4 Commits

Author	SHA1	Message	Date
Damien George	9e29217c73	unix/modffi: Use a union for passing/returning FFI values. ... This fixes a bug where double arguments on a 32-bit architecture would not be passed correctly because they only had 4 bytes of storage (not 8). It also fixes a compiler warning/error in return_ffi_value on certian architectures: array subscript 'double[0]' is partly outside array bounds of 'ffi_arg[1]' {aka 'long unsigned int[1]'}. Fixes issue #7064. Signed-off-by: Damien George <damien@micropython.org>	2021-05-06 12:17:10 +10:00
Paul Sokolovsky	5cb524673e	tests/ffi_float: Split tgammaf() testcase to a separate test. ... Some libc's may implement tgammaf as a header macro using tgamma(), so don't assume it'll be in the library.	2015-08-29 17:24:29 +03:00
Damien George	6bbbb1ab41	unix/modffi: Support passing float/double args.	2015-04-28 19:40:34 +01:00
Damien George	17598d49e1	unix: Don't use -Wno-error=cpp or #warning; fix strict alias warning. ... For the sake of older versions of gcc (and other compilers), don't use the #warning CPP directive, nor the -Wno-error=cpp option. Also, fix a strict alias warning in modffi.c for older compilers, and add a test for ffi module. Addresses issue #847.	2014-09-06 17:46:52 +01:00