Intel® Arria® 10 Device Family Variations

Variant Description
Arria® 10 GT FPGAs enabled with up to 78 full-duplex transceivers with data rates up to 25.78 Gbps chip-to-chip, 12.5 Gbps backplane and up to 1,150K equivalent logic elements (LEs)
Arria 10 GX FPGAs enabled with up to 96 full-duplex transceivers with data rates up to 17.4 Gbps chip-to-chip, 12.5 Gbps backplane, and up to 1,150K equivalent LEs
Arria 10 SX SoCs enabled with a dual-core ARM* Cortex*-A9 HPS, up to 48 full-duplex transceivers with data rates up to 17.4 Gbps chip-to-chip, 12.5 Gbps backplane, and up to 660K equivalent LEs

Intel® Arria® 10 Architecture

Highest Performance 20 nm FPGAs and SoCs

Intel® Arria® 10 FPGAs deliver more than a speed grade faster core performance and up to a 20% Fmax advantage compared to the competition, using publicly-available OpenCores designs. In addition, the Arria 10 family offers the programmable logic industry’s only 20 nm ARM-based SoCs, delivering clock speeds at up to 1.5 GHz. The Arria 10 family also delivers the first hardened support for floating point operations in an FPGA, enabling a new level of DSP performance.

High-Bandwidth, Low-Latency Transceivers

Arria 10 FPGA and SoC serial transceivers offer high bandwidth, low latency, and the lowest power to help you build high-speed communication systems. Whether getting data across a board, distributing data to server blades across a backplane, moving data to the next chassis in a data center, or transporting data across the world through a sophisticated optical transport network, the Arria 10 FPGA and SoC transceivers provide a wide range of capabilities to support an extensive set of protocols and deliver reliable bandwidth at low cost.  

Arria 10 SoCs: When Architecture Matters

SoCs integrate an ARM-based hard processor system (HPS) consisting of processor, peripherals, and memory interfaces with the FPGA fabric using a high-bandwidth interconnect backbone. It combines the performance and power savings of hard intellectual property (IP) with the flexibility of programmable logic. The Arria 10 SoCs, based on TSMC’s 20 nm process technology, combine a dual-core ARM Cortex-A9 MPCore* HPS with industry-leading programmable logic technology that includes hardened floating-point digital signal processing (DSP) blocks.  

Learn More about Arria 10 SoCs >>

Hardened Floating-Point DSP Blocks

In Arria 10 devices, Intel has enhanced the variable-precision DSP block by including hardened floating-point operators. The Arria 10 FPGA and SoC variable-precision DSP block introduces a new floating-point mode that delivers breakthrough floating-point performance of up to 1.5 TeraFLOPs.

The following table provides an overview of the Arria 10 GX/GT product variants. For the Arria 10 SX product variants, please go to the Arria 10 SoC Overview. Please note that all product information provided is preliminary and subject to change.

Part # Reference 10AX016 10AX022 10AX027 10AX032 10AX048 10AX057 10AX066 10AX090 10AX115 10AT090 10AT115
Arria 10 Product Line GX 160 GX 220 GX 270 GX 320 GX 480 GX 570 GX 660 GX 900 GX 1150 GT 900 GT 1150
Equivalent
LEs (K)
160 220 270 320 480 570 660 900 1,150 900 1,150
System LEs (K) 210 288 354 419 629 747 865 1,180 1,506 1,180 1,506
Adaptive logic
modules
(ALMs)
61,510 83,730 101,620 118,730 181,790 217,080 250,540 339,620 427,200 339,620 427,200
Registers 246,040 334,920 406,480 474,920 727,160 868,320 1,002,160 1,358,480 1,708,800 1,358,480 1,080,800

Maximum
transceiver
count

12 12 24 24 36 48 48 96 96 78 78
M20K memory
blocks
440 588 750 891 1,438 1,800 2,133 2,423 2,713 2,423 2,713
M20K memory
(Mb)
9 11 15 17 28 35 42 47 53 47 53
MLAB memory
(Mb)
1.0 1.8 2.4 2.8 4.3 5.0 5.7 9.2 12.7 9.2 12.7

