Lines Matching refs:AVX2

4 …inux-gnu -mcpu=core-avx2 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=AVX2
41 ; AVX2: Found an estimated cost of 1 for instruction:   %shl
52 ; AVX2: Found an estimated cost of 1 for instruction:   %shl
55 ; On AVX2 we are able to lower the following shift into a single
68 ; AVX2: Found an estimated cost of 1 for instruction:   %shl
72 ; vector multiply instructions.  With AVX (but not AVX2), the vector multiply
75 ; With AVX2, instruction vpmullw works with 256bit quantities and
92 ; AVX2: Found an estimated cost of 1 for instruction:   %shl
107 ; AVX2: Found an estimated cost of 1 for instruction:   %shl
110 ; On AVX2 we are able to lower the following shift into a single
123 ; AVX2: Found an estimated cost of 1 for instruction:   %shl
136 ; AVX2: Found an estimated cost of 2 for instruction:   %shl
149 ; AVX2: Found an estimated cost of 2 for instruction:   %shl
152 ; On AVX2 we are able to lower the following shift into a sequence of
165 ; AVX2: Found an estimated cost of 2 for instruction:   %shl