Intel Phi 7120P SC7120P Manuel D’Utilisation
Codes de produits
SC7120P
better Performance,
More Flexibility
More Flexibility
Table 1. Intel® Xeon Phi™ Coprocessor Family Overview
FEATURES
DETAIlS
BENEFITS
Intel® Many Integrated Cores
(MIC) architecture
(MIC) architecture
• Up to 61 cores, 244 threads, and 16 GB of GDDR5 memory
(352 GB/s bandwidth) per coprocessor
• Double-wide (256-bit) vector engines and 512-bit
SIMD instructions
• Ideal for highly-parallel, vector-intensive, and memory-
bound code
Up to 1.2 teraflops of
double-precision performance
per coprocessor
double-precision performance
per coprocessor
1
Familiar Intel® architecture
programming model
programming model
Developers can:
• Use familiar methods and tools, including the latest Intel® Software
• Use familiar methods and tools, including the latest Intel® Software
Development products
• Maintain a common code base for Intel® Xeon® processors and Intel®
Xeon Phi™ coprocessors
Simplified development
and dual-benefit for
performance optimization
and dual-benefit for
performance optimization
Linux* hosting capability
Run each coprocessor under the host operating system or as an
independent server running Red Hat Enterprise Linux* 6.x or SuSE
Linux* 12+
independent server running Red Hat Enterprise Linux* 6.x or SuSE
Linux* 12+
Exceptional execution flexibility
IP Addressable
Supports standard clustering models.
Simple scaling
Industry-leading silicon technology
• Intel 22 nm technology with 3D Tri-Gate transistors
• Power envelopes as low as 225 Watts per coprocessor
• Power envelopes as low as 225 Watts per coprocessor
Exceptional compute density
and energy efficiency
and energy efficiency
Flexible form factors
• Standard x16 PCIe* cards (with active, passive, or no thermal solution)
and a unique dense form factor (DFF) for more customized integration
• Use up to 8 coprocessors per host server
Flexible integration and
scalability
scalability
Flexible Execution Models
• Multicore only – MAIN() runs on host processor
• Multicore Hosted with Manycore Offload – MAIN() runs on host
• Multicore Hosted with Manycore Offload – MAIN() runs on host
processor and select routines are executed on the coprocessor
• Symmetric execution – MAIN() runs symmetrically on processor
and coprocessor
• Manycore only – Boot from host processor, MAIN() runs
on coprocessor
Best flexibility for optimizing
workload performance
workload performance
Table 2. Intel® Xeon Phi™ Product Family Specifications
PRODUCT
NUMBER
FORM
FACTOR &,
THERMAl
SOlUTION
4
BOARD
TDP (WATTS)
NUMBER
OF CORES
FREqUENCY
(GHz)
PEAk DOUBlE
PRECISION
PERFORMANCE
(GFlOP)
PEAk
MEMORY
BANDWIDTH
(GB/s)
MEMORY
CAPACITY
(GB)
INTEl®
TURBO
BOOST
TECHNOlOGY
3120P
PCIe, Passive 300
57
1.1
1003
240
6
N/A
3120A
PCIe, Active
300
57
1.1
1003
240
6
N/A
5110P
PCIe, Passive 225
60
1.053
1011
320
8
N/A
5120D
Dense form
factor, None
245
60
1.053
1011
352
8
N/A
7110P
PCIe, Passive 300
61
1.238
1208
352
16
Peak turbo
frequency:
1.33 GHz
7120X
PCIe, None
300
61
1.238
1208
352
16
3