Re: [Nouveau] [PATCH v2] nv50/ir: optimize shl(a, 0) to a

2017-04-29 Thread Ilia Mirkin
Maybe in a separate change. I'd want to double check on all gens. I think the thing I suggested is sufficient. On Apr 29, 2017 8:09 PM, "Karol Herbst" wrote: 2017-04-30 0:28 GMT+02:00 Ilia Mirkin : > On Sat, Apr 29, 2017 at 6:09 PM, Karol Herbst wrote: >> helps two alien isolation shaders >> >>

Re: [Nouveau] [PATCH v2] nv50/ir: optimize shl(a, 0) to a

2017-04-29 Thread Karol Herbst
2017-04-30 0:28 GMT+02:00 Ilia Mirkin : > On Sat, Apr 29, 2017 at 6:09 PM, Karol Herbst wrote: >> helps two alien isolation shaders >> >> shader-db: >> total instructions in shared programs : 4251497 -> 4251494 (-0.00%) >> total gprs used in shared programs: 513962 -> 513962 (0.00%) >> total l

Re: [Nouveau] [PATCH v2] nv50/ir: optimize shl(a, 0) to a

2017-04-29 Thread Ilia Mirkin
On Sat, Apr 29, 2017 at 6:09 PM, Karol Herbst wrote: > helps two alien isolation shaders > > shader-db: > total instructions in shared programs : 4251497 -> 4251494 (-0.00%) > total gprs used in shared programs: 513962 -> 513962 (0.00%) > total local used in shared programs : 29797 -> 29797

[Nouveau] [PATCH v2] nv50/ir: optimize shl(a, 0) to a

2017-04-29 Thread Karol Herbst
helps two alien isolation shaders shader-db: total instructions in shared programs : 4251497 -> 4251494 (-0.00%) total gprs used in shared programs: 513962 -> 513962 (0.00%) total local used in shared programs : 29797 -> 29797 (0.00%) total bytes used in shared programs : 38960264 -> 38960

Re: [Nouveau] [PATCH] nv50/ir: optimmize shl(a, 0) to a

2017-04-29 Thread Karol Herbst
2017-04-29 21:03 GMT+02:00 Ilia Mirkin : > On Sat, Apr 29, 2017 at 12:46 PM, Karol Herbst wrote: >> helps two alien isolation shaders >> >> shader-db: >> total instructions in shared programs : 4251497 -> 4251494 (-0.00%) >> total gprs used in shared programs: 513962 -> 513962 (0.00%) >> total

Re: [Nouveau] [PATCH] nv50/ir: optimmize shl(a, 0) to a

2017-04-29 Thread Ilia Mirkin
On Sat, Apr 29, 2017 at 12:46 PM, Karol Herbst wrote: > helps two alien isolation shaders > > shader-db: > total instructions in shared programs : 4251497 -> 4251494 (-0.00%) > total gprs used in shared programs: 513962 -> 513962 (0.00%) > total local used in shared programs : 29797 -> 29797

Re: [Nouveau] [PATCH] nv50/ir: optimmize shl(a, 0) to a

2017-04-29 Thread Samuel Pitoiset
"optimmize" ? No need to resend just for that though. Reviewed-by: Samuel Pitoiset On 04/29/2017 06:46 PM, Karol Herbst wrote: helps two alien isolation shaders shader-db: total instructions in shared programs : 4251497 -> 4251494 (-0.00%) total gprs used in shared programs: 513962 -> 513

[Nouveau] [PATCH] nv50/ir: optimmize shl(a, 0) to a

2017-04-29 Thread Karol Herbst
helps two alien isolation shaders shader-db: total instructions in shared programs : 4251497 -> 4251494 (-0.00%) total gprs used in shared programs: 513962 -> 513962 (0.00%) total local used in shared programs : 29797 -> 29797 (0.00%) total bytes used in shared programs : 38960264 -> 38960

Re: [Nouveau] [PATCH] nv50/ir: we can't replace 0x0 with zero reg for SHLADD

2017-04-29 Thread Karol Herbst
2017-04-29 17:18 GMT+02:00 Ilia Mirkin : > On Sat, Apr 29, 2017 at 10:41 AM, Karol Herbst wrote: >> fixes a crash in Alien Isolation > > What crash? assertion, because shladd requires an immediate, there can't be a reg at src1 "shladd u32 $r0 $r0 $r63 $r36" is invalid for the emiter so we have t

Re: [Nouveau] [PATCH] nv50/ir: we can't replace 0x0 with zero reg for SHLADD

2017-04-29 Thread Ilia Mirkin
On Sat, Apr 29, 2017 at 10:41 AM, Karol Herbst wrote: > fixes a crash in Alien Isolation What crash? How did the zero get there? Does this only happen if you do your optimization loop thing? In either case, we still want the replaceZero() logic. However that logic should be aware that the middle

[Nouveau] [PATCH] nv50/ir: we can't replace 0x0 with the zero reg for SHLADD

2017-04-29 Thread Karol Herbst
fixes a crash in Alien Isolation Signed-off-by: Karol Herbst Cc: 13.0 17.0 17.1 --- src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp b/src/gallium/driv

[Nouveau] [PATCH] nv50/ir: we can't replace 0x0 with zero reg for SHLADD

2017-04-29 Thread Karol Herbst
fixes a crash in Alien Isolation Signed-off-by: Karol Herbst --- src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/

Re: [Nouveau] [PATCH] drm/nouveau/fb/gf100-: Fix 32 bit wraparound in new ram detection

2017-04-29 Thread Karol Herbst
good catch Reviewed-by: Karol Herbst 2017-04-29 6:11 GMT+02:00 Mario Kleiner : > A missing u64 cast causes a 32-Bit wraparound from > 4096 MiB to 0 MiB and therefore total 0 MiB VRAM detected > if card has 4096 Mib per FBP. > > Signed-off-by: Mario Kleiner > --- > drivers/gpu/drm/nouveau/nvkm/