VPERMIL2PS ymm1, ymm2, ymm3, ymm4/m256, imz2

VPERMIL2PS (VEX.256 encoded version)
DEST[31:0]  sel_and_condzerosp(SRC1[127:0], SRC2[127:0], SRC3[3:0])
DEST[63:32]  sel_and_condzerosp(SRC1[127:0], SRC2[127:0], SRC3[35:32])
DEST[95:64]  sel_and_condzerosp(SRC1[127:0], SRC2[127:0], SRC3[67:64])
DEST[127:96]  sel_and_condzerosp(SRC1[127:0], SRC2[127:0], SRC3[99:96])
DEST[159:128]  sel_and_condzerosp(SRC1[255:128], SRC2[255:128], SRC3[131:128])
DEST[191:160]  sel_and_condzerosp(SRC1[255:128], SRC2[255:128], SRC3[163:160])
DEST[223:192]  sel_and_condzerosp(SRC1[255:128], SRC2[255:128], SRC3[195:192])
DEST[255:224]  sel_and_condzerosp(SRC1[255:128], SRC2[255:128], SRC3[227:224])

VPERMIL2PS __m128 _mm_permute2_ps (__m128 a, __m128 b, __m128i ctrl, int imm)
VPERMIL2PS __m256 _mm256_permute2_ps (__m256 a, __m256 b, __m256i ctrl, int imm)

VPERMILPS (256-bit immediate version)
DEST[31:0]  Select4(SRC1[127:0], imm8[1:0]);
DEST[63:32]  Select4(SRC1[127:0], imm8[3:2]);
DEST[95:64]  Select4(SRC1[127:0], imm8[5:4]);
DEST[127:96]  Select4(SRC1[127:0], imm8[7:6]);
DEST[159:128]  Select4(SRC1[255:128], imm8[1:0]);
DEST[191:160]  Select4(SRC1[255:128], imm8[3:2]);
DEST[223:192]  Select4(SRC1[255:128], imm8[5:4]);
DEST[255:224]  Select4(SRC1[255:128], imm8[7:6]);