltraScale+ | 2016 | High-end parts | |||
Virtex UltraScale+ 58G | Features new GTM transceivers (58 Gbit/s PAM4) | ||||
Virtex UltraScale+ HBM | Features High Bandwidth Memory within the same package and an integrated hard memory controller inside the FPGA die | ||||
Zynq UltraScale+ MPSoC | 2015 | An ARM Cortex-A53 based system on a chip integrated with a Kintex UltraScale+ FPGA on the same die | |||
Zynq UltraScale+ RFSoC | 2017 | Like the MPSoC, but adds RF-DAC and RF-ADC blocks for high-speed radios (5G technology) | |||
Alveo | 2018 | Alveo is a series of accelerator boards that are built on UltraScale+-series FPGAs that are identical to some Kintex/Virtex/Zynq devices, but are nominally considered to be distinct chip models | |||
Versal | 2019 | 7nm | 0.7V, 0.8V, or 0.88V | An ARM Cortex-A72 based system on a chip integrated with a new version of FPGA fabric (with new logic, DSP, and block RAM cells), hard DDR memory controllers, and a network-on-chip (NoC) connecting all of the parts together | |
Versal Prime | 2019 | The base Versal parts | |||
Versal AI Core | 2019 | Features the AI engine cores | |||
Versal Premium | Features high-bandwidth versions of the hard blocks | ||||
Versal AI Edge | Lower-end version of AI Core | ||||
Versal HBM | Features HBM memory |
Note: The process information for early FPGA devices (before Virtex) may be inaccurate, due to the devices being subject to die shrink without changing the model name — the process listed above may not be the only process in which a given device has been manufactured.
The XC2000 devices have the following user-programmable blocks: [25]
Model | CLBs | User I/O (max) |
---|---|---|
XC2064, XC2064L | 64 (8×8) | 58 |
XC2018, XC2018L | 100 (10×10) | 74 |
Note: the available user I/O amount varies with chip packaging.
The XC3000 devices have the following user-programmable blocks: [26]
Model | CLBs | User I/O (max) | Tri-state buses | Tri-state buffers per bus |
---|---|---|---|---|
XC3020, XC3020A, XC3020L, XC3120, XC3120A | 64 (8×8) | 64 | 16 | 9 |
XC3030, XC3030A, XC3030L, XC3130, XC3130A | 100 (10×10) | 80 | 20 | 11 |
XC3042, XC3042A, XC3042L, XC3142, XC3142A, XC3142L | 144 (12×12) | 96 | 24 | 13 |
XC3064, XC3064A, XC3064L, XC3164, XC3164A | 224 (16×14) | 120 | 32 | 15 |
XC3090, XC3090A, XC3090L, XC3190, XC3190A, XC3190L | 320 (16×20) | 144 | 40 | 17 |
XC3195, XC3195A | 484 (22×22) | 176 | 44 | 23 |
Note: the available user I/O amount varies with chip packaging.
The XC4000 and Spartan devices have the following user-programmable blocks: [27] [28] [29] [30]
Family | Distributed RAM | H-LUT inputs | CLB flip-flop capabilities | IOB capabilities | Clock buffers |
---|---|---|---|---|---|
XC4000, XC4000A | asynchronous | 1×F, 1×G, 1×general routing | Flip-flop | input and output flip-flops | 4 primary + 4 secondary global buffers |
XC4000H | no flip-flops | ||||
XC4000D | none | input and output flip-flops | |||
XC4000E, XC4000L, Spartan | synchronous or asynchronous write, asynchronous read | 3× any choice of F, G, general routing | input and output flip-flops with clock enable | ||
XC4000EX, XC4000XL, XC4000XLA, XC4000XV | Flip-flop or latch | input and output flip-flops with clock enable, fast capture latch, output multiplexer | 8 global buffers, 8 global low-skew buffers, 8 early clock buffers, 8 fast buffers | ||
Spartan XL | 8 global low-skew buffers |
Model | Family | CLBs | User I/O (max) |
---|---|---|---|
XC4002A | XC4000A | 64 (8×8) | 64 |
XC4002XL | XC4000XL | 64 (8×8) | 64 |
XC4003 | XC4000 | 100 (10×10) | 80 |
XC4003A | XC4000A | 100 (10×10) | 80 |
XC4003H | XC4000H | 100 (10×10) | 160 |
XC4003E | XC4000E | 100 (10×10) | 80 |
XCS05 | Spartan | 100 (10×10) | 77 |
XCS05XL | Spartan XL | 100 (10×10) | 77 |
XC4004A | XC4000A | 144 (12×12) | 96 |
XC4005 | XC4000 | 196 (14×14) | 112 |
XC4005A | XC4000A | 196 (14×14) | 112 |
XC4005H | XC4000H | 196 (14×14) | 192 |
XC4005E | XC4000E | 196 (14×14) | 112 |
XC4005L | XC4000L | 196 (14×14) | 112 |
XC4005XL | XC4000XL | 196 (14×14) | 112 |
XCS10 | Spartan | 196 (14×14) | 112 |
XCS10XL | Spartan XL | 196 (14×14) | 112 |
XC4006 | XC4000 | 256 (16×16) | 128 |
XC4006E | XC4000E | 256 (16×16) | 128 |
XC4008 | XC4000 | 324 (18×18) | 144 |
XC4008E | XC4000E | 324 (18×18) | 144 |
XC4010 | XC4000 | 400 (20×20) | 160 |
XC4010D | XC4000D | 400 (20×20) | 160 |
XC4010E | XC4000E | 400 (20×20) | 160 |
XC4010L | XC4000L | 400 (20×20) | 160 |
XC4010XL | XC4000XL | 400 (20×20) | 160 |
XCS20 | Spartan | 400 (20×20) | 160 |
XCS20XL | Spartan XL | 400 (20×20) | 160 |
XC4013 | XC4000 | 576 (24×24) | 192 |
XC4013D | XC4000D | 576 (24×24) | 192 |
XC4013E | XC4000E | 576 (24×24) | 192 |
XC4013L | XC4000L | 576 (24×24) | 192 |
XC4013XL | XC4000XL | 576 (24×24) | 192 |
XC4013XLA | XC4000XLA | 576 (24×24) | 192 |
XCS30 | Spartan | 576 (24×24) | 192 |
XCS30XL | Spartan XL | 576 (24×24) | 192 |
XC4020E | XC4000E | 784 (28×28) | 224 |
XC4020XL | XC4000XL | 784 (28×28) | 224 |
XC4020XLA | XC4000XLA | 784 (28×28) | 224 |
XCS40 | Spartan | 784 (28×28) | 205 |
XCS40XL | Spartan XL | 784 (28×28) | 205 |
XC4025E | XC4000E | 1024 (32×32) | 256 |
XC4028EX | XC4000EX | 1024 (32×32) | 256 |
XC4028XL | XC4000XL | 1024 (32×32) | 256 |
XC4028XLA | XC4000XLA | 1024 (32×32) | 256 |
XC4036EX | XC4000EX | 1296 (36×36) | 288 |
XC4036XL | XC4000XL | 1296 (36×36) | 288 |
XC4036XLA | XC4000XLA | 1296 (36×36) | 288 |
XC4044XL | XC4000XL | 1600 (40×40) | 320 |
XC4044XLA | XC4000XLA | 1600 (40×40) | 320 |
XC4052XL | XC4000XL | 1936 (44×44) | 352 |
XC4052XLA | XC4000XLA | 1936 (44×44) | 352 |
XC4062XL | XC4000XL | 2304 (48×48) | 384 |
XC4062XLA | XC4000XLA | 2304 (48×48) | 384 |
XC4085XL | XC4000XL | 3136 (56×56) | 448 |
XC4085XLA | XC4000XLA | 3136 (56×56) | 448 |
XC40110XV | XC4000XV | 4096 (64×64) | 448 |
XC40150XV | XC4000XV | 5184 (72×72) | 448 |
XC40200XV | XC4000XV | 7056 (84×84) | 448 |
XC40250XV | XC4000XV | 8464 (92×92) | 448 |
Note: the available user I/O amount varies with chip packaging.
The XC5200 devices have the following user-programmable blocks: [31]
Model | CLBs | User I/O (max) |
---|---|---|
XC5202, XC5202L | 64 (10×10) | 84 |
XC5204 | 120 (10×12) | 124 |
XC5206, XC5206L | 196 (14×14) | 148 |
XC5210 | 324 (18×18) | 196 |
XC5216, XC5216L | 484 (22×22) | 244 |
Note: the available user I/O amount varies with chip packaging.
The XC6200 family is unusual in several ways: [32]
Model | Logic cells | IOBs | Configuration RAM (bits) | Notes |
---|---|---|---|---|
XC6209 | 2304 (48×48) | 192 | 36K | listed as planned product, unclear if it ever reached production |
XC6216 | 4096 (64×64) | 256 | 65K | |
XC6236 | 9216 (96×96) | 384 | 147K | listed as planned product, unclear if it ever reached production |
XC6264 | 16384 (128×128) | 512 | 262K | listed as planned product, unclear if it ever reached production |
The XC8100 family is unusual in several ways: [32]
Model | Logic cells | User I/O (max) | Notes |
---|---|---|---|
XC8100 | 192 (24×8) | 32 | |
XC8101 | 384 (24×16) | 72 | |
XC8103 | 1024 (32×32) | 128 | |
XC8106 | 1728 (48×36) | 168 | |
XC8109 | 2688 (56×48) | 192 | |
XC8112 | 3744 | 248 | planned product that never reached production |
XC8116 | 4800 | 280 | planned product that never reached production |
XC8120 | 6144 | 320 | planned product that never reached production |
The Virtex and Spartan-II devices are made of the following user-programmable blocks:
The Virtex and Spartan-II devices are functionally identical to each other and differ only in available size range, performance, and packaging options. The Spartan-IIE devices use the same die as the corresponding Virtex E devices, but have some block RAM and DLLs disabled.
