[PATCH i-g-t 09/11] lib/intel_compute: Fix enqueued local size in xehp

[Thomas Hellström]

On Tue, 2025-03-11 at 16:21 +0100, Francois Dugast wrote:
> According to the metadata of the compute kernel used for this test,
> the
> enqueued_local_size comes at offset 52, right after the value of the
> "count" argument. Fix it and add comments for clarity.
> 
> Relevant part of the kernel metadata:
> 
>       - arg_type:        arg_bypointer
>         offset:          32
>         size:            8
>         arg_index:       0
>         addrmode:        stateless
>         addrspace:       global
>         access_type:     readwrite
>       - arg_type:        arg_bypointer
>         offset:          40
>         size:            8
>         arg_index:       1
>         addrmode:        stateless
>         addrspace:       global
>         access_type:     readwrite
>       - arg_type:        arg_byvalue
>         offset:          48
>         size:            4
>         arg_index:       2
>       - arg_type:        enqueued_local_size
>         offset:          52
>         size:            12
> 
> Signed-off-by: Francois Dugast <francois.dugast at intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>

> ---
>  lib/intel_compute.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/lib/intel_compute.c b/lib/intel_compute.c
> index 7a2e04b10..f5b3a88f0 100644
> --- a/lib/intel_compute.c
> +++ b/lib/intel_compute.c
> @@ -781,12 +781,12 @@ static void xehp_create_indirect_data(uint32_t
> *addr_bo_buffer_batch,
>  	addr_bo_buffer_batch[b++] = addr_output & 0xffffffff;
>  	addr_bo_buffer_batch[b++] = addr_output >> 32;
>  	addr_bo_buffer_batch[b++] = loop_count;
> +	addr_bo_buffer_batch[b++] = 0x00000400; // Enqueued local
> size X
> +	addr_bo_buffer_batch[b++] = 0x00000001; // Enqueued local
> size Y
> +	addr_bo_buffer_batch[b++] = 0x00000001; // Enqueued local
> size Z
>  	addr_bo_buffer_batch[b++] = 0x00000000;
>  	addr_bo_buffer_batch[b++] = 0x00000000;
>  	addr_bo_buffer_batch[b++] = 0x00000000;
> -	addr_bo_buffer_batch[b++] = 0x00000400;
> -	addr_bo_buffer_batch[b++] = 0x00000001;
> -	addr_bo_buffer_batch[b++] = 0x00000001;
>  	addr_bo_buffer_batch[b++] = 0x00000000;
>  	addr_bo_buffer_batch[b++] = 0x00000000;
>  	addr_bo_buffer_batch[b++] = 0x00000000;