| Commit message (Expand) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | [NVPTX] Added llvm.nvvm.mma.m8n8k4.* intrinsics | Artem Belevich | 2019-10-28 | 1 | -59/+101 |
| * | PTX 6.3 extends `wmma` instruction to support s8/u8/s4/u4/b1 -> s32. | Artem Belevich | 2019-04-25 | 1 | -70/+357 |
| * | [NVPTX] generate correct MMA instruction mnemonics with PTX63+. | Artem Belevich | 2019-04-25 | 1 | -3/+14 |
| * | Python compat - print statement | Serge Guelton | 2019-01-03 | 1 | -0/+2 |
| * | [NVPTX, CUDA] Added support for m8n32k16 and m32n8k16 variants of wmma instru... | Artem Belevich | 2018-04-18 | 1 | -18/+23 |
| * | [NVPTX] Make tensor shape part of WMMA intrinsic's name. | Artem Belevich | 2018-03-21 | 1 | -39/+44 |
| * | [NVPTX] Make tensor load/store intrinsics overloaded. | Artem Belevich | 2018-03-20 | 1 | -16/+36 |
| * | [NVPTX] Implemented wmma intrinsics and instructions. | Artem Belevich | 2017-10-12 | 1 | -0/+201 |
 |
index : bcm5719-llvm | |
| Project Ortega BCM5719 LLVM | Raptor Computing Systems |
| summaryrefslogtreecommitdiffstats |
|