Model | Family | CLBs | 4-LUTs (CLBs×4) | Block RAMs (4kbit each) | User I/O (max) | User I/O differential pairs (max) | DLLs |
---|---|---|---|---|---|---|---|
XC2S15 | Spartan-II [33] | 96 (12×8) | 384 | 4 | 86 | - | 4 |
XC2S30 | Spartan-II | 216 (18×12) | 864 | 6 | 92 | - | 4 |
XCV50 | Virtex [34] | 384 (24×16) | 1536 | 8 | 180 | - | 4 |
XC2S50 | Spartan-II | 384 (24×16) | 1536 | 8 | 176 | - | 4 |
XCV50E | Virtex E [35] | 384 (24×16) | 1536 | 16 | 176 | 83 | 8 |
XC2S50E | Spartan-IIE [36] | 384 (24×16) | 1536 | 8 | 182 | 83 | 4 |
XCV100 | Virtex | 600 (30×20) | 2400 | 10 | 180 | - | 4 |
XC2S100 | Spartan-II | 600 (30×20) | 2400 | 10 | 176 | - | 4 |
XCV100E | Virtex E | 600 (30×20) | 2400 | 20 | 196 | 83 | 8 |
XC2S100E | Spartan-IIE | 600 (30×20) | 2400 | 10 | 202 | 86 | 4 |
XCV150 | Virtex | 864 (36×24) | 3456 | 12 | 260 | - | 4 |
XC2S150 | Spartan-II | 864 (36×24) | 3456 | 12 | 260 | - | 4 |
XC2S150E | Spartan-IIE | 864 (36×24) | 3456 | 12 | 265 | 114 | 4 |
XCV200 | Virtex | 1176 (42×28) | 4704 | 14 | 284 | - | 4 |
XC2S200 | Spartan-II | 1176 (42×28) | 4704 | 14 | 284 | - | 4 |
XCV200E | Virtex E | 1176 (42×28) | 4704 | 28 | 284 | 119 | 8 |
XC2S200E | Spartan-IIE | 1176 (42×28) | 4704 | 14 | 289 | 120 | 4 |
XCV300 | Virtex | 1536 (48×32) | 6144 | 16 | 316 | - | 4 |
XCV300E | Virtex E | 1536 (48×32) | 6144 | 32 | 316 | 137 | 8 |
XC2S300E | Spartan-IIE | 1536 (48×32) | 6144 | 16 | 329 | 120 | 4 |
XCV400 | Virtex | 2400 (60×40) | 9600 | 20 | 404 | - | 4 |
XCV400E | Virtex E | 2400 (60×40) | 9600 | 40 | 404 | 183 | 8 |
XC2S400E | Spartan-IIE | 2400 (60×40) | 9600 | 40 | 410 | 172 | 4 |
XCV405E | Virtex EM [37] | 2400 (60×40) | 9600 | 140 | 404 | 183 | 8 |
XCV600 | Virtex | 3456 (72×48) | 13824 | 24 | 512 | - | 4 |
XCV600E | Virtex E | 3456 (72×48) | 13824 | 72 | 512 | 247 | 8 |
XC2S600E | Spartan-IIE | 3456 (72×48) | 13824 | 72 | 514 | 205 | 4 |
XCV800 | Virtex | 4704 (84×56) | 18816 | 28 | 512 | - | 4 |
XCV812E | Virtex EM | 4704 (84×56) | 18816 | 280 | 556 | 201 | 8 |
XCV1000 | Virtex | 6144 (96×64) | 24576 | 32 | 512 | - | 4 |
XCV1000E | Virtex E | 6144 (96×64) | 24576 | 96 | 660 | 281 | 8 |
XCV1600E | Virtex E | 7776 (108×72) | 31104 | 144 | 724 | 344 | 8 |
XCV2000E | Virtex E | 9600 (120×80) | 38400 | 160 | 804 | 344 | 8 |
XCV2600E | Virtex E | 12696 (138×92) | 50784 | 184 | 804 | 344 | 8 |
XCV3000E | Virtex E | 16224 (156×104) | 64896 | 208 | 804 | 344 | 8 |
Note: the available user I/O amount varies with chip packaging. Additionally, not all I/Os can be used as part of a differential pair, so the available differential pair count can be smaller than half of the available I/O count.
The Virtex-II devices are made of the following user-programmable blocks:
Virtex-II Pro devices include some additional blocks:
Model | Family | CLBs | 4-LUTs (CLBs×8) | Multiplier blocks and block RAMs (18kbit each) | DCMs | User I/O (max) | Multi-gigabit transceivers (max) | PPC cores |
---|---|---|---|---|---|---|---|---|
XC2V40 | Virtex-II [38] | 64 (8×8) | 512 | 4 | 4 | 88 | - | - |
XC2V80 | Virtex-II | 128 (8×16) | 1024 | 8 | 4 | 120 | - | - |
XC2V250 | Virtex-II | 384 (16×24) | 3072 | 24 | 8 | 200 | - | - |
XC2V500 | Virtex-II | 768 (24×32) | 6144 | 32 | 8 | 264 | - | - |
XC2V1000 | Virtex-II | 1280 (32×40) | 10240 | 40 | 8 | 432 | - | - |
XC2V1500 | Virtex-II | 1920 (40×48) | 15360 | 48 | 8 | 528 | - | - |
XC2V2000 | Virtex-II | 2688 (48×56) | 21504 | 56 | 8 | 624 | - | - |
XC2V3000 | Virtex-II | 3584 (56×64) | 28672 | 96 | 12 | 720 | - | - |
XC2V4000 | Virtex-II | 5760 (72×80) | 46080 | 120 | 12 | 912 | - | - |
XC2V6000 | Virtex-II | 8448 (88×96) | 67584 | 144 | 12 | 1104 | - | - |
XC2V8000 | Virtex-II | 11648 (104×112) | 93184 | 168 | 12 | 1108 | - | - |
XC2VP2 | Virtex-II Pro [39] | 352 | 2816 | 12 | 4 | 204 | RocketIO ×4 | - |
XC2VP4 | Virtex-II Pro | 752 | 6016 | 28 | 4 | 348 | RocketIO ×4 | 1 |
XC2VP7 | Virtex-II Pro | 1232 | 9856 | 44 | 4 | 396 | RocketIO ×8 | 1 |
XC2VP20 | Virtex-II Pro | 2320 | 18560 | 88 | 8 | 564 | RocketIO ×8 | 2 |
XC2VPX20 | Virtex-II Pro X | 2448 | 19584 | 88 | 8 | 552 | RocketIO X ×8 | 1 |
XC2VP30 | Virtex-II Pro | 3424 | 27392 | 136 | 8 | 644 | RocketIO ×8 | 2 |
XC2VP40 | Virtex-II Pro | 4848 | 38784 | 192 | 8 | 804 | RocketIO ×12 | 2 |
XC2VP50 | Virtex-II Pro | 5904 | 47232 | 232 | 8 | 852 | RocketIO ×16 | 2 |
XC2VP70 | Virtex-II Pro | 8272 | 66176 | 328 | 8 | 996 | RocketIO ×20 | 2 |
XC2VPX70 | Virtex-II Pro X | 8272 | 66176 | 308 | 8 | 992 | RocketIO X ×20 | 2 |
XC2VP100 | Virtex-II Pro | 11024 | 88192 | 444 | 12 | 1164 | RocketIO ×20 | 2 |
Note: the available user I/O and multi-gigabit transceiver amount varies with chip packaging.
Note: the CLB count for Virtex-II Pro devices is no longer a simple columns×rows multiplication, as the CLB grid contains holes for the PowerPC cores.
The Spartan-3 devices are made of:
Model | Family | CLBs | 4-LUTs (CLBs×8) | Block RAMs (18kbit each) | Multiplier blocks | DCMs | User I/O (max) | Differential I/O pairs (max) |
---|---|---|---|---|---|---|---|---|
XC3S50 | Spartan-3 [40] | 192 (12×16) | 1536 | 4 | 4 | 2 | 124 | 56 |
XC3S200 | Spartan-3 | 480 (20×24) | 3840 | 12 | 12 | 4 | 173 | 76 |
XC3S400 | Spartan-3 | 896 (28×32) | 7168 | 16 | 16 | 4 | 264 | 116 |
XC3S1000, XC3S1000L | Spartan-3 | 1920 (40×48) | 15360 | 24 | 24 | 4 | 391 | 175 |
XC3S1500, XC3S1500L | Spartan-3 | 3328 (52×64) | 26624 | 32 | 32 | 4 | 487 | 221 |
XC3S2000 | Spartan-3 | 5120 (64×80) | 40960 | 40 | 40 | 4 | 565 | 270 |
XC3S4000 | Spartan-3 | 6912 (72×96) | 55296 | 96 | 96 | 4 | 633 | 300 |
XC3S5000 | Spartan-3 | 8320 (80×104) | 66560 | 104 | 104 | 4 | 633 | 300 |
XC3S100E | Spartan-3E [41] | 240 | 1920 | 4 | 4 | 2 | 108 | 40 |
XC3S250E | Spartan-3E | 612 | 4896 | 12 | 12 | 4 | 172 | 68 |
XC3S500E | Spartan-3E | 1164 | 9312 | 20 | 20 | 4 | 232 | 92 |
XC3S1200E | Spartan-3E | 2168 | 17344 | 28 | 28 | 8 | 304 | 124 |
XC3S1600E | Spartan-3E | 3688 | 29504 | 36 | 36 | 8 | 376 | 156 |
XC3S50A, XC3S50AN | Spartan-3A/3AN [42] | 176 | 1408 | 3 | 3 | 2 | 144 | 64 |
XC3S200A, XC3S200AN | Spartan-3A/3AN | 448 | 3584 | 16 | 16 | 4 | 248 | 112 |
XC3S400A, XC3S400AN | Spartan-3A/3AN | 896 | 7168 | 20 | 20 | 4 | 311 | 142 |
XC3S700A, XC3S700AN | Spartan-3A/3AN | 1472 | 11776 | 20 | 20 | 8 | 372 | 165 |
XC3S1400A, XC3S1400AN | Spartan-3A/3AN | 2816 | 22528 | 32 | 32 | 8 | 502 | 227 |
XC3SD1800A | Spartan-3A DSP [43] | 4160 | 33280 | 84 | DSP48A ×84 | 8 | 519 | 227 |
XC3SD3400A | Spartan-3A DSP | 5968 | 47744 | 126 | DSP48A ×126 | 8 | 469 | 213 |
Note: the available user I/O amount varies with chip packaging. Additionally, not all I/Os can be used as part of a differential pair, so the available differential pair count can be smaller than half of the available I/O count.
Note: for families other than Spartan-3, the CLB grid is irregular and includes holes for block RAMs and DCMs, so the CLB count is not a simple multiplication of columns×rows
The Virtex-4 devices are made of: [44] [45]
The Virtex-4 FX devices additionally contain:
Model | Sub-family | CLBs | 4-LUTs (CLBs×8) | Block RAMs (18kbit each) | DSP48 blocks | DCMs | PMCDs | Clock Regions | I/O banks | User I/Os (max) | Gigabit transceivers (max) | PPC cores |
---|---|---|---|---|---|---|---|---|---|---|---|---|
XC4VLX15 | LX | 1536 (24×64) | 12288 | 48 | 32 | 4 | - | 8 | 9 | 320 | - | - |
XC4VLX25 | LX | 2688 (28×96) | 21504 | 72 | 48 | 8 | 4 | 12 | 11 | 448 | - | - |
XC4VLX40 | LX | 4608 (36×128) | 36864 | 96 | 64 | 8 | 4 | 16 | 13 | 640 | - | - |
XC4VLX60 | LX | 6656 (52×128) | 53248 | 160 | 64 | 8 | 4 | 16 | 13 | 640 | - | - |
XC4VLX80 | LX | 8960 (56×160) | 71680 | 200 | 80 | 12 | 8 | 20 | 15 | 768 | - | - |
XC4VLX100 | LX | 12288 (64×192) | 98304 | 240 | 96 | 12 | 8 | 24 | 17 | 960 | - | - |
XC4VLX160 | LX | 16896 (88×192) | 135168 | 288 | 96 | 12 | 8 | 24 | 17 | 960 | - | - |
XC4VLX200 | LX | 22272 (116×192) | 178176 | 336 | 96 | 12 | 8 | 24 | 17 | 960 | - | - |
XC4VSX25 | SX | 2560 (40×64) | 20480 | 128 | 128 | 4 | - | 8 | 9 | 420 | - | - |
XC4VSX35 | SX | 3840 (40×96) | 30720 | 192 | 192 | 8 | 4 | 12 | 11 | 448 | - | - |
XC4VSX55 | SX | 6144 (48×128) | 49152 | 320 | 512 | 8 | 4 | 16 | 13 | 640 | - | - |
XC4VFX12 | FX | 1368 | 10944 | 36 | 32 | 4 | - | 8 | 9 | 320 | - | 1 |
XC4VFX20 | FX | 2136 | 17088 | 68 | 32 | 4 | - | 8 | 9 | 320 | 8 | 1 |
XC4VFX40 | FX | 4656 | 37248 | 144 | 48 | 8 | 4 | 12 | 11 | 448 | 12 | 2 |
XC4VFX60 | FX | 6320 | 50560 | 232 | 128 | 12 | 8 | 16 | 13 | 576 | 16 | 2 |
XC4VFX100 | FX | 10544 | 84352 | 376 | 160 | 12 | 8 | 20 | 15 | 768 | 20 | 2 |
XC4VFX140 | FX | 15792 | 126336 | 552 | 192 | 20 | 8 | 24 | 17 | 896 | 24 | 2 |
Note: the I/O banks count includes special bank 0, which contains only dedicated configuration I/O (no user I/O)
Note: the available user I/O, I/O bank, and multi-gigabit transceiver amount varies with chip packaging.
