On 9/30/25 7:48 AM, Akhil P Oommen wrote:
> A8x is the next generation of Adreno GPUs, featuring a significant
> hardware design change. A major update to the design is the introduction
> of Slice architecture. Slices are sort of mini-GPUs within the GPU which
> are more independent in processing Graphics and compute workloads. Also,
> in addition to the BV and BR pipe we saw in A7x, CP has more concurrency
> with additional pipes.
>
> From a software interface perspective, these changes have a significant
> impact on the KMD side. First, the GPU register space has been extensively
> reorganized. Second, to avoid a register space explosion caused by the
> new slice architecture and additional pipes, many registers are now
> virtualized, instead of duplicated as in A7x. KMD must configure an
> aperture register with the appropriate slice and pipe ID before accessing
> these virtualized registers.
>
> This patch adds only a skeleton support for the A8x family. An A8x GPU
> support will be added in an upcoming patch.
>
> Signed-off-by: Akhil P Oommen <[email protected]>
> ---
[...]
> +static void a8xx_aperture_slice_set(struct msm_gpu *gpu, enum adreno_pipe
> pipe, u32 slice)
> +{
> + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
> + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
> + u32 val;
> +
> + val = A8XX_CP_APERTURE_CNTL_HOST_PIPEID(pipe) |
> A8XX_CP_APERTURE_CNTL_HOST_SLICEID(slice);
> +
> + if (a6xx_gpu->cached_aperture == val)
> + return;
> +
> + gpu_write(gpu, REG_A8XX_CP_APERTURE_CNTL_HOST, val);
unless the effect is instantenous, this needs a readback
[...]
> +static u32 a8xx_get_first_slice(struct a6xx_gpu *a6xx_gpu)
> +{
> + return ffs(a6xx_gpu->slice_mask) - 1;
> +}
#define instead?
Perhaps also move it closer to the user
> +static void a8xx_set_ubwc_config(struct msm_gpu *gpu)
You modified a6xx_calc_ubwc_config() earlier in the patch
is one of them unnecessary?
[...]
> +static int a8xx_zap_shader_init(struct msm_gpu *gpu)
You can borrow this from a6xx_gpu
Perhaps moving such common functions to a separate file would be
even better, I glanced over the change and there is probably some
potential to commonize
Konrad
