projects / platform / upstream / tvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 464ebb1) | patch
add GPU checking before compilation for rocm (#4394)
authorThomas Viehmann <tv.code@beamnet.de>
Thu, 21 Nov 2019 14:40:29 +0000 (15:40 +0100)
committermasahi <masahi129@gmail.com>
Thu, 21 Nov 2019 14:40:29 +0000 (23:40 +0900)
commit786d7998e1afe0a9d5a9e0091a4509afc748d798
treed2581ec98095b37bbd0257f1e1f73184c6158aa9tree | snapshot
parent464ebb13f810147f9241ae58f11cc10d4e5f65bccommit | diff
add GPU checking before compilation for rocm (#4394)

Previously, we would rely on the later phases to error out
(often for using too much shared memory). This enables the
checks on the IR that already exist for CUDA and OpenCL also
for ROCm.
python/tvm/autotvm/measure/measure_methods.py diff | blob | history
Domain: Machine Learning / ML Framework;