[PATCH v7 1/5] lib/gpu_cmds: add Xe_LP version of emit_vfe_state

[Zbigniew Kempczyński]

On Wed, Jun 12, 2024 at 11:38:59AM +0200, Andrzej Hajda wrote:
> In Xe_LP version there is added argument to control EU thread
> dispatching mode. For shaders lagacy mode is used.
> 
> v2: added commit description
> v6: added public function descriptions
> 
> Signed-off-by: Andrzej Hajda <andrzej.hajda at intel.com>
> Reviewed-by: Dominik Grzegorzek <dominik.grzegorzek at intel.com>
> ---
>  lib/gpu_cmds.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++------
>  lib/gpu_cmds.h |  6 ++++++
>  2 files changed, 52 insertions(+), 6 deletions(-)
> 
> diff --git a/lib/gpu_cmds.c b/lib/gpu_cmds.c
> index 378fa9166ab8..b096670b073c 100644
> --- a/lib/gpu_cmds.c
> +++ b/lib/gpu_cmds.c
> @@ -651,10 +651,10 @@ gen7_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
>  	intel_bb_out(ibb, 0);
>  }
>  
> -void
> -gen8_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
> -		    uint32_t urb_entries, uint32_t urb_size,
> -		    uint32_t curbe_size)
> +static void
> +__gen8_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
> +		      uint32_t urb_entries, uint32_t urb_size,
> +		      uint32_t curbe_size, bool legacy_mode)
>  {
>  	intel_bb_out(ibb, GEN7_MEDIA_VFE_STATE | (9 - 2));
>  
> @@ -662,8 +662,8 @@ gen8_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
>  	intel_bb_out(ibb, 0);
>  	intel_bb_out(ibb, 0);
>  
> -	/* number of threads & urb entries */
> -	intel_bb_out(ibb, threads << 16 | urb_entries << 8);
> +	/* number of threads & urb entries & eu fusion */
> +	intel_bb_out(ibb, threads << 16 | urb_entries << 8 | legacy_mode << 6);
>  
>  	intel_bb_out(ibb, 0);
>  
> @@ -676,6 +676,25 @@ gen8_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
>  	intel_bb_out(ibb, 0);
>  }
>  
> +/**
> + * gen8_emit_vfe_state:
> + * @ibb: batchbuffer
> + * @threads: maximum number of threads
> + * @urb_entries: number of URB entries
> + * @urb_size: URB entry allocation size
> + * @curbe_size: CURBE allocation size
> + *
> + * Emits instruction MEDIA_VFE_STATE for Gen8+ which sets Video Front End (VFE)
> + * state.
> + */
> +void gen8_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
> +			 uint32_t urb_entries, uint32_t urb_size,
> +			 uint32_t curbe_size)
> +{
> +	__gen8_emit_vfe_state(ibb, threads, urb_entries, urb_size, curbe_size,
> +			      false);
> +}
> +
>  void
>  gen7_emit_curbe_load(struct intel_bb *ibb, uint32_t curbe_buffer)
>  {
> @@ -864,6 +883,27 @@ gen7_emit_media_objects(struct intel_bb *ibb,
>  			gen_emit_media_object(ibb, x + i * 16, y + j * 16);
>  }
>  
> +/**
> + * xelp_emit_vfe_state:
> + * @ibb: pointer to intel_bb
> + * @threads: maximum number of threads
> + * @urb_entries: number of URB entries
> + * @urb_size: URB entry allocation size
> + * @curbe_size: CURBE allocation size
> + * @legacy_mode: if set, threads are dispatched individually (legacy mode),
> + *     otherwise they are dispatched in sets(fused EU mode)
> + *
> + * Emits instruction MEDIA_VFE_STATE for XeLP which sets Video Front End (VFE)
> + * state.
> + */
> +void xelp_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
> +			 uint32_t urb_entries, uint32_t urb_size,
> +			 uint32_t curbe_size, bool legacy_mode)
> +{
> +	return __gen8_emit_vfe_state(ibb, threads, urb_entries, urb_size,
> +				     curbe_size, legacy_mode);

return is not necessary here, __gen8_emit_vfe_state() is void function.

As patch is already reviewed it's just notice, not nit.

--
Zbigniew

> +}
> +
>  /*
>   * XEHP
>   */
> diff --git a/lib/gpu_cmds.h b/lib/gpu_cmds.h
> index 348c6c9453e9..1b9156a80c7c 100644
> --- a/lib/gpu_cmds.h
> +++ b/lib/gpu_cmds.h
> @@ -81,6 +81,12 @@ void
>  gen8_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
>  		    uint32_t urb_entries, uint32_t urb_size,
>  		    uint32_t curbe_size);
> +
> +void
> +xelp_emit_vfe_state(struct intel_bb *ibb, uint32_t threads,
> +		    uint32_t urb_entries, uint32_t urb_size,
> +		    uint32_t curbe_size, bool legacy_mode);
> +
>  void
>  gen7_emit_curbe_load(struct intel_bb *ibb, uint32_t curbe_buffer);
>  
> 
> -- 
> 2.34.1
>