Lines Matching full:vectors

71   /// sub vectors of type \p T. Returns the sub-vectors in \p DecomposedVectors.
76   /// returns the transposed-vectors in \p TransposedVectors.
104   /// requires a wide-load instruction \p 'I', a group of interleaved-vectors
134   // Currently, lowering is supported for the following vectors:  in isSupported()
136   //    1. Store and load of 4-element vectors of 64 bits on AVX.  in isSupported()
137   //    2. Store of 16/32-element vectors of 8 bits on AVX.  in isSupported()
139   //    1. Load of 16/32-element vectors of 8 bits on AVX.  in isSupported()
241 // genShuffleBland - Creates shuffle according to two vectors.This function is
321   // Assuming we start from the following vectors:  in interleave8bitStride4VF8()
361   // Example: Assuming we start from the following vectors:  in interleave8bitStride4()
545   // Example: Assuming we start from the following vectors:  in deinterleave8bitStride3()
628   // Example: Assuming we start from the following vectors:  in interleave8bitStride3()
751     // Now replace the unoptimized-interleaved-vectors with the  in lowerIntoOptimizedSequence()
752     // transposed-interleaved vectors.  in lowerIntoOptimizedSequence()
764   //   vectors.  in lowerIntoOptimizedSequence()
769   //   2. Transpose the interleaved-vectors into vectors of contiguous  in lowerIntoOptimizedSequence()
792   //   3. Concatenate the contiguous-vectors back into a wide vector.  in lowerIntoOptimizedSequence()