Variable-precision

digital signal processing

(DSP) blocks

156 191 830 985 1,368 1,523 1,688 1,518 1,518 1,518 1,518
18x19
multipliers
312 382 1,660 1,970 2,736 3,046 3,376 3,036 3,036 3,036 3,036
Peak GMACS 343 420 1,826 2,167 3,010 3,351 3,714 3,340 3,340 3,340 3,340

Single-precision

floating-point

multipliers

156 191 830 985 1,368 1,523 1,688 1,518 1,518 1,518 1,518

Single-precision

floating-point

adders

156 191 830 985 1,368 1,523 1,688 1,518 1,518 1,518 1,518

Peak giga

floating-point operation

per second (GFLOPs)

140 172 747 887 1,231 1,371 1,519 1,366 1,366 1,366 1,366
PCI Express* 
(PCIe*) hardened intellectual
property (IP)
block(s) (up to Gen3)
1 1 2 2 2 2 2 4 4 4 4
Part # Reference 10AX016 10AX022 10AX027 10AX032 10AX048 10AX057 10AX066 10AX090 10AX115 10AT090 10AT115
Arria 10 Product Line GX 160 GX 220 GX 270 GX 320 GX 480 GX 570 GX 660 GX 900 GX 1150 GT 900 GT 1150
U19 (U484)
19 mm
192,48,
72,6
192,48,
72,6
- - - - - - - - -
F27 (F672)
27 mm
240,48,
96,12
240,48,
96,12
240,48,
96,12
240,48,
96,12
- - - - - - -
F29 (F780)
29 mm
288,48,
120,12
288,48,
120,12
360,48,
156,12
360,48,
156,12
360,48,
156,12
- - - - - -
F34 (F1152)
35 mm
- - 384,48,
168,24
384,48,
168,24
492,48,
222,24
492,48,
222,24
492,48,
222,24
504,0,
225,24
504,0,
252,24
- -
F35 (F1152)
35 mm
- - 384,48,
168,24
384,48,
168,24
396,48,
174,36
396,48,
174,36
396,48,
174,36
- - - -
KF40 (F1517)
40 mm
- - - - -

696, 48, 324, 36

696, 48, 324, 36

- - - -
NF40 (F1517)
40 mm
- - - - - 588,48,
270,48
588,48,
270,48
600,0,
300,48
600,0,
300,48
- -
RF40 (F1517)
40 mm
- - - - - - - 342,0,
154,66
342,0,
154,66
- -
NF45 (F1932)
45 mm
- - - - - - - 768,0,
384,48
768,0,
384,48
- -
SF45 (F1932)
45 mm
- - - - - - - 624,0,
312,72
624,0,
312,72
624,0,
312,72
624,0,
312,72

UF45 (F1932)
45 mm

- - - - - - - 480,0,
240,96
480,0,
240,96
- -
Notes:
  1. All packages are ball grid arrays with 1.0 mm pitch, except for U19 (U484), which is 0.8 mm pitch.
  2. High-voltage I/O pins are used for 3.3 V and 2.5 V interfacing.
  3. Each LVDS pair can be configured as either a differential input or a differential output.
  4. High-voltage I/O pins and LVDS pairs are included in the General Purpose I/O count. Transceivers are counted separately.

Please refer to the Product Catalog for the Arria FPGA family package plans with vertical migration support and ordering code information.

Related Links

 

Tests measure performance of components on a particular test, in specific systems. Differences in hardware, software, or configuration will affect actual performance. Consult other sources of information to evaluate performance as you consider your purchase.  For more complete information about performance and benchmark results, visit www.intel.com/benchmarks. Performance comparison methodology and detailed results documented in the Arria 10 Performance Benchmarking Methodology and Results white paper at www.altera.com/arriaperformance.