Note: the CLB count for FX devices is no longer a simple columns×rows multiplication, as the CLB grid contains holes for the PowerPC cores.
The Virtex-5 devices are made of: [47] [48]
Model | Sub-family | CLBs | 6-LUTs (=CLBs×8) | SLICEMs | Block RAMs (36kbit each) | DSP48E blocks | DCMs | PLLs | Clock regions | I/O banks (max) | User I/Os (max) | Gigabit transceivers (max) | PPC cores | Ethernet MACs | PCI Express cores |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
XC5VLX20T | LXT | 1560 (26×60) | 12480 | 840 | 26 | 24 | 2 | 1 | 6 | 7 | 172 | 4 GTP | - | 2 | 1 |
XC5VLX30 | LX | 2400 (30×80) | 19200 | 1280 | 32 | 32 | 4 | 2 | 8 | 13 | 400 | - | - | - | - |
XC5VLX30T | LXT | 2400 (30×80) | 19200 | 1280 | 36 | 32 | 4 | 2 | 8 | 12 | 360 | 8 GTP | - | 4 | 1 |
XC5VLX50 | LX | 3600 (30×120) | 28800 | 1920 | 48 | 48 | 12 | 6 | 12 | 17 | 560 | - | - | - | - |
XC5VLX50T | LXT | 3600 (30×120) | 28800 | 1920 | 60 | 48 | 12 | 6 | 12 | 15 | 480 | 12 GTP | - | 4 | 1 |
XC5VLX85 | LX | 6480 (54×120) | 51840 | 3360 | 96 | 48 | 12 | 6 | 12 | 17 | 560 | - | - | - | - |
XC5VLX85T | LXT | 6480 (54×120) | 51840 | 3360 | 108 | 48 | 12 | 6 | 12 | 15 | 480 | 12 GTP | - | 4 | 1 |
XC5VLX110 | LX | 8640 (64×160) | 69120 | 4480 | 128 | 64 | 12 | 6 | 16 | 23 | 800 | - | - | - | - |
XC5VLX110T | LXT | 8640 (64×160) | 69120 | 4480 | 148 | 64 | 12 | 6 | 16 | 20 | 680 | 16 GTP | - | 4 | 1 |
XC5VLX155 | LX | 12160 (76×160) | 97280 | 6560 | 192 | 128 | 12 | 6 | 16 | 23 | 800 | - | - | - | - |
XC5VLX155T | LXT | 12160 (76×160) | 97280 | 6560 | 212 | 128 | 12 | 6 | 16 | 20 | 680 | 16 GTP | - | 4 | 1 |
XC5VLX220 | LX | 17280 (108×160) | 138240 | 9120 | 192 | 128 | 12 | 6 | 16 | 23 | 800 | - | - | - | - |
XC5VLX220T | LXT | 17280 (108×160) | 138240 | 9120 | 212 | 128 | 12 | 6 | 16 | 20 | 680 | 16 GTP | - | 4 | 1 |
XC5VLX330 | LX | 25920 (108×240) | 207360 | 13680 | 288 | 192 | 12 | 6 | 24 | 33 | 1200 | - | - | - | - |
XC5VLX330T | LXT | 25920 (108×240) | 207360 | 13680 | 324 | 192 | 12 | 6 | 24 | 27 | 960 | 20 GTP | - | 4 | 1 |
XC5VSX35T | SXT | 2720 (34×80) | 21760 | 2080 | 84 | 192 | 4 | 2 | 8 | 12 | 360 | 8 GTP | - | 4 | 1 |
XC5VSX50T | SXT | 4080 (34×120) | 32640 | 3120 | 132 | 288 | 12 | 6 | 12 | 15 | 480 | 12 GTP | - | 4 | 1 |
XC5VSX95T | SXT | 7360 (46×160) | 58880 | 6080 | 244 | 640 | 12 | 6 | 16 | 19 | 640 | 16 GTP | - | 4 | 1 |
XC5VSX240T | SXT | 18720 (78×240) | 149760 | 16800 | 516 | 1056 | 12 | 6 | 24 | 27 | 960 | 24 GTP | - | 4 | 1 |
XC5VTX150T | TXT | 11600 (58×200) | 92800 | 6000 | 228 | 80 | 12 | 6 | 20 | 20 | 680 | 40 GTX | - | 4 | 1 |
XC5VTX240T | TXT | 18720 (78×240) | 149760 | 9600 | 324 | 96 | 12 | 6 | 24 | 20 | 680 | 48 GTX | - | 4 | 1 |
XC5VFX30T | FXT | 2560 | 20480 | 1520 | 68 | 64 | 4 | 2 | 8 | 12 | 360 | 8 GTX | 1 | 4 | 1 |
XC5VFX70T | FXT | 5600 | 44800 | 3280 | 148 | 128 | 12 | 6 | 16 | 19 | 640 | 16 GTX | 1 | 4 | 3 |
XC5VFX100T | FXT | 8000 | 64000 | 4960 | 228 | 256 | 12 | 6 | 16 | 20 | 680 | 16 GTX | 2 | 4 | 3 |
XC5VFX130T | FXT | 10240 | 81920 | 6320 | 298 | 320 | 12 | 6 | 20 | 24 | 840 | 20 GTX | 2 | 6 | 3 |
XC5VFX200T | FXT | 15360 | 122880 | 9120 | 456 | 384 | 12 | 6 | 24 | 27 | 960 | 24 GTX | 2 | 8 | 4 |
Note: the I/O banks count includes special bank 0, which contains only dedicated configuration I/O (no user I/O)
Note: the available user I/O, I/O bank, and multi-gigabit transceiver amount varies with chip packaging.
Note: the CLB count for FXT devices is no longer a simple columns×rows multiplication, as the CLB grid contains holes for the PowerPC cores.
The Virtex-6 devices are made of: [52]
Model | Sub-family | CLBs | 6-LUTs (=CLBs×8) | SLICEMs | 36 Kibit block RAMs | DSP48E1 blocks | MMCMs | Clock Regions | I/O banks (max) | User I/Os (max) | Gigabit transceivers (max) | Ethernet MACs | PCI Express Cores |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
XC6VLX75T | LXT | 5820 | 46560 | 4180 | 156 | 288 | 6 | 6 | 9 | 360 | 12 GTX | 4 | 1 |
XC6VCX75T | CXT [58] | 5820 | 46560 | 4180 | 156 | 288 | 6 | 6 | 9 | 360 | 12 GTX | 1 | 1 |
XC6VLX130T | LXT | 10000 | 80000 | 6960 | 264 | 480 | 10 | 10 | 15 | 600 | 20 GTX | 4 | 2 |
XC6VCX130T | CXT | 10000 | 80000 | 6960 | 264 | 480 | 10 | 10 | 15 | 600 | 16 GTX | 1 | 2 |
XC6VLX195T | LXT | 15600 | 124800 | 12160 | 344 | 640 | 10 | 10 | 15 | 600 | 20 GTX | 4 | 2 |
XC6VCX195T | CXT | 15600 | 124800 | 12160 | 344 | 640 | 10 | 10 | 15 | 600 | 16 GTX | 1 | 2 |
XC6VLX240T | LXT | 18840 | 150720 | 14600 | 416 | 768 | 12 | 12 | 18 | 720 | 24 GTX | 4 | 2 |
XC6VCX240T | CXT | 18840 | 150720 | 14600 | 416 | 768 | 12 | 12 | 18 | 600 | 16 GTX | 1 | 2 |
XC6VLX365T | LXT | 28440 | 227520 | 16520 | 416 | 576 | 12 | 12 | 18 | 720 | 24 GTX | 4 | 2 |
XC6VLX550T | LXT | 42960 | 343680 | 24800 | 632 | 864 | 18 | 18 | 30 | 1200 | 36 GTX | 4 | 2 |
XC6VLX760 | LX | 59280 | 474240 | 33120 | 720 | 864 | 18 | 18 | 30 | 1200 | - | - | - |
XC6VSX315T | SXT | 24600 | 196800 | 20360 | 704 | 1344 | 12 | 12 | 18 | 720 | 24 GTX | 4 | 2 |
XC6VSX475T | SXT | 37200 | 297600 | 30560 | 1064 | 2016 | 18 | 18 | 21 | 840 | 36 GTX | 4 | 2 |
XC6VHX250T | HXT | 19680 | 157440 | 12160 | 504 | 576 | 12 | 12 | 8 | 320 | 48 GTX | 4 | 4 |
XC6VHX255T | HXT | 19800 | 158400 | 12200 | 516 | 576 | 12 | 12 | 12 | 480 | 24 GTX + 24 GTH | 2 | 2 |
XC6VHX380T | HXT | 29880 | 239040 | 18280 | 768 | 864 | 18 | 18 | 18 | 720 | 48 GTX + 24 GTH | 4 | 4 |
XC6VHX565T | HXT | 44280 | 354240 | 25480 | 912 | 864 | 18 | 18 | 18 | 720 | 24 GTX + 24 GTH | 4 | 4 |
Note: the I/O banks count does not include special bank 0, which contains only dedicated configuration I/O (no user I/O)
Note: the available user I/O, I/O bank, and multi-gigabit transceiver amount varies with chip packaging.
Note: Virtex-6 CLB grid is irregular and contains holes (for configuration center and PCI Express blocks), and so the CLB count is no longer a simple columns×rows multiplication
Note: The CXT devices use an identical die to the corresponding LXT devices, but with some disabled blocks and reduced performance (GTX transceivers have a speed range of 150 Mb/s to 3.75 Gb/s).
