Intel® ISA Extensions
Use hardware-based isolation and memory encryption to provide more code protection in your solutions.
Announcements
FPGA community forums and blogs on community.intel.com are migrating to the new Altera Community and are read-only. For urgent support needs during this transition, please visit the FPGA Design Resources page or contact an Altera Authorized Distributor.
1135 Discussions

AVX512F round intrinsics not work

User1573649127519766
Beginner
‎11-17-2019 06:12 PM
603 Views

I use the _mm512_div_round_pd intrinsic, the input parameters are (0.0030214, 12458.125, 0.12, 54.4445785, 1.0, 31.125, 10.254, -57.147) and (-0.0030214, 15.11, 0.000001, 78.223245, 2, 31.25, 6.58, -4487.12). output = _mm512_div_round_pd(a, b, _MM_FROUND_TO_NEAREST_INT |_MM_FROUND_NO_EXC);

I have checked the assembly instruction, the instruction is vdivpd {rn - sae}. However, the output is not a rounding result, it's just the same as _mm512_div_pd. I have tryed _MM_FROUND_TO_NEG_INF and other parameters, but the answer is same. The question also appears in _mm512_add_round_pd function.

​

ps. OS is CentOs Linux release 7.6.1810, CPU model name is Intel(R) Xeon(R) Gold 6130 CPU @ 2.10GHz

0 Kudos

Link Copied

0 Replies
Reply

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.