[mlir] Change test-gpu-to-cubin to derive from SerializeToBlobPass
authorChristian Sigg <csigg@google.com>
Wed, 10 Mar 2021 16:52:58 +0000 (17:52 +0100)
committerChristian Sigg <csigg@google.com>
Thu, 11 Mar 2021 09:42:20 +0000 (10:42 +0100)
commitbafe418d12e9aa94fc3de210b556c5452799f6b1
tree6751e59cfba51650732b102f824bf5652c927f77
parent68e01339cc5bc3d8a885bc9413611fbc6ca151e4
[mlir] Change test-gpu-to-cubin to derive from SerializeToBlobPass

Clean-up after D98279, remove one call to createConvertGPUKernelToBlobPass().

Depends On D98203

Reviewed By: mehdi_amini

Differential Revision: https://reviews.llvm.org/D98360
mlir/test/Conversion/GPUToCUDA/lower-nvvm-kernel-to-cubin.mlir
mlir/test/lib/Transforms/TestConvertGPUKernelToCubin.cpp
mlir/tools/mlir-opt/mlir-opt.cpp