The Spartan-6 devices are basically Spartan-3A DSP devices upgraded with some Virtex-6 technology. They are made of: [59]
Model | Sub-family | CLBs | 6-LUTs (=CLBs×8) | SLICEMs | Block RAMs (18kbit each) | DSP48A1 blocks | DCMs | PLLs | Clock Regions | I/O banks | User I/Os (max) | MCBs | Gigabit transceivers (max) | PCI Express Cores | Notes |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
XC6SLX4 | LX | 300 | 2400 | 300 | 12 | 8 | 4 | 2 | 4 | 4 | 132 | - | - | - | uses the same die as XC6SLX9, with lots of disabled blocks |
XC6SLX9 | LX | 715 | 5720 | 360 | 32 | 16 | 4 | 2 | 4 | 4 | 200 | 2 | - | - | |
XC6SLX16 | LX | 1139 | 9112 | 544 | 32 | 32 | 4 | 2 | 4 | 4 | 232 | 2 | - | - | |
XC6SLX25 | LX | 1879 | 15032 | 916 | 52 | 38 | 4 | 2 | 5 | 4 | 266 | 2 | - | - | uses the same die as XC6SLX25T, with disabled transceivers |
XC6SLX25T | LXT | 1879 | 15032 | 916 | 52 | 38 | 4 | 2 | 5 | 4 | 250 | 2 | 2 | 1 | |
XC6SLX45 | LX | 3411 | 27288 | 1602 | 116 | 58 | 8 | 4 | 8 | 4 | 358 | 2 | - | - | uses the same die as XC6SLX45T, with disabled transceivers |
XC6SLX45T | LXT | 3411 | 27288 | 1602 | 116 | 58 | 8 | 4 | 8 | 4 | 296 | 2 | 4 | 1 | |
XC6SLX75 | LX | 5831 | 46648 | 2768 | 172 | 132 | 12 | 6 | 12 | 6 | 408 | 4 | - | - | uses the same die as XC6SLX75T, with disabled transceivers |
XC6SLX75T | LXT | 5831 | 46648 | 2768 | 172 | 132 | 12 | 6 | 12 | 6 | 348 | 4 | 8 | 1 | |
XC6SLX100 | LX | 7911 | 63288 | 3904 | 268 | 180 | 12 | 6 | 12 | 6 | 480 | 4 | - | - | uses the same die as XC6SLX100T, with disabled transceivers |
XC6SLX100T | LXT | 7911 | 63288 | 3904 | 268 | 180 | 12 | 6 | 12 | 6 | 498 | 4 | 8 | 1 | |
XC6SLX150 | LX | 11519 | 92152 | 5420 | 268 | 180 | 12 | 6 | 12 | 6 | 576 | 4 | - | - | uses the same die as XC6SLX150T, with disabled transceivers |
XC6SLX150T | LXT | 11519 | 92152 | 5420 | 268 | 180 | 12 | 6 | 12 | 6 | 540 | 4 | 8 | 1 |
The 7 series devices are made of: [67]
Depending on exact device family, devices may also contain some special blocks:
Model | Family | CLBs | 6-LUTs (=CLBs×8) | SLICEMs | Block RAMs (36kbit each) | DSP48E1 blocks | CMTs | Clock Regions | I/O banks (max) | User I/Os (max) | Gigabit transceivers (max) | PCI Express Cores | XADCs | Processing System | Notes |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
XC7S6 | Spartan-7 | 469* | 3752* | 280* | 5* | 10* | 2 | 2 (2x1) | 2 HR | 100 HR | - | - | - | - | software-limitted version of XC7S15 |
XC7S15 | Spartan-7 | 1000 | 8000 | 600 | 10 | 20 | 2 | 2 (2x1) | 2 HR | 100 HR | - | - | - | - | |
XC7S25 | Spartan-7 | 1825 | 14600 | 1250 | 45 | 80 | 3 | 4 (2x2) | 3 HR | 150 HR | - | - | 1 | - | XC7A25T with disabled transceivers |
XC7S50 | Spartan-7 | 4075 | 32600 | 2400 | 75 | 120 | 5 | 6 (2x3) | 5 HR | 250 HR | - | - | 1 | - | XC7A50T with disabled transceivers |
XC7S75 | Spartan-7 | 6000* | 48000* | 3328* | 90* | 140* | 8 | 8 (2x4) | 8 HR | 400 HR | - | - | 1 | - | software-limitted version of XC7S100 |
XC7S100 | Spartan-7 | 8000 | 64000 | 4400 | 120 | 160 | 8 | 8 (2x4) | 8 HR | 400 HR | - | - | 1 | - | |
XC7A12T | Artix-7 | 1000* | 8000* | 684* | 20* | 40* | 3 | 4 (2x2) | 3 HR | 150 HR | 2 GTP | 1 Gen2×4 | 1 | - | software-limitted version of XC7A25T |
XC7A15T | Artix-7 | 1300* | 10400* | 800* | 25* | 45* | 5 | 6 (2x3) | 5 HR | 250 HR | 4 GTP | 1 Gen2×4 | 1 | - | software-limitted version of XC7A50T |
XC7A25T | Artix-7 | 1825 | 14600 | 1250 | 45 | 80 | 3 | 4 (2x2) | 3 HR | 150 HR | 4 GTP | 1 Gen2×4 | 1 | - | |
XC7A35T | Artix-7 | 2600* | 20800* | 1600* | 50* | 90* | 5 | 6 (2x3) | 5 HR | 250 HR | 4 GTP | 1 Gen2×4 | 1 | - | software-limitted version of XC7A50T |
XC7A50T | Artix-7 | 4075 | 32600 | 2400 | 75 | 120 | 5 | 6 (2x3) | 5 HR | 250 HR | 4 GTP | 1 Gen2×4 | 1 | - | |
XC7A75T | Artix-7 | 5900* | 47200* | 3568* | 105* | 180* | 6 | 8 (2x4) | 6 HR | 300 HR | 8 GTP | 1 Gen2×4 | 1 | - | software-limitted version of XC7A100T |
XC7A100T | Artix-7 | 7925 | 63400 | 4750 | 135 | 240 | 6 | 8 (2x4) | 6 HR | 300 HR | 8 GTP | 1 Gen2×4 | 1 | - | |
XC7A200T | Artix-7 | 16825 | 134600 | 11550 | 365 | 740 | 10 | 10 (2x5) | 10 HR | 500 HR | 16 GTP | 1 Gen2×4 | 1 | - | |
XC7K70T | Kintex-7 | 5125 | 41000 | 3350 | 135 | 240 | 6 | 8 (2x4) | 4 HR + 2 HP | 200 HR + 100 HP | 8 GTX | 1 Gen2×8 | 1 | - | |
XC7K160T | Kintex-7 | 12675 | 101400 | 8750 | 325 | 600 | 8 | 10 (2x5) | 5 HR + 3 HP | 250 HR + 150 HP | 8 GTX | 1 Gen2×8 | 1 | - | |
XC7K325T | Kintex-7 | 25475 | 203800 | 16000 | 445 | 840 | 10 | 14 (2x7) | 7 HR + 3 HP | 350 HR + 150 HP | 16 GTX | 1 Gen2×8 | 1 | - | |
XC7K355T | Kintex-7 | 27825 | 222600 | 20350 | 715 | 1440 | 6 | 12 (2x6) | 6 HR | 300 HR | 24 GTX | 1 Gen2×8 | 1 | - | |
XC7K410T | Kintex-7 | 31775 | 254200 | 22650 | 795 | 1540 | 10 | 14 (2x7) | 7 HR + 3 HP | 350 HR + 150 HP | 16 GTX | 1 Gen2×8 | 1 | - | |
XC7K420T | Kintex-7 | 32575* | 260600* | 23752* | 835* | 1680* | 8 | 16 (2x8) | 8 HR | 400 HR | 32 GTX | 1 Gen2×8 | 1 | - | software-limitted version of XC7K480T |
XC7K480T | Kintex-7 | 37325 | 298600 | 27150 | 955 | 1920 | 8 | 16 (2x8) | 8 HR | 400 HR | 32 GTX | 1 Gen2×8 | 1 | - | |
XC7V585T | Virtex-7 | 45525 | 364200 | 27750 | 795 | 1260 | 18 | 18 (2x9) | 3 HR + 15 HP | 100 HR + 750 HP | 36 GTX | 3 Gen2×8 | 1 | - | |
XC7V2000T | Virtex-7 | 152700 | 1221600 | 86200 | 1292 | 2160 | 24 | 24 (2x12) | 24 HP | 1200 HP | 36 GTX | 4 Gen2×8 | 1 | - | 3D device, made of 4 identical FPGA die |
XC7VX330T | Virtex-7 | 25500 | 204000 | 17550 | 750 | 1120 | 14 | 14 (2x7) | 1 HR + 13 HP | 50 HR + 650 HP | 28 GTH | 2 Gen3×8 | 1 | - | |
XC7VX415T | Virtex-7 | 32200 | 257600 | 26100 | 880 | 2160 | 12 | 12 (2x6) | 12 HP | 600 HP | 48 GTH | 2 Gen3×8 | 1 | - | |
XC7VX485T | Virtex-7 | 37950 | 303600 | 32700 | 1030 | 2800 | 14 | 14 (2x7) | 14 HP | 700 HP | 56 GTX | 4 Gen2×8 | 1 | - | |
XC7VX550T | Virtex-7 | 43300* | 346400* | 34900* | 1180* | 2880* | 20 | 20 (2x10) | 20 HP | 600 HP | 80 GTH | 2 Gen3×8 | 1 | - | software-limitted version of XC7VX690T |
XC7VX690T | Virtex-7 | 54150 | 433200 | 43550 | 1470 | 3600 | 20 | 20 (2x10) | 20 HP | 1000 HP | 80 GTH | 3 Gen3×8 | 1 | - | |
XC7VX980T | Virtex-7 | 76500 | 612000 | 55350 | 1500 | 3600 | 18 | 18 (2x9) | 18 HP | 900 HP | 72 GTH | 3 Gen3×8 | 1 | - | |
XC7VX1140T | Virtex-7 | 109400 | 875200 | 70800 | 1880 | 3360 | 24 | 24 (2x12) | 24 HP | 1100 HP | 96 GTH | 4 Gen3×8 | 1 | - | 3D device, made of 4 identical FPGA die |
XC7VH580T | Virtex-7 | 54700 | 437600 | 35400 | 940 | 1680 | 12 | 12 (2x6) | 12 HP | 600 HP | 48 GTH + 8 GTZ | 2 Gen3×8 | 1 | - | heterogenous 3D device, made of 2 FPGA die (identical to the XC7VX1140T FPGA die) and 1 GTZ die |
XC7VH870T | Virtex-7 | 82050 | 656400 | 53100 | 1410 | 2520 | 18 | 18 (2x9) | 18 HP | 300 HP | 72 GTH + 16 GTZ | 3 Gen3×8 | 1 | - | heterogenous 3D device, made of 3 FPGA die (identical to the XC7VX1140T FPGA die) and 2 GTZ die |
XC7Z007S | Zynq-7000 (Artix-7 FPGA fabric) [73] | 1800* | 14400* | 50* | 66* | 2 | 4 (2x2) | 2 HR | 100 HR | - | - | 1 | single core | software-limitted XC7Z010 with one ARM core disabled | |
XC7Z012S | Zynq-7000 (Artix-7 FPGA fabric) | 4300* | 34400* | 72* | 120* | 3 | 6 (2x3) | 3 HR | 150 HR | 4 GTP | 1 Gen2×4 | 1 | single core | software-limitted XC7Z015 with one ARM core disabled | |
XC7Z014S | Zynq-7000 (Artix-7 FPGA fabric) | 5075* | 40600* | 107* | 170* | 4 | 6 (2x3) | 4 HR | 200 HR | - | - | 1 | single core | software-limitted XC7Z020 with one ARM core disabled | |
XC7Z010 | Zynq-7000 (Artix-7 FPGA fabric) | 2200 | 17600 | 1500 | 60 | 80 | 2 | 4 (2x2) | 2 HR | 100 HR | - | - | 1 | dual core | |
XC7Z015 | Zynq-7000 (Artix-7 FPGA fabric) | 5775 | 46200 | 3600 | 95 | 160 | 3 | 6 (2x3) | 3 HR | 150 HR | 4 GTP | 1 Gen2×4 | 1 | dual core | |
XC7Z020 | Zynq-7000 (Artix-7 FPGA fabric) | 6650 | 53200 | 4350 | 140 | 220 | 4 | 6 (2x3) | 4 HR | 200 HR | - | - | 1 | dual core | |
XC7Z030 | Zynq-7000 (Kintex-7 FPGA fabric) | 9825 | 78600 | 6650 | 265 | 400 | 5 | 8 (2x4) | 2 HR + 3 HP | 100 HR + 150 HP | 4 GTX | 1 Gen2×4 | 1 | dual core | |
XC7Z035 | Zynq-7000 (Kintex-7 FPGA fabric) | 21487.5* | 171900* | 500* | 900 | 8 | 14 (2x7) | 5 HR + 3 HP | 212 HR + 150 HP | 8 GTX | 1 Gen2×8 | 1 | dual core | software-limitted version of XC7Z045 | |
XC7Z045 | Zynq-7000 (Kintex-7 FPGA fabric) | 27325 | 218600 | 17600 | 545 | 900 | 8 | 14 (2x7) | 5 HR + 3 HP | 212 HR + 150 HP | 8 GTX | 1 Gen2×8 | 1 | dual core | |
XC7Z100 | Zynq-7000 (Kintex-7 FPGA fabric) | 34675 | 277400 | 27050 | 755 | 2020 | 8 | 14 (2x7) | 5 HR + 3 HP | 250 HR + 150 HP | 16 GTX | 1 Gen2×8 | 1 | dual core |
Note: many 7 series devices are actually software-limitted versions of larger devices: [74] for example, XC7A35T is the exact same die as XC7A50T, with the same geometry and block count, but the Xilinx development tools artificially limit device usage to the limits in the table above. Such software-limitted devices have very different behavior from "full" devices when nearing full utilization: a design that would have utilized 90% of XC7A50T resources will most likely fail to route (or succeed with very suboptimal performance), since the place&route tool will have very little space to optimally arrange blocks and will likely run out of routing resources due to suboptimal placement. However, an XC7A35T design that utilizes even 100% of its resources will almost certainly route with no performance degradation, as it is far from the real hardware limits, and the placer has full freedom to utilize any subset of the available blocks as long as the total used CLB/DSP/block RAM count is within the allowed software limit. The software-enforced limits are marked with * in the above table.
