Re: [Intel-gfx] [PATCH] drm/i915: Micro-optimise i915_request_retire()

2018-05-03 Thread Tvrtko Ursulin
On 03/05/2018 15:06, Chris Wilson wrote: Quoting Joonas Lahtinen (2018-05-03 14:59:35) Quoting Chris Wilson (2018-05-02 20:21:42) I caught the compiler emitting the if(!NULL) guard at the start of dma_fence_put(); on the request it should know for certain is already non-NULL. Mark up the funct

Re: [Intel-gfx] [PATCH] drm/i915: Micro-optimise i915_request_retire()

2018-05-03 Thread Chris Wilson
Quoting Joonas Lahtinen (2018-05-03 14:59:35) > Quoting Chris Wilson (2018-05-02 20:21:42) > > I caught the compiler emitting the if(!NULL) guard at the start of > > dma_fence_put(); on the request it should know for certain is already > > non-NULL. Mark up the function as non-null and tell the com

Re: [Intel-gfx] [PATCH] drm/i915: Micro-optimise i915_request_retire()

2018-05-03 Thread Joonas Lahtinen
Quoting Chris Wilson (2018-05-02 20:21:42) > I caught the compiler emitting the if(!NULL) guard at the start of > dma_fence_put(); on the request it should know for certain is already > non-NULL. Mark up the function as non-null and tell the compiler that > the request pointer doesn't change: > >

[Intel-gfx] [PATCH] drm/i915: Micro-optimise i915_request_retire()

2018-05-02 Thread Chris Wilson
I caught the compiler emitting the if(!NULL) guard at the start of dma_fence_put(); on the request it should know for certain is already non-NULL. Mark up the function as non-null and tell the compiler that the request pointer doesn't change: add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-5 (-5) Fun