The new floating point co-processor from
BittWare for FPGAs
BittWare has announced the Anemone floating point co-processor
chip for use with Altera's high performance FPGAs. OEM'd
from Adapteva's new Epiphany architecture targets signal
processing applications. Each Anemone features 16 processors,
providing 32 GFLOPS of floating point processing while consuming
2 Watts of total chip power. Multiple Anemones can be gluelessly
connected to scale up to create compute blocks of up to
4096 processors providing 8 TFLOPs of floating point performance.
Availability will be via the soon to be announced Anemone
product family of COTS boards which combine this new technology
with Altera's high-density Stratix family of FPGAs in form
factors such as FMC (VITA 57), AdvancedMC (AMC), VPX (VITA
46/48/65), and PCI Express (PCIe) slot card.
"It seems like our industry has not demonstrated much
creativity in the past few years, and processing improvements
have only come at the expense of increasingly ridiculous
power consumption, which has in turn created burdensome
cooling problems," stated Jeff Milrod, BittWare President
& CEO. "We believe that Adapteva's Epiphany architecture
represents a flash of brilliance that reintroduces some
much needed creativity into the embedded signal processing
world. The resulting Anemone chip, combined with Altera's
family of FPGAs, creates an insanely cool solution for complex
signal processing tasks that can be optimized for power,
performance, and productivity."
"This joint C and RTL solution of Anemone plus Altera
FPGAs provides users with the unique ability to partition
algorithms into hardware or software, enabling them to design
a thoroughly optimized system solution with superior development
productivity and unmatched system size, weight, and power,"
said David Gamba, director of Altera's military business
unit. "BittWare is once again providing our COTS customers
with an incredibly powerful solution for their signal processing
applications."
Anemone was architected specifically for complex signal
processing rather than for I/O, protocol processing, memory
interfacing, or special functions. Each eCore processor
features a compact, general-purpose instruction to ensure
program efficiency. All floating point computations are
performed as single-precision IEEE 754; hardware looping
is also supported. Anemone offers distributed and segmented
memory, and large uniform register files. On-chip distributed
shared memory is 4 Mb (32 KByte per eCore) with 32 GBytes/sec
of sustained memory bandwidth within each eCore. The cache-less
shared memory architecture is extended off-chip, and between
chips, via external I/O links.
The Anemone features an internal high-throughput mesh network,
with separate data paths for on-chip and off-chip communications.
Each eCore processor has a multi-channel DMA engine to support
background data movement over the 'eMesh'. Total on-chip,
inter-core bandwidth is 128 GBytes/sec full duplex, with
an additional 8 GBytes/sec of off-chip bandwidth. Each router
node can simultaneously sustain full-duplex transfers on
all ports, with automatic routing based on global addressing.
The Anemone provides a flexible low-overhead external interconnect
scheme that supports memory-mapped direct connection of
multiple Anemones and is compatible with any LVDS capable
FPGA. This is achieved via 4 Links that are full-duplex
8-bit LVDS data ports @ 500 MHz DDR, each simultaneously
providing 1 GByte/sec in each direction for a total off-chip
bandwidth of 8 GBytes/sec. Its FPGA co-processor use model
provides the ultimate flexibility: since all external I/O
goes through an FPGA, system designers can customize the
I/O to their application's specific requirements.
The Anemone supports execution of applications written
in regular ANSI-C langauge and does not require any C-subset,
language extensions, or SIMD. Standard GNU development tools
are supported including an optimizing C complier, simulator,
GDB debugger, and Eclipse multi-core IDE.
Availability
The Anemone will be available from BittWare on standard
COTS boards, including FMC (VITA 57), AdvancedMC (AMC),
VPX (VITA 46/48/65), and PCI Express (PCIe) slot cards starting
in Q3. Development boards, software and systems will also
be available.