arm64: Add support for Half precision floating point
authorSuzuki K Poulose <suzuki.poulose@arm.com>
Tue, 26 Jan 2016 15:52:46 +0000 (15:52 +0000)
committerCatalin Marinas <catalin.marinas@arm.com>
Fri, 26 Feb 2016 15:37:01 +0000 (15:37 +0000)
commitbf5006184400d96d8c17eb9711178dc2221b8f34
tree327f30505f11097de7e12c6384568f7fe3d9e07f
parent3eca86e75ec7a7d4b9a9c8091b11676f7bd2a39f
arm64: Add support for Half precision floating point

ARMv8.2 extensions [1] include an optional feature, which supports
half precision(16bit) floating point/asimd data processing
instructions. This patch adds support for detecting and exposing
the same to the userspace via HWCAPs

[1] https://community.arm.com/groups/processors/blog/2016/01/05/armv8-a-architecture-evolution

Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
arch/arm64/include/uapi/asm/hwcap.h
arch/arm64/kernel/cpufeature.c
arch/arm64/kernel/cpuinfo.c