Note: some Spartan-7 devices are identical to some Artix-7 devices, but with disabled transceivers. However, this is different from the above software-enforced usage limit: the transceivers cannot be used anyway, as their power and I/O pads are not bonded out to device pins in the packaging.
Note: the Artix-7 devices use the same PCI Express block as Kintex-7 devices, with Gen2×8 support, but they can only be used in at most Gen2×4 configuration due to GTP transceiver limitations.
Note: several devices have smaller max User I/Os count than the I/O bank count would imply. This means that the device is not available in any packaging that actually bonds out the complete set of pads.
The UltraScale devices are made of: [75]
The UltraScale+ devices have a few differences:
Zynq UltraScale+ devices are ARM Cortex-A53 based systems on chip sharing a die with an FPGA. The SoC part of the device is called a Processing System (PS). Each model of Zynq UltraScale+ MPSoC is available in up to 3 sub-models: CG, EG, and EV. The main differences among these sub-models are in the CPU and GPU configurations. [77] Zynq UltraScale+ RFSoC devices are available in DR sub-models, which have PS capabilities identical to MPSoC EG sub-models.
CG | EG and DR | EV | |
---|---|---|---|
APU | 2x Arm A53 | 4x Arm A53 | 4x Arm A53 |
RPU | 2x Arm R5 | 2x Arm R5 | 2x Arm R5 |
GPU | - | Arm Mali-400MP2 | Arm Mali-400MP2 |
VCU | - | - | H.264/H.265 |
Zynq UltraScale+ devices have some additional blocks:
Model | Family | CLBs | 6-LUTs (=CLBs×8) | SLICEMs | Block RAMs (36kbit each) | Ultra RAMs (288kbit each) | DSP48E2 blocks | CMTs | Clock Regions | I/O banks (max) | User I/Os (max) | Gigabit transceivers (max) | PCI Express Cores | 100 Gigabit Ethernet MACs | Intelaken Cores | Others | Notes |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
XCKU025 | Kintex UltraScale | 18180 | 145440 | 8460 | 360 | - | 1152 | 6 | 12 (4×3) | 2 HR + 4 HP | 104 HR + 208 HP | 12 GTH | 1 | - | - | - | cut (partial) version of XCKU040 |
XCKU035 | Kintex UltraScale | 25391* | 203128* | 540* | - | 1700* | 10 | 20 (4×5) | 2 HR + 8 HP | 104 HR + 416 HP | 16 GTH | 2* | - | - | - | software-limitted version of XCKU040 | |
XCKU040 | Kintex UltraScale | 30300 | 242400 | 14100 | 600 | - | 1920 | 10 | 20 (4×5) | 2 HR + 8 HP | 104 HR + 416 HP | 20 GTH | 3 | - | - | - | |
XCKU060 | Kintex UltraScale | 41460 | 331680 | 18360 | 1080 | - | 2760 | 12 | 30 (6×5) | 2 HR + 10 HP | 104 HR + 520 HP | 32 GTH | 3 | - | - | - | |
XCKU085 | Kintex UltraScale | 62190* | 497520* | 1620* | - | 4100* | 22 | 54 (6×9) | 4 HR + 18 HP | 104 HR + 572 HP | 56 GTH | 4* | - | - | - | software-limitted version of XCKU115 with one partial die | |
XCKU095 | Kintex UltraScale | 67200 | 537600 | 9600 | 1680* | - | 768 | 16 | 40 (5×8) | 1 HR + 15 HP | 52 HR + 650 HP | 32 GTH + 32 GTY | 4 | 2* | 2* | - | software-limitted version of XCVU095 |
XCKU115 | Kintex UltraScale | 82920 | 663360 | 36720 | 2160 | - | 5520 | 24 | 60 (6×10) | 4 HR + 20 HP | 156 HR + 676 HP | 64 GTH | 6 | - | - | - | a multi-die FPGA made of two XCKU060 |
XCVU065 | Virtex UltraScale | 44760 | 358080 | 9660 | 1260 | - | 600 | 10 | 30 (6×5) | 1 HR + 9 HP | 52 HR + 468 HP | 20 GTH + 20 GTY | 2 | 3 | 3 | - | |
XCVU080 | Virtex UltraScale | 55714* | 445712* | 1421* | - | 672* | 16 | 40 (5×8) | 1 HR + 15 HP | 52 HR + 780 HP | 32 GTH + 32 GTY | 4 | 4 | 6 | - | software-limitted version of XCVU095 | |
XCVU095 | Virtex UltraScale | 67200 | 537600 | 9600 | 1728 | - | 768 | 16 | 40 (5×8) | 1 HR + 15 HP | 52 HR + 780 HP | 32 GTH + 32 GTY | 4 | 4 | 6 | - | |
XCVU125 | Virtex UltraScale | 89520 | 716160 | 19320 | 2520 | - | 1200 | 20 | 60 (6×10) | 2 HR + 18 HP | 104 HR + 780 HP | 40 GTH + 40 GTY | 4 | 6 | 6 | - | a multi-die FPGA made of two XCVU065 |
XCVU160 | Virtex UltraScale | 115800* | 926400* | 3276* | - | 1560* | 28 | 84 (6×14) | 2 HR + 26 HP | 52 HR + 650 HP | 52 GTH + 52 GTY | 4* | 9 | 8 | - | software-limitted version of XCVU190 with one partial die | |
XCVU190 | Virtex UltraScale | 134280 | 1074240 | 28980 | 3780 | - | 1800 | 30 | 90 (6×15) | 3 HR + 27 HP | 52 HR + 650 HP | 60 GTH + 60 GTY | 6 | 9 | 9 | - | a multi-die FPGA made of three XCVU065 |
XCVU440 | Virtex UltraScale | 316620 | 2532960 | 57420 | 2520 | - | 2880 | 30 | 135 (9×15) | 3 HR + 27 HP | 52 HR + 1404 HP | 48 GTH | 6 | 3 | - | - | a multi-die FPGA made of three dedicated die |
XCAU7P | Artix UltraScale+ | 4680 | 37440 | 108 | 215 | 2 | 2 HP + 6 HD | 104 HP + 144 HD | 4 GTH | 1 PCIE4C | - | - | - | not yet in production | |||
XCAU10P | Artix UltraScale+ | 5500* | 44000* | 100* | - | 400 | 3 | 6 (2x3) | 3 HP + 3 HD | 156 HP + 72 HD | 12 GTH | 1 PCIE4C | - | - | - | software-limitted version of XCAU15P | |
XCAU15P | Artix UltraScale+ | 9720 | 77760 | 5040 | 144 | - | 576 | 3 | 6 (2x3) | 3 HP + 3 HD | 156 HP + 72 HD | 12 GTH | 1 PCIE4C | - | - | - | |
XCAU20P | Artix UltraScale+ | 13625* | 109000* | 200* | - | 900* | 3* | 16 (4x4) | 3 HP + 3 HD | 156 HP + 72 HD | 12 GTY | 1 PCIE4 | - | - | - | software-limitted version of XCKU5P | |
XCAU25P | Artix UltraScale+ | 17625* | 141000* | 300* | - | 1200* | 4 | 16 (4x4) | 4 HP + 4 HD | 208 HP + 96 HD | 12 GTY | 1 PCIE4 | - | - | - | software-limitted version of XCKU5P | |
XCKU3P | Kintex UltraScale+ | 20340* | 162720* | 360* | 48* | 1368* | 4 | 16 (4×4) | 4 HP + 4 HD | 208 HP + 96 HD | 16 GTY | 1 PCIE4 | - | - | - | software-limitted version of XCKU5P | |
XCKU5P | Kintex UltraScale+ | 27120 | 216960 | 12480 | 480 | 64 | 1824 | 4 | 16 (4×4) | 4 HP + 4 HD | 208 HP + 96 HD | 16 GTY | 1 PCIE4 | 1 | - | - | |
XCKU9P | Kintex UltraScale+ | 34260 | 274080 | 18000 | 912 | - | 2520 | 4 | 25 (4×7-3) | 4 HP + 5 HD | 208 HP + 96 HD | 28 GTH | - | - | - | - | same die as XCZU9*, with disabled PS |
XCKU11P | Kintex UltraScale+ | 37320 | 298560 | 18540 | 600 | 80 | 2928 | 8 | 29 (4×8-3) | 8 HP + 4 HD | 416 HP + 96 HD | 32 GTH + 20 GTY | 4 PCIE4 | 2 | 1 | - | same die as XCZU11*, with disabled PS |
XCKU13P | Kintex UltraScale+ | 42660 | 341280 | 23040 | 744 | 112 | 3528 | 4 | 25 (4×7-3) | 4 HP + 5 HD | 208 HP + 96 HD | 28 GTH | - | - | - | - | same die as XCZU15*, with disabled PS |
XCKU15P | Kintex UltraScale+ | 65340 | 522720 | 20160 | 984 | 128 | 1968 | 11 | 41 (4×11-3) | 11 HP + 4 HD | 572 HP + 96 HD | 44 GTH + 32 GTY | 5 PCIE4 | 4 | 4 | - | same die as XCZU19*, with disabled PS |
XCKU19P | Kintex UltraScale+ | 105300 | 842400 | 1728 | 288 | 1080 | 9 | 45 (5×9) | 9 HP + 3 HD | 468 HP + 72 HD | 32 GTY | 3 PCIE4C | 1 | - | - | partial version of XCVU23P | |
XCVU3P | Virtex UltraScale+ | 49260 | 394080 | 24660 | 720 | 320 | 2280 | 10 | 30 (6×5) | 10 HP | 520 HP | 40 GTY | 2 PCIE4 | 3 | 3 | - | |
XCVU5P | Virtex UltraScale+ | 75072.125* | 600577* | 1024* | 470* | 3474* | 20 | 60 (6×10) | 20 HP | 832 HP | 80 GTY | 4 PCIE4 | 4* | 4* | - | software limited version of XCVU7P | |
XCVU7P | Virtex UltraScale+ | 98520 | 788160 | 49320 | 1440 | 640 | 4560 | 20 | 60 (6×10) | 20 HP | 832 HP | 80 GTY | 4 PCIE4 | 6 | 6 | - | a multi-die FPGA made of two XCVU3P FPGAs |
XCVU9P, XCU200 | Virtex UltraScale+ | 147780 | 1182240 | 75120 | 2160 | 960 | 6840 | 30 | 90 (6×15) | 30 HP | 832 HP | 120 GTY | 6 PCIE4 | 9 | 9 | - | a multi-die FPGA made of three XCVU3P FPGAs; XCU200 is the designation of the FPGA used on the Alveo U200 board, which is rebadged XCVU9P |
XCVU11P | Virtex UltraScale+ | 162000 | 1296000 | 74160 | 2016 | 960 | 9216 | 12 | 96 (8×12) | 12 HP | 624 HP | 96 GTY | 3 PCIE4 | 9 | 6 | - | a multi-die FPGA made of three die |
XCVU13P, XCU250 | Virtex UltraScale+ | 216000 | 1728000 | 98880 | 2688 | 1280 | 12288 | 16 | 128 (8×16) | 16 HP | 832 HP | 128 GTY | 4 PCIE4 | 12 | 8 | - | a multi-die FPGA made of four die (same base die as XCVU11P); XCU250 is the designation of the FPGA used on the Alveo U250 board, which is rebadged XCVU13P |
XCVU19P | Virtex UltraScale+ | 510720 | 4085760 | 119520 | 2160 | 320 | 3840 | 40 | 180 (9×20) | 40 HP + 4 HD | 1976 HP + 96 HD | 80 GTY | 8 PCIE4C | - | - | - | a multi-die FPGA made of four die |
XCVU23P, XCU26 | Virtex UltraScale+ | 128700 | 1029600 | 29040 | 2112 | 352 | 1320 | 11 | 55 (5×11) | 11 HP + 3 HD | 572 HP + 72 HD | 34 GTY + 4 GTM | 4 PCIE4C | 2 | - | - | XCU26 is the designation of the FPGA used on the Alveo SN1022 SmartNIC board, which is a rebadged XCVU23P |
