nvm, I somehow didn't notice that "if (atom->dType != TYPE_F32)" check...
On Wed, Dec 5, 2018 at 3:43 PM Karol Herbst wrote:
>
> but uhm, how would that work if you assert(atom->subOp ==
> NV50_IR_SUBOP_ATOM_ADD); inside handleSharedATOMGM107? I thought
> that's only needed for fadd, not for all a
but uhm, how would that work if you assert(atom->subOp ==
NV50_IR_SUBOP_ATOM_ADD); inside handleSharedATOMGM107? I thought
that's only needed for fadd, not for all atoms
On Wed, Dec 5, 2018 at 3:17 PM Ilia Mirkin wrote:
>
> On Wed, Dec 5, 2018 at 4:59 AM Karol Herbst wrote:
> >
> > On Wed, Dec 5
On Wed, Dec 5, 2018 at 4:59 AM Karol Herbst wrote:
>
> On Wed, Dec 5, 2018 at 6:30 AM Ilia Mirkin wrote:
> >
> > Signed-off-by: Ilia Mirkin
> > ---
> > .../nouveau/codegen/nv50_ir_lowering_nvc0.cpp | 49 +++
> > .../nouveau/codegen/nv50_ir_lowering_nvc0.h | 1 +
> > 2 files c
On Wed, Dec 5, 2018 at 6:30 AM Ilia Mirkin wrote:
>
> Signed-off-by: Ilia Mirkin
> ---
> .../nouveau/codegen/nv50_ir_lowering_nvc0.cpp | 49 +++
> .../nouveau/codegen/nv50_ir_lowering_nvc0.h | 1 +
> 2 files changed, 50 insertions(+)
>
> diff --git a/src/gallium/drivers/nouvea
Signed-off-by: Ilia Mirkin
---
.../nouveau/codegen/nv50_ir_lowering_nvc0.cpp | 49 +++
.../nouveau/codegen/nv50_ir_lowering_nvc0.h | 1 +
2 files changed, 50 insertions(+)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
b/src/gallium/drivers/nouveau