Optimized scalar promotion with load and splat SIMD instructions

A computer program product comprising a non-transitory computer readable medium having a computer readable program recorded thereon, wherein the computer readable program, when executed on a computing device, causes the computing device to:

• determine placement of vector operation-splat operations based on an identification of scalar and single instruction multiple data (SIMD) operations in an original code representation, wherein each vector operation-splat operation is a single operation that performs a combination of a vector operation and a splat operation without performing a separate vector operation and separate splat operation;
• modify the original code representation to include the vector operation-splat operations based on the determined placement of vector operation-splat operations to generate a first modified code representation;
• determine placement of separate splat operations based on identification of scalar and SIMD operations in the first modified code representation;
• modify the first modified code representation to insert or delete separate splat operations based on the determined placement of the separate splat operations to generate a second modified code representation;
• and
• output SIMD code based on the second modified code representation for execution by the SIMD engine.

An apparatus, comprising:

• a processor;
• and
• a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to:
• determine placement of vector operation-splat operations based on an identification of scalar and single instruction multiple data (SIMD) operations in an original code representation, wherein each vector operation-splat operation is a single operation that performs a combination of a vector operation and a splat operation without performing a separate vector operation and separate splat operation;
• modify the original code representation to include the vector operation-splat operations based on the determined placement of vector operation-splat operations to generate a first modified code representation;
• determine placement of separate splat operations based on identification of scalar and SIMD operations in the first modified code representation;
• modify the first modified code representation to insert or delete separate splat operations based on the determined placement of the separate splat operations to generate a second modified code representation;
• and
• output SIMD code based on the second modified code representation for execution by the SIMD engine.