XCVU27P | Virtex UltraScale+ | 162000* | 1296000* | 74160* | 2016* | 960* | 9216* | 16 | 128 (8×16) | 16 HP | 676 HP | 32 GTY + 48 GTM | 1 PCIE4 | 15 | 8 | - | software-limitted version of XCVU29P |
XCVU29P | Virtex UltraScale+ | 216000 | 1728000 | 98880 | 2688 | 1280 | 12288 | 16 | 128 (8×16) | 16 HP | 676 HP | 32 GTY + 48 GTM | 1 PCIE4 | 15 | 8 | - | a multi-die FPGA made of four die; one die is identical to the one used in XCVU11P, the other three contain the GTM transceivers |
XCVU31P | Virtex UltraScale+ HBM | 54960 | 439680 | 25680 | 672 | 320 | 2880 | 4 | 32 (8×4) | 4 HP | 208 HP | 32 GTY | 4 PCIE4C | 2 | - | HBM memory controller + 4GB HBM memory stack | same die as XCVU33P, but with less HBM memory |
XCVU33P | Virtex UltraScale+ HBM | 54960 | 439680 | 25680 | 672 | 320 | 2880 | 4 | 32 (8×4) | 4 HP | 208 HP | 32 GTY | 4 PCIE4C | 2 | - | 2 HBM memory controllers + 2×4GB HBM memory stacks | |
XCVU35P, XCU50 | Virtex UltraScale+ HBM | 108960 | 871680 | 50400 | 1344 | 640 | 5952 | 8 | 64 (8×8) | 8 HP | 416 HP | 64 GTY | 1 PCIE4 + 4 PCIE4C | 5 | 2 | 2 HBM memory controllers + 2×4GB HBM memory stacks | a multi-die FPGA made of XCVU33P + one XCVU11P die; XCU50 is the designation of the FPGA used on the Alveo U50 board, which is rebadged XCVU35P |
XCVU37P, XCU280, XCU55C | Virtex UltraScale+ HBM | 162960 | 1303680 | 75120 | 2016 | 960 | 9024 | 12 | 96 (8×12) | 12 HP | 624 HP | 96 GTY | 2 PCIE4 + 4 PCIE4C | 8 | 4 | 2 HBM memory controllers + 2×4GB HBM memory stacks | a multi-die FPGA made of XCVU33P + two XCVU11P die; XCU280 and XCU55C are the designations of the FPGAs used on the Alveo U280 and Alveo U55C boards, respectively, which are rebadged XCVU37P |
XCVU45P | Virtex UltraScale+ HBM | 108960 | 871680 | 50400 | 1344 | 640 | 5952 | 8 | 64 (8×8) | 8 HP | 416 HP | 64 GTY | 1 PCIE4 + 4 PCIE4C | 5 | 2 | 2 HBM memory controllers + 2×8GB HBM memory stacks | same as XCVU35P, but with more HBM memory |
XCVU47P | Virtex UltraScale+ HBM | 162960 | 1303680 | 75120 | 2016 | 960 | 9024 | 12 | 96 (8×12) | 12 HP | 624 HP | 96 GTY | 2 PCIE4 + 4 PCIE4C | 8 | 4 | 2 HBM memory controllers + 2×8GB HBM memory stacks | same as XCVU37P, but with more HBM memory |
XCVU57P | Virtex UltraScale+ HBM | 162960 | 1303680 | 75120 | 2016 | 960 | 9024 | 12 | 96 (8×12) | 12 HP | 624 HP | 32 GTY + 32 GTM | 4 PCIE4C | 10 | 4 | 2 HBM memory controllers + 2×8GB HBM memory stacks | same as XCVU47P, but with the XCVU11P die replaced with XCVU27P GTM-containing die |
XCZU1CG, XCZU1EG | Zynq UltraScale+ MPSoC | 4680 | 37440 | 108 | - | 216 | 3 | 3 (1×3) | 3 HP + 1 HD | 156 HP + 24 HD | - | - | - | - | Processing System | ||
XCZU2CG, XCZU2EG | Zynq UltraScale+ MPSoC | 5904* | 47232* | 150* | - | 240* | 3 | 6 (2×3) | 3 HP + 4 HD | 156 HP + 96 HD | - | - | - | - | Processing System | software-limitted XCZU3 | |
XCZU3CG, XCZU3EG | Zynq UltraScale+ MPSoC | 8820 | 70560 | 3600 | 216 | - | 360 | 3 | 6 (2×3) | 3 HP + 4 HD | 156 HP + 96 HD | - | - | - | - | Processing System | |
XCZU3TCG XCZU3TEG | Zynq UltraScale+ MPSoC | 9000 | 72000 | 144 | 48 | 576 | 1 | 1 HP + 3 HD | 52 HP + 72 HD | 8 GTH | 1 PCIE4C | - | - | Processing System | not yet in production | ||
XCZU4CG, XCZU4EG, XCZU4EV | Zynq UltraScale+ MPSoC | 10980* | 87840* | 128* | 48* | 728* | 4 | 12 (3×4) | 4 HP + 4 HD | 156 HP + 96 HD | 16 GTH | 2 PCIE4 | - | - | Processing System, VCU | software-limitted XCZU5 | |
XCZU5CG, XCZU5EG, XCZU5EV, XCK26 | Zynq UltraScale+ MPSoC | 14640 | 117120 | 7200 | 144 | 64 | 1248 | 4 | 12 (3×4) | 4 HP + 4 HD | 156 HP + 96 HD | 16 GTH | 2 PCIE4 | - | - | Processing System, VCU | XCK26 is the designation of the device on the Kria K26 system on module, which is a rebadged XCZU5EV device |
XCZU6CG, XCZU6EG | Zynq UltraScale+ MPSoC | 26825.5* | 214604* | 714* | - | 1973* | 4 | 25 (4×7-3) | 4 HP + 5 HD | 208 HP + 120 HD | 24 GTH | - | - | - | Processing System | software-limitted XCZU9 | |
XCZU7CG, XCZU7EG, XCZU7EV, XCU30 | Zynq UltraScale+ MPSoC | 28800 | 230400 | 12720 | 312 | 96 | 1728 | 8 | 20 (4×6-4) | 8 HP + 4 HD | 416 HP + 48 HD | 24 GTH | 2 PCIE4 | - | - | Processing System, VCU | XCU30 is the designation of the devices on the Alveo U30 board, which are rebadged XCZU7EV devices |
XCZU9CG, XCZU9EG | Zynq UltraScale+ MPSoC | 34260 | 274080 | 18000 | 912 | - | 2520 | 4 | 25 (4×7-3) | 4 HP + 5 HD | 208 HP + 120 HD | 24 GTH | - | - | - | Processing System | |
XCZU11EG | Zynq UltraScale+ MPSoC | 37320 | 298560 | 18540 | 600 | 80 | 2928 | 8 | 29 (4×8-3) | 8 HP + 4 HD | 416 HP + 96 HD | 32 GTH + 16 GTY | 4 PCIE4 | 2 | 1 | Processing System | |
XCZU15EG | Zynq UltraScale+ MPSoC | 42660 | 341280 | 23040 | 744 | 112 | 3528 | 4 | 25 (4×7-3) | 4 HP + 5 HD | 208 HP + 120 HD | 24 GTH | - | - | - | Processing System | |
XCZU17EG | Zynq UltraScale+ MPSoC | 52925.375* | 423403* | 796* | 102* | 1590* | 11 | 41 (4×11-3) | 11 HP + 4 HD | 572 HP + 96 HD | 44 GTH + 28 GTY | 4* PCIE4 | 2* | 2* | Processing System | software-limitted XCZU19 | |
XCZU19EG, XCU25 | Zynq UltraScale+ MPSoC | 65340 | 522720 | 20160 | 984 | 128 | 1968 | 11 | 41 (4×11-3) | 11 HP + 4 HD | 572 HP + 96 HD | 44 GTH + 28 GTY | 5 PCIE4 | 4 | 4 | Processing System | XCU25 is the designation of the device on the Alveo U25 board, which is a rebadged XCZU19EG device |
XCZU21DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 208 HP + 72 HD | 16 GTY | 2 PCIE4 | 2 | 1 | Processing System, 8 SD-FEC cores | same die as XCZU28DR |
XCZU25DR | Zynq UltraScale+ RFSoC | 38761* | 310088* | 19561* | 792* | 48* | 3145* | 6 | 33 (6×6-3) | 6 HP + 4 HD | 299 HP + 48 HD | 8 GTY | 1 PCIE4 | 1 | 1 | Processing System, 8×4GSPS RF-ADC, 8×6.5GSPS RF-DAC | partial XCZU28DR die |
XCZU27DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 299 HP + 48 HD | 16 GTY | 2 PCIE4 | 2 | 1 | Processing System, 8×4GSPS RF-ADC, 8×6.5GSPS RF-DAC | same die as XCZU28DR |
XCZU28DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 299 HP + 48 HD | 16 GTY | 2 PCIE4 | 2 | 1 | Processing System, 8×4GSPS RF-ADC, 8×6.5GSPS RF-DAC, 8 SD-FEC cores | |
XCZU29DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 312 HP + 96 HD | 16 GTY | 2 PCIE4 | 2 | 1 | Processing System, 16×2GSPS RF-ADC, 16×6.5GSPS RF-DAC | same die as XCZU28DR |
XCZU39DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 312 HP + 96 HD | 16 GTY | 2 PCIE4 | 2 | 1 | Processing System, 16×2.2GSPS RF-ADC, 16×6.5GSPS RF-DAC | same die as XCZU28DR |
XCZU42DR | Zynq UltraScale+ RFSoC | 27960 | 223680 | 13740 | 648 | 160 | 1872 | 5 | 22 (5x5-3) | 5 HP + 1 HD | 128 HP + 24 HD | 8 GTY | - | 1 | - | Processing System, 2×5GSPS RF-ADC, 8×2.5GSPS RF-ADC, 8×10GSPS RF-DAC | same die as XCZU67DR |
XCZU43DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 299 HP + 48 HD | 16 GTY | 2 PCIE4C | 2 | 1 | Processing System, 4×5GSPS RF-ADC, 4×10GSPS RF-DAC | same die as XCZU48DR |
XCZU46DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 312 HP + 48 HD | 16 GTY | 2 PCIE4C | 2 | 1 | Processing System, 4×5GSPS RF-ADC, 8×2.5GSPS RF-ADC 12×10GSPS RF-DAC, 8 SD-FEC cores | same die as XCZU48DR |
XCZU47DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 299 HP + 48 HD | 16 GTY | 2 PCIE4C | 2 | 1 | Processing System, 8×5GSPS RF-ADC, 8×10GSPS RF-DAC | same die as XCZU48DR |
XCZU48DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 299 HP + 48 HD | 16 GTY | 2 PCIE4C | 2 | 1 | Processing System, 8×5GSPS RF-ADC, 8×10GSPS RF-DAC, 8 SD-FEC cores | |
XCZU49DR | Zynq UltraScale+ RFSoC | 53160 | 425280 | 26700 | 1080 | 80 | 4272 | 8 | 45 (6×8-3) | 8 HP + 6 HD | 312 HP + 96 HD | 16 GTY | 2 PCIE4C | 2 | 1 | Processing System, 16×2.5GSPS RF-ADC, 16×10GSPS RF-DAC | same die as XCZU48DR |
XCZU65DR | Zynq UltraScale+ RFSoC | 27960 | 223680 | 13740 | 648 | 160 | 1872 | 5 | 22 (5x5-3) | 5 HP + 1 HD | 128 HP + 24 HD | 8 GTY | - | 1 | - | Processing System, Digital Front End, 6×5.9GSPS RF-ADC, 6×10GSPS RF-DAC | same die as XCZU67DR |
XCZU67DR | Zynq UltraScale+ RFSoC | 27960 | 223680 | 13740 | 648 | 160 | 1872 | 5 | 22 (5x5-3) | 5 HP + 1 HD | 128 HP + 24 HD | 8 GTY | - | 1 | - | Processing System, Digital Front End, 2×5.9GSPS RF-ADC, 8×2.95GSPS RF-ADC, 8×10GSPS RF-DAC |
Note: the clock region grid is irregular on some UltraScale+ devices because of a hole in bottom for the Processing System (and possibly the VCU).
