| Commit message (Expand) | Author | Age |
* | Revert addition of unused `paddsub<Packet2cf>`. This fixes #2242 | Christoph Hertzberg | 2021-05-06 |
* | Better CUDA complex division. | Antonio Sanchez | 2021-04-29 |
* | Add missing pcmp_lt_or_nan for NEON Packet4bf. | Antonio Sanchez | 2021-04-27 |
* | Tests added and AVX512 bug fixed for pcmp_lt_or_nan | Jakub Lichman | 2021-04-25 |
* | Fix taking address of rvalue compiler issue with TensorFlow (plus other warni... | Chip-Kerchner | 2021-04-21 |
* | HasExp added for AVX512 Packet8d | Jakub Lichman | 2021-04-20 |
* | Fix ldexp for AVX512 (#2215) | Antonio Sanchez | 2021-04-20 |
* | Avoid using uninitialized inputs and if available, use slightly more efficien... | Christoph Hertzberg | 2021-04-13 |
* | Fix address of temporary object errors in clang11. | Chip Kerchner | 2021-04-02 |
* | Eliminate `round_impl` double-promotion warnings for c++03. | Antonio Sanchez | 2021-03-25 |
* | Fixed performance issues for complex VSX and P10 MMA in gebp_kernel (level 3). | Chip Kerchner | 2021-03-25 |
* | Revert "Uses _mm512_abs_pd for Packet8d pabs" | Christoph Hertzberg | 2021-03-23 |
* | Remove yet another comma at end of enum | David Tellenbach | 2021-03-18 |
* | Uses _mm512_abs_pd for Packet8d pabs | Steve Bronder | 2021-03-18 |
* | Augment NumTraits with min/max_exponent() again. | Antonio Sanchez | 2021-03-16 |
* | Fix another warning on missing commas | David Tellenbach | 2021-03-17 |
* | Revert "Augment NumTraits with min/max_exponent()." | David Tellenbach | 2021-03-17 |
* | Augment NumTraits with min/max_exponent(). | Antonio Sanchez | 2021-03-17 |
* | Silence warning on comma at end of enumerator list | David Tellenbach | 2021-03-17 |
* | Add fmod(half, half). | Antonio Sanchez | 2021-03-15 |
* | Fix pround and add print | Chip Kerchner | 2021-03-15 |
* | Fix NVCC+ICC issues. | Antonio Sanchez | 2021-03-15 |
* | Add increment/decrement operators to Eigen::half. | Antonio Sanchez | 2021-03-15 |
* | Fix ambiguous call to CUDA __half constructor. | Antonio Sanchez | 2021-03-08 |
* | Fix typo: DEVICE -> GPU | Antonio Sanchez | 2021-03-08 |
* | Fix non-trivial Half constructor for CUDA. | Antonio Sanchez | 2021-03-08 |
* | Changing the Eigen::half implementation for HIP | Deven Desai | 2021-03-05 |
* | Fix rint SSE/NEON again, using optimization barrier. | Antonio Sanchez | 2021-03-05 |
* | Revert "Fix rint for SSE/NEON." | Antonio Sánchez | 2021-03-03 |
* | Fix rint for SSE/NEON. | Antonio Sanchez | 2021-03-03 |
* | Add print for SSE/NEON, use NEON rounding intrinsics if available. | Antonio Sanchez | 2021-02-27 |
* | Make half/bfloat16 constructor take inputs by value, fix powerpc test. | Antonio Sanchez | 2021-02-27 |
* | Fix double-promotion warnings | Christoph Hertzberg | 2021-02-27 |
* | Fix NEON sqrt for 32-bit, add prsqrt. | Antonio Sanchez | 2021-02-26 |
* | Fix floor/ceil for NEON fp16. | Antonio Sanchez | 2021-02-25 |
* | Fix SSE/NEON pfloor/pceil for saturated values. | Antonio Sanchez | 2021-02-25 |
* | Fix clang compile when no MMA flags are set. Simplify MMA compiler detection. | Chip-Kerchner | 2021-02-24 |
* | Having forward template function declarations in a P10 file causes bad code i... | Chip-Kerchner | 2021-02-24 |
* | Fixes to support old and new versions of the compilers for built-ins. Cast t... | Chip-Kerchner | 2021-02-24 |
* | Disable fast psqrt for NEON. | Antonio Sanchez | 2021-02-23 |
* | Fix some CUDA warnings. | Antonio Sanchez | 2021-02-24 |
* | Accurate pow, part 2. This change adds specializations of log2 and exp2 for d... | Rasmus Munk Larsen | 2021-02-23 |
* | Fix compilation errors with later versions of GCC and use of MMA. | Chip-Kerchner | 2021-02-22 |
* | Fixes Bug #1925. Packets should be passed by const reference, even to inline ... | Christoph Hertzberg | 2021-02-20 |
* | Use the Cephes double subtraction trick in pexp<float> even when FMA is avail... | Rasmus Munk Larsen | 2021-02-18 |
* | Fix uninitialized warning on AVX. | Antonio Sanchez | 2021-02-17 |
* | Fixed performance issues for VSX and P10 MMA in general_matrix_matrix_product | Chip Kerchner | 2021-02-17 |
* | New accurate algorithm for pow(x,y). This version is accurate to 1.4 ulps for... | Rasmus Munk Larsen | 2021-02-17 |
* | Updated pfrexp implementation. | Antonio Sanchez | 2021-02-17 |
* | missing method in packetmath.h void ptranspose(PacketBlock<Packet16uc, 4>& ke... | Ashutosh Sharma | 2021-02-16 |