Add SSE4-16 target.

Along the lines of sse4-8, this is an 8-wide target for SSE4, using
16-bit elements for the mask.  It's thus (in principle) the best
target for SIMD computation with 16-bit datatypes.
This commit is contained in:
Matt Pharr
2013-07-24 09:40:50 -07:00
parent 04d61afa23
commit 780b0dfe47
5 changed files with 463 additions and 7 deletions

View File

@@ -37,7 +37,7 @@ parser.add_option("-g", "--generics-include", dest="include_file", help="Filenam
parser.add_option("-f", "--ispc-flags", dest="ispc_flags", help="Additional flags for ispc (-g, -O1, ...)",
default="")
parser.add_option('-t', '--target', dest='target',
help='Set compilation target (neon, sse2, sse2-x2, sse4, sse4-x2, sse4-8, avx, avx-x2, generic-4, generic-8, generic-16, generic-32)',
help='Set compilation target (neon, sse2, sse2-x2, sse4, sse4-x2, sse4-8, sse4-16, avx, avx-x2, generic-4, generic-8, generic-16, generic-32)',
default="sse4")
parser.add_option('-a', '--arch', dest='arch',
help='Set architecture (arm, x86, x86-64)',