In 2018, Xilinx announced a product line called Versal. [78] Versal chips contain CPU, GPU, DSP, and FPGA components. Versal is fabricated using 7nm process technology.
The Versal devices are made of: [79]
Model | Family | SLICEs | 6-LUTs (=SLICEs×8) | Block RAMs (36kbit each) | Ultra RAMs (288kbit each) | DSP58 blocks | DDRMC blocks | XPIO banks | HDIO banks | NoC master/slave ports | Transceivers | PCI Express blocks | Ethernet MACs | Interlaken blocks | HSC blocks | AI Engines | Other | Notes |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
XCVE2002 | Versal AI Edge | 2500* | 20000* | 24* | 24* | 90* | 1 | 4 | 0 | 2 | - | - | - | - | - | 8 AI-ML | XRAM | not yet in production |
XCVE2102 | Versal AI Edge | 4576 | 36608 | 47 | 47 | 176 | 1 | 4 | 0 | 2 | - | - | - | - | - | 12 AI-ML | XRAM | not yet in production |
XCVE2202 | Versal AI Edge | 13125* | 105000* | 108* | 108* | 324* | 1 | 4 | 1 | 5 | 8 GTYP | 1 Gen4 | 1 MRMAC | - | - | 24 AI-ML (12×2) | XRAM | software-limitted version of XCVE2302, not yet in production |
XCVE2302 | Versal AI Edge | 18784 | 150272 | 155 | 155 | 464 | 1 | 4 | 1 | 5 | 8 GTYP | 1 Gen4 | 1 MRMAC | - | - | 34 AI-ML (17×2) | XRAM | not yet in production |
XCVE1752 | Versal AI Edge | 56064 | 448512 | 954 | 462 | 1312 | 3 | 9 | 2 | 21 | 44 GTY | 4 Gen4 | 2 MRMAC | - | - | 304 (38×8) | CPM Gen4 | software-limitted version of XCVC1702 |
XCVE2602 | Versal AI Edge | 46875* | 375000* | 476* | 224* | 984* | 3 | 9 | 2 | 21 | 32 GTYP | 4 Gen5 | 2 MRMAC | - | - | 152 AI-ML (38×4) | CPM Gen5, 2×VDE | software-limitted version of XCVC2802, not yet in production |
XCVE2802 | Versal AI Edge | 65088 | 520704 | 600 | 264 | 1312 | 3 | 9 | 2 | 21 | 32 GTYP | 4 Gen5 | 2 MRMAC | - | - | 304 AI-ML (38×8) | CPM Gen5, 4×VDE | software-limitted version of XCVC2802, not yet in production |
XCVC1352 | Versal AI Core | 30848 | 246784 | 441 | 209 | 928 | 2 | 7 | 2 | 10 | 8 GTYP | 1 Gen4 | 1 MRMAC | - | - | 128 | XRAM | not yet in production |
XCVC1502 | Versal AI Core | 46544 | 372352* | 848 | 390 | 1032 | 3 | 9 | 1 | 21 | 32 GTY | 4 Gen4 | 3 MRMAC | - | - | 198 (33×6) | CPM Gen4 | software-limitted version of XCVC1702 |
XCVC1702 | Versal AI Core | 56064 | 448512 | 954 | 462 | 1312 | 3 | 9 | 2 | 21 | 44 GTY | 4 Gen4 | 4 MRMAC | - | - | 304 (38×8) | CPM Gen4 | |
XCVC1802 | Versal AI Core | 90625* | 725000* | 800* | 325* | 1600* | 4 | 12 | 2 | 28 | 44 GTY | 4 Gen4 | 4 MRMAC | - | - | 300 (50×6) | CPM Gen4 | software-limitted version of XCVC1902 |
XCVC1902 | Versal AI Core | 112480 | 899840 | 967 | 463 | 1968 | 4 | 12 | 2 | 28 | 44 GTY | 4 Gen4 | 4 MRMAC | - | - | 400 (50×8) | CPM Gen4 | |
XCVC2602 | Versal AI Core | 46875* | 375000* | 476* | 224* | 984* | 3 | 9 | 2 | 21 | 32 GTYP | 4 Gen5 | 2 MRMAC | - | - | 152 AI-ML (38×4) | CPM Gen5, 2×VDE | software-limitted version of XCVC2802, not yet in production |
XCVC2802 | Versal AI Core | 65088 | 520704 | 600 | 264 | 1312 | 3 | 9 | 2 | 21 | 32 GTYP | 4 Gen5 | 2 MRMAC | - | - | 304 AI-ML (38×8) | CPM Gen5, 4×VDE | not yet in production |
XCVM1102 | Versal Prime | 18784 | 150272 | 155 | 155 | 464 | 1 | 4 | 1 | 5 | 8 GTYP | 1 Gen4 | 1 MRMAC | - | - | - | XRAM | software-limitted version of XCVE2302, not yet in production |
XCVM1302 | Versal Prime | 39616* | 316928* | 502* | 178* | 832* | 2 | 8 | 1 | 9* | 24 GTY | 2 Gen4 | 2 MRMAC | - | - | - | CPM Gen4 | software-limitted version of XCVM1402 |
XCVM1402 | Versal Prime | 70720 | 565760 | 1150 | 286 | 1696 | 4 | 12 | 1 | 18 | 24 GTY | 2 Gen4 | 2 MRMAC | - | - | - | CPM Gen4 | |
XCVM1502 | Versal Prime | 56064 | 448512 | 954 | 462 | 1312 | 3 | 9 | 2 | 21 | 44 GTY | 4 Gen4 | 4 MRMAC | - | - | - | CPM Gen4 | XCVC1702 with AI Engines disabled |
XCVM1802 | Versal Prime | 112480 | 899840 | 967 | 463 | 1968 | 4 | 12 | 2 | 28 | 44 GTY | 4 Gen4 | 4 MRMAC | - | - | - | CPM Gen4 | XCVC1902 with AI Engines disabled |
XCVM2202 | Versal Prime | 65088 | 520704 | 600 | 264 | 1312 | 3 | 9 | 2 | 21 | 32 GTYP | 4 Gen5 | 2 MRMAC | - | - | - | CPM Gen5 | XCVC2802 with AI Engines and VDE disabled, not yet in production |
XCVM2302 | Versal Prime | 89984 | 719872 | 1405 | 453 | 1904 | 3 | 9 | 2 | 30 | 8 GTYP + 40 GTM | 2 Gen5 | 6 MRMAC | - | - | - | - | software-limitted version of XCVP1402, not yet in production |
XCVM2502 | Versal Prime | 112528 | 900224 | 1341 | 677 | 3984 | 4 | 12 | - | 28 | 16 GTYP | 2 Gen5 | 2 MRMAC | - | - | - | CPM Gen5 | software-limitted version of XCVP1202, not yet in production |
XCVM2902 | Versal Prime | 127616 | 1020928 | 1981 | 645 | 2672 | 3 | 9 | 2 | 42 | 8 GTYP + 40 GTM | 2 Gen5 | 6 MRMAC | - | - | - | - | software-limitted version of XCVP1402, not yet in production |
XCVP1002 | Versal Premium | 47600* | 380800* | 535* | 345* | 1140* | 2 | 7 | - | 16* | 20 GTY + 24 GTM | 1 Gen4 | 3 MRMAC + 2 DCMAC | 1 | 1 | - | CPM Gen4 | software-limitted version of XCVP1052, not yet in production |
XCVP1052 | Versal Premium | 67760 | 542080 | 751 | 489 | 1572 | 2 | 7 | - | 22 | 20 GTY + 48 GTM | 1 Gen4 | 5 MRMAC + 3 DCMAC | 2 | 1 | - | CPM Gen4 | not yet in production |
XCVP1102 | Versal Premium | 89984 | 719872 | 1405 | 453 | 1904 | 3 | 9 | 2 | 30 | 8 GTYP + 64 GTM | 2 Gen5 | 6 MRMAC + 4 DCMAC | 2 | 3 | - | - | software-limitted version of XCVP1402 |
XCVP1202 | Versal Premium | 112528 | 900224 | 1341 | 677 | 3984 | 4 | 13 | - | 28 | 28 GTYP + 20 GTM | 2 Gen5 | 2 MRMAC + 1 DCMAC | - | 1 | - | CPM Gen5 | |
XCVP1402 | Versal Premium | 127616 | 1020928 | 1981 | 645 | 2672 | 3 | 9 | 2 | 42 | 8 GTYP + 96 GTM | 2 Gen5 | 6 MRMAC + 8 DCMAC | 2 | 5 | - | - | |
XCVP1502 | Versal Premium | 215056 | 1720448 | 2541 | 1301 | 7440 | 4 | 13 | - | 52 | 28 GTYP + 60 GTM | 2 Gen5 | 4 MRMAC + 3 DCMAC | 1 | 2 | - | CPM Gen5 | multi-die device consisting of XCVP1202 + an extension die |
XCVP1552 | Versal Premium | 219248 | 1753984 | 2541 | 1301 | 7392 | 4 | 13 | - | 52 | 68 GTYP + 20 GTM | 8 Gen5 | 4 MRMAC + 1 DCMAC | - | 2 | - | CPM Gen5 | XCVH15x2 without HBM |
XCVP1702 | Versal Premium | 317584 | 2540672 | 3741 | 1925 | 10896 | 4 | 13 | - | 76 | 28 GTYP + 100 GTM | 2 Gen5 | 6 MRMAC + 5 DCMAC | 2 | 3 | - | CPM Gen5 | multi-die device consisting of XCVP1202 + 2× extension die (same as XCVP1502) |
XCVP1802 | Versal Premium | 420112 | 3360896 | 4941 | 2549 | 14352 | 4 | 13 | - | 100 | 28 GTYP + 140 GTM | 2 Gen5 | 8 MRMAC + 7 DCMAC | 3 | 4 | - | CPM Gen5 | multi-die device consisting of XCVP1202 + 3× extension die (same as XCVP1502) |
XCVP2502 | Versal Premium | 213584 | 1708672 | 2541 | 1301 | 7392 | 4 | 13 | - | 52 | 28 GTYP + 60 GTM | 2 Gen5 | 4 MRMAC + 3 DCMAC | 1 | 2 | 472 (59×8) | CPM Gen5 | multi-die device consisting of XCVP1202 + AI extension die |
XCVP2802 | Versal Premium | 418640 | 3349120 | 4941 | 2549 | 14304 | 4 | 13 | - | 100 | 28 GTYP + 140 GTM | 2 Gen5 | 8 MRMAC + 7 DCMAC | 3 | 4 | 472 (59×8) | CPM Gen5 | multi-die device consisting of XCVP1202 + 2× extension die (same as XCVP1502) + AI extension die (same as XCVP2502) |
XCVH1522 | Versal HBM | 219248 | 1753984 | 2541 | 1301 | 7392 | 4 | 13 | - | 52 | 68 GTYP + 20 GTM | 8 Gen5 | 4 MRMAC + 1 DCMAC | - | 2 | - | CPM Gen5, 8GB HBM | multi-die device consisting of XCVP1202 + HBM extension die + HBM memory stacks, not yet in production |
XCVH1542 | CPM Gen5, 16GB HBM | |||||||||||||||||
XCVH1582 | CPM Gen5, 32GB HBM | |||||||||||||||||
XCVH1742 | Versal HBM | 321776 | 2574208 | 3741 | 1925 | 10848 | 4 | 13 | - | 76 | 68 GTYP + 60 GTM | 2 Gen5 | 6 MRMAC + 3 DCMAC | 1 | 3 | - | CPM Gen5, 16GB HBM | multi-die device consisting of XCVP1202 + extension die (same as XCVP1502) + HBM extension die (same as XCVH15x2) + HBM memory stacks, not yet in production |
XCVH1782 | CPM Gen5, 32GB HBM |
In addition to standalone FPGA chips, Xilinx also offers the Alveo product line of ready-to-use FPGA-based accelerator boards, and the Kria product line of FPGA-based Systems-on-Module (SOMs). The FPGAs used on these boards reuse the same die as standalone chips, but are considered to be distinct products by the Vivado toolchain.
