From 70329cf51fabe2ef6922dab8968ede71d64bf731 Mon Sep 17 00:00:00 2001 From: David Rosca Date: Tue, 26 May 2026 10:08:43 +0200 Subject: [PATCH] radeonsi/mm: Remove comment about kernel AV1 instance scheduling bug This has already been fixed. We still want to always use new context with multi instance VCNs to utilize all instances, so the kernel bug being present or not won't change the decision there. Reviewed-by: Pierre-Eric Pelloux-Prayer Part-of: --- src/gallium/drivers/radeonsi/mm/si_video.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/src/gallium/drivers/radeonsi/mm/si_video.c b/src/gallium/drivers/radeonsi/mm/si_video.c index f928116f92c..3e195fc1884 100644 --- a/src/gallium/drivers/radeonsi/mm/si_video.c +++ b/src/gallium/drivers/radeonsi/mm/si_video.c @@ -201,11 +201,6 @@ static bool si_vcn_need_context(struct si_context *ctx) /* Kernel does VCN instance scheduling per context, so when we have * multiple instances we should use new context to be able to utilize * all of them. - * Another issue is with AV1, VCN 3 and VCN 4 only support AV1 on - * first instance. Kernel parses IBs and switches to first instance when - * it detects AV1, but this only works for first submitted IB in context. - * The CS would be rejected if we first decode/encode other codecs, kernel - * schedules on second instance (default) and then we try to decode/encode AV1. */ return ctx->screen->info.ip[AMD_IP_VCN_ENC].num_instances > 1; }