NVPTX: Add f16 SIMD intrinsics #2370

Job	Run time
Check Style	15s
Automatic intrinsic verification	29s
Build Documentation	1m 17s
Env Override (ubuntu-latest)	13s
Test (i686-unknown-linux-gnu)	2m 2s
Env Override (windows-latest)	28s
Test (x86_64-unknown-linux-gnu)	3m 51s
Build std_detect	1m 2s
Test (x86_64-unknown-linux-gnu-emulated)	9m 26s
Test (arm-unknown-linux-gnueabihf)	1m 17s
Test (armv7-unknown-linux-gnueabihf)	10m 46s
Test (aarch64-unknown-linux-gnu)	21m 23s
Test (riscv64gc-unknown-linux-gnu)	1m 16s
Test (powerpc64le-unknown-linux-gnu)	3m 39s
Test (s390x-unknown-linux-gnu)	1m 23s
Test (wasm32-wasip1)	1m 27s
Test (i586-unknown-linux-gnu)	1m 56s
Test (nvptx64-nvidia-cuda)	28s
Test (thumbv6m-none-eabi)	16s
Test (thumbv7m-none-eabi)	13s
Test (thumbv7em-none-eabi)	11s
Test (thumbv7em-none-eabihf)	15s
Test (loongarch64-unknown-linux-gnu)	1m 32s
Test (x86_64-apple-darwin)	9m 10s
Test (aarch64-apple-darwin)	57s
Test (x86_64-pc-windows-msvc)	6m 55s
Test (i686-pc-windows-msvc)	3m 9s
Test (aarch64-pc-windows-msvc)	1m 22s
Test (x86_64-pc-windows-gnu)	7m 6s
success	1s
	1h 33m 45s

Provide feedback