diff options
| author | Damien George <damien@micropython.org> | 2021-04-14 15:37:33 +1000 |
|---|---|---|
| committer | Damien George <damien@micropython.org> | 2021-05-06 12:17:10 +1000 |
| commit | 9e29217c73f36802de616c05bee9bf7f9090f722 (patch) | |
| tree | 93d886a253be4f66e3c6932099934134e52529c6 /tests/unix/ffi_float.py.exp | |
| parent | 8172c2e9c5d5eec9a6b0a3f6cc4a2383b3d96d26 (diff) | |
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>
Diffstat (limited to 'tests/unix/ffi_float.py.exp')
| -rw-r--r-- | tests/unix/ffi_float.py.exp | 20 |
1 files changed, 14 insertions, 6 deletions
diff --git a/tests/unix/ffi_float.py.exp b/tests/unix/ffi_float.py.exp index b9d7da2bd..3d9091431 100644 --- a/tests/unix/ffi_float.py.exp +++ b/tests/unix/ffi_float.py.exp @@ -1,8 +1,16 @@ 1.230000 1.230000 -1.772454 -1.000000 -1.000000 -0.886227 -6.000000 -6.000000 +tgamma 1.77245 +tgamma 1.00000 +tgamma 1.00000 +tgamma 0.88623 +tgamma 6.00000 +tgamma 6.00000 +powf 0.00000 +powf 1.00000 +powf 1.41421 +powf 81.00000 +pow 0.00000 +pow 1.00000 +pow 1.41421 +pow 81.00000 |