[CODEGEN][CUDA] Fix vector load (#5226)
authorLiangLiu <1432249204@qq.com>
Tue, 14 Apr 2020 03:35:31 +0000 (11:35 +0800)
committerGitHub <noreply@github.com>
Tue, 14 Apr 2020 03:35:31 +0000 (23:35 -0400)
commitd2e58ad2fd92c09dffe064e4efbfc484cf2de6e5
treeb0a00570f5c606e768c0dfffba2a4e3f88f14620
parent2c1ca60ea38587401a20f11c5e64f452b79fa777
[CODEGEN][CUDA] Fix vector load (#5226)

* Fix high-low bit bug in __pack_half2

* Fix vector load

* Add unit8 support for PrintVecElemLoadExpr and BroadcastNode
src/target/source/codegen_c.cc
src/target/source/codegen_c.h
src/target/source/codegen_cuda.cc
src/target/source/codegen_cuda.h
src/target/source/literal/cuda_half_t.h
tests/python/unittest/test_target_codegen_cuda.py