Product | Purpose | FPGA | Corresponding standalone FPGA | Board format | Peripherials on board |
---|---|---|---|---|---|
Alveo SN1000 SmartNIC [80] | Accelerated network interface controller | XCU26 | XCVU23P | PCI Express ×16 full height, half length, single slot |
|
Alveo U25N | XCU25 | XCZU19EG | PCI Express ×16 half height, half length, single slot | ||
Alveo U30 | Media accelerator card | 2×XCU30 | 2×XCZU7EV | PCI Express ×8 half height, half length, single slot |
|
Alveo U55C [81] | High performance compute card | XCU55C | XCVU47P | PCI Express ×16 full height, half length, single slot | |
Alveo U50 [82] | Data center accelerator card | XCU50 | XCVU35P | PCI Express ×16 half height, half length, single slot |
|
Alveo U200 [83] | XCU200 | XCVU9P | PCI Express ×16 full height, full or ¾ length, dual slot |
| |
Alveo U250 | XCU250 | XCVU13P | |||
Alveo U280 [84] | XCU280 | XCVU37P | |||
Alveo X3522 [85] | Low Latency Network Adapter | XCUX35 | XCVU23P | PCI Express ×8 half height, half length, single slot |
|
Alveo X3522PV | Adaptable Accelerator Card | ||||
Kria K26 | XCK26 | XCZU5EV | System on Module |
|
Family | Launch | Process | Logic cells | Block RAM | DSP slices | MGT | PCIe blocks | Mem Intf BW | IO pins | VCCINT | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
nm | Count (K) | TITO (ns) | TCKO (ns) | Total (Mb) | FMAX (MHz) | Count | Total GMAC/s | FMAX (MHz) | Type | Count | Gbps | Total Gbps | Type | Count | Type | Gbps | ||||
Artix-7 | 2010 | 28 nm | 16-215 | 0.94 | 0.4 | 0.9-13 | 509 | 45-740 | 929 | 628 | GTP | 0-16 | 6.6 | 211 | x4 Gen2 | 1 | DDR3 | 1066 | 106-500 | 1.00 |
Family | Launch | Process | Logic cells | Block RAM | UltraRAM | DSP slices | MGT | PCIe blocks | Mem Intf BW | IO pins | VCCINT | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
nm | Count (K) | TITO (ns) | TCKO (ns) | Total (Mb) | FMAX (MHz) | Total (Mb) | FMAX (MHz) | Count | Total GMAC/s | FMAX (MHz) | Type | Count | Gbps | Total Gbps | Type | Count | Type | Gbps | ||||
Kintex-7 | 2010 | 28 nm | 66-478 | 0.58 | 0.26 | 5-34 | 601 | 240-1920 | 2845 | 741 | GTX | 4-32 | 12.5 | 800 | x8 Gen2 | 1 | DDR3 | 1866 | 285-500 | 1.00 | ||
Kintex UltraScale | 2013 [87] | 20 nm | 318-1451 | 12.7-75.9 | 660 | 768-5520 | 8180 | 741 | GTH, GTY | 12-64 | 16.3 | 2086 | x8 Gen3 | 1-6 | DDR3 | 2400 | 312-832 | 0.95 | ||||
Kintex UltraScale+ | 2015 [88] | 16 nm | 356-1143 | 12.7-34.6 | 825 | 0-36 | 650 | 1368-3528 | 6287 | 891 | GTH, GTY | 16-76 | 32.75 | 3268 | x16 Gen3 | 0-5 | DDR4 | 2666 | 280-668 | 0.85 |
A field-programmable gate array (FPGA) is an integrated circuit designed to be configured by a customer or a designer after manufacturing – hence the term field-programmable. The FPGA configuration is generally specified using a hardware description language (HDL), similar to that used for an application-specific integrated circuit (ASIC). Circuit diagrams were previously used to specify the configuration, but this is increasingly rare due to the advent of electronic design automation tools.
Reconfigurable computing is a computer architecture combining some of the flexibility of software with the high performance of hardware by processing with very flexible high speed computing fabrics like field-programmable gate arrays (FPGAs). The principal difference when compared to using ordinary microprocessors is the ability to make substantial changes to the datapath itself in addition to the control flow. On the other hand, the main difference from custom hardware, i.e. application-specific integrated circuits (ASICs) is the possibility to adapt the hardware during runtime by "loading" a new circuit on the reconfigurable fabric.
Altera Corporation was a manufacturer of programmable logic devices (PLDs) headquartered in San Jose, California. It was founded in 1983 and acquired by Intel in 2015.
Xilinx, Inc. was an American technology and semiconductor company that primarily supplied programmable logic devices. The company was known for inventing the first commercially viable field-programmable gate array (FPGA) and creating the first fabless manufacturing model.
A complex programmable logic device (CPLD) is a programmable logic device with complexity between that of PALs and FPGAs, and architectural features of both. The main building block of the CPLD is a macrocell, which contains logic implementing disjunctive normal form expressions and more specialized logic operations.
The MicroBlaze is a soft microprocessor core designed for Xilinx field-programmable gate arrays (FPGA). As a soft-core processor, MicroBlaze is implemented entirely in the general-purpose memory and logic fabric of Xilinx FPGAs.
The PowerPC 400 family is a line of 32-bit embedded RISC processor cores based on the PowerPC or Power ISA instruction set architectures. The cores are designed to fit inside specialized applications ranging from system-on-a-chip (SoC) microcontrollers, network appliances, application-specific integrated circuits (ASICs) and field-programmable gate arrays (FPGAs) to set-top boxes, storage devices and supercomputers.
PicoBlaze is the designation of a series of three free soft processor cores from Xilinx for use in their FPGA and CPLD products. They are based on an 8-bit RISC architecture and can reach speeds up to 100 MIPS on the Virtex 4 FPGA's family. The processors have an 8-bit address and data port for access to a wide range of peripherals. The license of the cores allows their free use, albeit only on Xilinx devices, and they come with development tools. Third-party tools are available from Mediatronix and others. Also PacoBlaze, a behavioral and device independent implementation of the cores exists and is released under the BSD License. The PauloBlaze is an open source VHDL implementation under the Apache License.
Minimig is an open source re-implementation of an Amiga 500 using a field-programmable gate array (FPGA).
A multi-gigabit transceiver (MGT) is a SerDes capable of operating at serial bit rates above 1 Gigabit/second. MGTs are used increasingly for data communications because they can run over longer distances, use fewer wires, and thus have lower costs than parallel interfaces with equivalent data throughput.
QPACE is a massively parallel and scalable supercomputer designed for applications in lattice quantum chromodynamics.
Field-programmable gate array prototyping, also referred to as FPGA-based prototyping, ASIC prototyping or system-on-chip (SoC) prototyping, is the method to prototype system-on-chip and application-specific integrated circuit designs on FPGAs for hardware verification and early software development.
Computing with Memory refers to computing platforms where function response is stored in memory array, either one or two-dimensional, in the form of lookup tables (LUTs) and functions are evaluated by retrieving the values from the LUTs. These computing platforms can follow either a purely spatial computing model, as in field-programmable gate array (FPGA), or a temporal computing model, where a function is evaluated across multiple clock cycles. The latter approach aims at reducing the overhead of programmable interconnect in FPGA by folding interconnect resources inside a computing element. It uses dense two-dimensional memory arrays to store large multiple-input multiple-output LUTs. Computing with Memory differs from Computing in Memory or processor-in-memory (PIM) concepts, widely investigated in the context of integrating a processor and memory on the same chip to reduce memory latency and increase bandwidth. These architectures seek to reduce the distance the data travels between the processor and the memory. The Berkeley IRAM project is one notable contribution in the area of PIM architectures.
The NetFPGA project is an effort to develop open-source hardware and software for rapid prototyping of computer network devices. The project targeted academic researchers, industry users, and students. It was not the first platform of its kind in the networking community. NetFPGA used an FPGA-based approach to prototyping networking devices. This allows users to develop designs that are able to process packets at line-rate, a capability generally unafforded by software based approaches. NetFPGA focused on supporting developers that can share and build on each other's projects and IP building blocks.
Xilinx ISE is a discontinued software tool from Xilinx for synthesis and analysis of HDL designs, which primarily targets development of embedded firmware for Xilinx FPGA and CPLD integrated circuit (IC) product families. It was succeeded by Xilinx Vivado. Use of the last released edition from October 2013 continues for in-system programming of legacy hardware designs containing older FPGAs and CPLDs otherwise orphaned by the replacement design tool, Vivado Design Suite.
Virtex is the flagship family of FPGA products developed by Xilinx, a part of Advanced Micro Devices (AMD). Other current product lines include Kintex (mid-range) and Artix (low-cost), each including configurations and models optimized for different applications. In addition, Xilinx offers the Spartan low-cost series, which continues to be updated and is nearing production utilizing the same underlying architecture and process node as the larger 7-series devices.
Tabula was an American fabless semiconductor company based in Santa Clara, California. Founded in 2003 by Steve Teig, it raised $215 million in venture funding. The company designed and built three dimensional field programmable gate arrays and ranked third on the Wall Street Journal's annual "Next Big Thing" list in 2012.
SoundGrid is a networking and processing platform audio application made by Waves Audio and developed in cooperation with DiGiCo.
In computing, a logic block or configurable logic block (CLB) is a fundamental building block of field-programmable gate array (FPGA) technology. Logic blocks can be configured by the engineer to provide reconfigurable logic gates.
iCE is the brand name used for a family of low-power field-programmable gate arrays (FPGAs) produced by Lattice Semiconductor. Parts in the family are marketed with the "world's smallest FPGA" tagline, and are intended for use in portable and battery-powered devices, where they would be used to offload tasks from the device's main processor or system on chip. By doing so, the main processor and its peripherals can enter a low-power state or be powered off entirely, potentially increasing battery life.
{{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link){{cite web}}
: CS1 maint: url-status (link)