Re: [Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-21 Thread Marek Olšák
On Tue, Aug 21, 2018 at 2:26 PM Andres Rodriguez wrote: > > > > On 2018-08-21 01:54 PM, Marek Olšák wrote: > > Note that WAVES_PER_SH should be 0x3ff on the compute ring for the > > ring priorities to be applied. > > Correct, we would need to set WAVES_PER_SH during pipeline creation. > > > I

Re: [Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-21 Thread Andres Rodriguez
On 2018-08-21 01:54 PM, Marek Olšák wrote: Note that WAVES_PER_SH should be 0x3ff on the compute ring for the ring priorities to be applied. Correct, we would need to set WAVES_PER_SH during pipeline creation. I don't know if you need to do the same thing for the gfx ring. You can ask

Re: [Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-21 Thread Marek Olšák
Note that WAVES_PER_SH should be 0x3ff on the compute ring for the ring priorities to be applied. I don't know if you need to do the same thing for the gfx ring. You can ask Andres for more info. Marek On Tue, Aug 14, 2018 at 12:10 PM Samuel Pitoiset wrote: > > The last parameter of

Re: [Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-20 Thread Marek Olšák
You are lucky that WAVES_PER_SH was not 3. Such a low limit could decrease compute shader performance to ~2%. Marek ___ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev

Re: [Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-15 Thread Samuel Pitoiset
On 8/15/18 3:34 PM, Bas Nieuwenhuizen wrote: On Wed, Aug 15, 2018 at 2:13 PM, Samuel Pitoiset wrote: On 8/14/18 9:15 PM, Bas Nieuwenhuizen wrote: On Tue, Aug 14, 2018 at 6:11 PM, Samuel Pitoiset wrote: The last parameter of radeon_set_sh_reg_seq() is the number of dwords to emit. We

Re: [Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-15 Thread Bas Nieuwenhuizen
On Wed, Aug 15, 2018 at 2:13 PM, Samuel Pitoiset wrote: > > > On 8/14/18 9:15 PM, Bas Nieuwenhuizen wrote: >> >> On Tue, Aug 14, 2018 at 6:11 PM, Samuel Pitoiset >> wrote: >>> >>> The last parameter of radeon_set_sh_reg_seq() is the number of >>> dwords to emit. We were lucky because

Re: [Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-15 Thread Samuel Pitoiset
On 8/14/18 9:15 PM, Bas Nieuwenhuizen wrote: On Tue, Aug 14, 2018 at 6:11 PM, Samuel Pitoiset wrote: The last parameter of radeon_set_sh_reg_seq() is the number of dwords to emit. We were lucky because WAVES_PER_SH(0x3) is 3 but it was initialized to 0. COMPUTE_RESOURCE_LIMITS is correctly

Re: [Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-14 Thread Bas Nieuwenhuizen
On Tue, Aug 14, 2018 at 6:11 PM, Samuel Pitoiset wrote: > The last parameter of radeon_set_sh_reg_seq() is the number of > dwords to emit. We were lucky because WAVES_PER_SH(0x3) is 3 but > it was initialized to 0. > > COMPUTE_RESOURCE_LIMITS is correctly set when generating > compute pipelines,

[Mesa-dev] [PATCH] radv: drop wrong initialization of COMPUTE_RESOURCE_LIMITS

2018-08-14 Thread Samuel Pitoiset
The last parameter of radeon_set_sh_reg_seq() is the number of dwords to emit. We were lucky because WAVES_PER_SH(0x3) is 3 but it was initialized to 0. COMPUTE_RESOURCE_LIMITS is correctly set when generating compute pipelines, so we don't need to initialize it. Signed-off-by: Samuel Pitoiset