Method for performing intra-simd data movement for lane-wise operated single instruction, multiple data (simd) coprocessors

A method performable by a processing system comprising a first single instruction multiple data (SIMD) coprocessor and a second single instruction multiple data (SIMD) coprocessor, the method comprising:

• moving, by the first SIMD coprocessor, data from a first SIMD lane of a lane-wise SIMD register of the first SIMD coprocessor to a first segment of a memory;
• retrieving, by the second SIMD coprocessor, the data from the first segment of the memory and storing the data in a first SIMD lane of a SIMD register of the second SIMD coprocessor that supports intra-SIMD data movement;
• executing, by the second SIMD coprocessor, one or more instructions to move the data from the first SIMD lane of the SIMD register of the second SIMD coprocessor to a second SIMD lane of the SIMD register of the second SIMD coprocessor;
• loading, by the second SIMD coprocessor, the data stored in the second SIMD lane of the SIMD register of the second SIMD coprocessor onto a second segment of the memory;
• and
• retrieving, by the first SIMD coprocessor, the data stored on the second segment of the memory and storing the data on a second SIMD lane of the lane-wise SIMD register of the first SIMD coprocessor.

An apparatus, comprising

• a first single instruction multiple data (SIMD) coprocessor including a first plurality of SIMD registers, each of the first plurality of SIMD registers including a first plurality of SIMD lanes, the first SIMD coprocessor configured to:
• move data from a SIMD register of the plurality of SIMD registers to a memory independent of a cross-lane operation occurring between the first plurality of SIMD lanes of the SIMD register;
• a second SIMD coprocessor including a second plurality of SIMD registers, each of the second plurality of SIMD registers including a second plurality of SIMD lanes, the second SIMD coprocessor configured to:
• move the data from the memory to a SIMD register of the second plurality of SIMD registers;
• perform movement operations on the data that involve cross-lane operations between the second plurality of SIMD lanes of the SIMD register.