Re: [Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-02-01 Thread Iago Toral
On Mon, 2016-02-01 at 10:38 -0800, Matt Turner wrote: > On Thu, Jan 28, 2016 at 11:44 PM, Iago Toral wrote: > > On Thu, 2016-01-28 at 09:21 -0800, Matt Turner wrote: > >> On Thu, Jan 28, 2016 at 12:32 AM, Iago Toral wrote: > >> > On Mon, 2016-01-25 at 15:18 -0800, Matt Turner wrote: > > (...) > >

Re: [Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-02-01 Thread Matt Turner
On Thu, Jan 28, 2016 at 11:44 PM, Iago Toral wrote: > On Thu, 2016-01-28 at 09:21 -0800, Matt Turner wrote: >> On Thu, Jan 28, 2016 at 12:32 AM, Iago Toral wrote: >> > On Mon, 2016-01-25 at 15:18 -0800, Matt Turner wrote: > (...) >> >> diff --git a/src/glsl/nir/nir_opt_algebraic.py >> >> b/src/g

Re: [Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-01-29 Thread Jason Ekstrand
On Jan 29, 2016 8:44 AM, "Iago Toral" wrote: > > On Thu, 2016-01-28 at 09:21 -0800, Matt Turner wrote: > > On Thu, Jan 28, 2016 at 12:32 AM, Iago Toral wrote: > > > On Mon, 2016-01-25 at 15:18 -0800, Matt Turner wrote: > (...) > > >> diff --git a/src/glsl/nir/nir_opt_algebraic.py b/src/glsl/nir/n

Re: [Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-01-28 Thread Iago Toral
On Thu, 2016-01-28 at 09:21 -0800, Matt Turner wrote: > On Thu, Jan 28, 2016 at 12:32 AM, Iago Toral wrote: > > On Mon, 2016-01-25 at 15:18 -0800, Matt Turner wrote: (...) > >> diff --git a/src/glsl/nir/nir_opt_algebraic.py > >> b/src/glsl/nir/nir_opt_algebraic.py > >> index b761b54..56b0f5e 1006

Re: [Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-01-28 Thread Matt Turner
On Thu, Jan 28, 2016 at 10:43 AM, Jason Ekstrand wrote: > That's not quite correct. 1 means exactly one component while a destination > size of 0 means that it's a vectorizable operation. All 0-sized sources > automatically take on the size of the destination. This is how most > standard ALU opc

Re: [Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-01-28 Thread Jason Ekstrand
On Jan 28, 2016 09:22, "Matt Turner" wrote: > > On Thu, Jan 28, 2016 at 12:32 AM, Iago Toral wrote: > > On Mon, 2016-01-25 at 15:18 -0800, Matt Turner wrote: > >> --- > >> src/glsl/nir/nir.h | 4 > >> src/glsl/nir/nir_lower_alu_to_scalar.c | 32 +

Re: [Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-01-28 Thread Matt Turner
On Thu, Jan 28, 2016 at 12:32 AM, Iago Toral wrote: > On Mon, 2016-01-25 at 15:18 -0800, Matt Turner wrote: >> --- >> src/glsl/nir/nir.h | 4 >> src/glsl/nir/nir_lower_alu_to_scalar.c | 32 >> src/glsl/nir/nir_opcodes.py| 10 +

Re: [Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-01-28 Thread Iago Toral
On Mon, 2016-01-25 at 15:18 -0800, Matt Turner wrote: > --- > src/glsl/nir/nir.h | 4 > src/glsl/nir/nir_lower_alu_to_scalar.c | 32 > src/glsl/nir/nir_opcodes.py| 10 ++ > src/glsl/nir/nir_opt_algebraic.py | 20 ++

[Mesa-dev] [PATCH 09/12] nir: Add lowering support for packing opcodes.

2016-01-25 Thread Matt Turner
--- src/glsl/nir/nir.h | 4 src/glsl/nir/nir_lower_alu_to_scalar.c | 32 src/glsl/nir/nir_opcodes.py| 10 ++ src/glsl/nir/nir_opt_algebraic.py | 20 4 files changed, 66 insertions(+) diff --gi