diff options
| author | steniu01 <steven.niu@arm.com> | 2017-06-29 10:14:58 +0100 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-09-17 14:15:39 +0100 |
| commit | da37e2fa661f85090bd4a3b93c07178df268bd8c (patch) | |
| tree | 18c1937779c28e277ec6a0d9424ddc90f2292c87 /arm_compute/core/CL | |
| parent | 34702479adcf3559e8ebe27915179af509b070d2 (diff) | |
| download | ComputeLibrary-da37e2fa661f85090bd4a3b93c07178df268bd8c.tar.gz | |
COMPMID-431 Port CLDepthConvert to use 8-bit and 16-bit fixed point
Change-Id: Iedea9e985427e6242f34a5362615f79c0526d5bd
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/79786
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Diffstat (limited to 'arm_compute/core/CL')
| -rw-r--r-- | arm_compute/core/CL/kernels/CLDepthConvertKernel.h | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/arm_compute/core/CL/kernels/CLDepthConvertKernel.h b/arm_compute/core/CL/kernels/CLDepthConvertKernel.h index 2c3b1b8b69..b03b90b275 100644 --- a/arm_compute/core/CL/kernels/CLDepthConvertKernel.h +++ b/arm_compute/core/CL/kernels/CLDepthConvertKernel.h @@ -43,14 +43,17 @@ public: * * Valid conversions Input -> Output : * + * - QS8 -> F32 + * - QS16 -> F32 * - U8 -> U16, S16, U32, S32 * - U16 -> U8, U32, S32 * - S16 -> U8, U32, S32 * - U32 -> U8, U16, S16 * - S32 -> U8, U16, S16 + * - F32 -> QS8, QS16 * - * @param[in] input The input tensor to convert. Data types supported: U8, U16, S16, U32 or S32. - * @param[out] output The output tensor. Data types supported: U8, U16, S16, U32 or S32. + * @param[in] input The input tensor to convert. Data types supported: U8/QS8/U16/S16/QS16/U32/S32/F32. + * @param[out] output The output tensor. Data types supported: U8/QS8/U16/S16/QS16/U32/S32/F32. * @param[in] policy Conversion policy * @param[in] shift Value for down/up conversions. Must be 0 <= shift < 8. */ |