diff options
author | Ray Molenkamp <github@lazydodo.com> | 2020-02-18 16:42:35 +0300 |
---|---|---|
committer | Ray Molenkamp <github@lazydodo.com> | 2020-02-18 16:42:35 +0300 |
commit | 003a97e0bf509c7eb8b1ae6bdc3f26976d514ab2 (patch) | |
tree | db0a0ec6950e4241fa9f3dcbf3dfd7b53e54c9e5 /intern | |
parent | ad9b91996209f76bb3658afeba426ecd3e8243e7 (diff) |
Cycles: Fix failing avxf cross test on AVX2
cycles_util_avxf_avx2_test failed on the cross test, since
it wasn't immediately clear why, the test was disabled.
After looking into it, this test when build for AVX2 is
generating FMA instructions where the intermediate results
have "infinite" precision [1] leading to slightly different
results.
This diff re-enables the cross test and allows for a small error
in the results.
[1] https://www.felixcloutier.com/x86/vfmadd132ps:vfmadd213ps:vfmadd231ps
Differential Revision: https://developer.blender.org/D6873
Reviewers: brecht
Diffstat (limited to 'intern')
-rw-r--r-- | intern/cycles/test/util_avxf_test.h | 30 |
1 files changed, 16 insertions, 14 deletions
diff --git a/intern/cycles/test/util_avxf_test.h b/intern/cycles/test/util_avxf_test.h index 1dd677e35e6..353c8fa9b28 100644 --- a/intern/cycles/test/util_avxf_test.h +++ b/intern/cycles/test/util_avxf_test.h @@ -44,6 +44,10 @@ bool validate_cpu_capabilities() for (size_t index = 0; index < a.size; index++) \ EXPECT_FLOAT_EQ(a[index], b[index]); +#define compare_vector_vector_near(a, b, abserror) \ + for (size_t index = 0; index < a.size; index++) \ + EXPECT_NEAR(a[index], b[index], abserror); + #define basic_test_vv(a, b, op) \ VALIDATECPU \ avxf c = a op b; \ @@ -190,23 +194,21 @@ TEST(util_avx, avxf_shuffle) compare_vector_vector(res, avxf(0.4f, 0.2f, 0.1f, 0.3f, 0.5f, 0.6f, 0.7f, 0.8f)); } -/* XXX Test Fails on AVX2, needs further investigation before it can be enabled */ -#if 0 TEST(util_avx, avxf_cross) { - VALIDATECPU - avxf res = cross(avxf_b, avxf_c); - compare_vector_vector(res, - avxf(0.0f, - -9.5367432e-07f, - 0.0f, - 4.7683716e-07f, - 0.0f, - -3.8146973e-06f, - 3.8146973e-06f, - 3.8146973e-06f)); + VALIDATECPU + avxf res = cross(avxf_b, avxf_c); + compare_vector_vector_near(res, + avxf(0.0f, + -9.5367432e-07f, + 0.0f, + 4.7683716e-07f, + 0.0f, + -3.8146973e-06f, + 3.8146973e-06f, + 3.8146973e-06f), + 0.000002000f); } -#endif TEST(util_avx, avxf_dot3) { |