StreamHPC
https://streamhpc.com/knowledge/sdks/texas-instruments-dsp/
Export date: Tue Jun 18 7:16:25 2019 / +0000 GMT

Texas Instruments DSP




Texas-Instruments-logo-designTI has a fully conformant OpenCL 1.1 implementation.

The below table is taken from http://downloads.ti.com/mctools/esd/docs/opencl/intro.html 1 and shows which DSPs have OpenCL-support.





















































SoC System Khronos Conformance Installation Instructions
AM572 AM572 EVM OpenCL v1.1 Conformant Processor SDK for AM57x
DRA75x DRA75x EVM OpenCL v1.1 Conformant Processor SDK for DRA7x (Enabling OpenCL on DRA75x)
AM571 AM572 EVM OpenCL v1.1 Conformant Processor SDK for AM57x
66AK2H 66AK2H EVM OpenCL v1.1 Conformant Processor SDK for K2H
66AK2L 66AK2L EVM Not submitted for conformance Processor SDK for K2L
66AK2E 66AK2E EVM Not submitted for conformance Processor SDK for K2E
66AK2G 66AK2G EVM Not submitted for conformance Processor SDK for K2G

Theoretical Performance of the C66x



  • Fixed point 16x16 MACs per cycle: 32

  • Fixed point 32x32 MACs per cycle: 8

  • Floating point single precision MACs per cycle: 8

  • Arithmetic floating point operations per cycle: 16 2-way SIMD on .L and .S units (e.g. 8 SP operations for A and B) and 4 SP multiply on one .M unit (e.g 8 SP operations for A and B)

  • Arithmetic floating point operations per cycle: 164 2-way SIMD on .L and .S units (e.g. 8 SP operations for A and B) and 4 SP multiply on one .M unit (e.g 8 SP operations for A and B)

  • Load/store width 2 x 64-bit 2 x 64-bit Vector size (SIMD capability): 128-bit (4 x 32-bit, 4 x 16-bit, 4x-8bits)


GFLOPs


2 FLOPs - 2-way SIMD on .L1 (A side) such as DADDSP or DSUBSP
2 FLOPs - 2-way SIMD on .L2 (B side) such as DADDSP or DSUBSP
2 FLOPs - 2-way SIMD on .S1 (A side) such as DADDSP or DSUBSP
2 FLOPs - 2-way SIMD on .S2 (B side) such as DADDSP or DSUBSP
4 FLOPs - 4-way SIMD on .M1 (A side) such as QMPYSP (or CMPYSP, maybe not 4-way SIMD)
4 FLOPs - 4-way SIMD on .M2 (B side) such as QMPYSP (or CMPYSP, maybe not 4-way SIMD)
========================
16 FLOPs total per cycle per C66x CorePac (source 2)

Boards


A good starter board is the BeagleBoard X-15 3, and has OpenCL drivers 4. It has 2x C66X DSPs and 2x 1.5-GHz ARM Cortex-A15.

X15_TOP_SIDE
Links:
  1. http://downloads.ti.com/mctools/esd/docs/opencl/in tro.html
  2. https://e2e.ti.com/support/dsp/c6000_multi-core_ds ps/f/639/t/145286
  3. http://beagleboard.org/x15
  4. http://www.elinux.org/Beagleboard:BeagleBoard-X15# Will_I_be_able_to_program_the_C66x_DSPs.3F
Post date: 2015-09-25 10:30:39
Post date GMT: 2015-09-25 08:30:39

Post modified date: 2017-05-29 12:39:26
Post modified date GMT: 2017-05-29 10:39:26

Export date: Tue Jun 18 7:16:25 2019 / +0000 GMT
This page was exported from StreamHPC [ https://streamhpc.com ]
Export of Post and Page has been powered by [ Universal Post Manager ] plugin from www.ProfProjects.com