Displaying 20 results from an estimated 25 matches for "ffma".
Did you mean:
fma
2017 Jul 01
2
[PATCH 1/2] nv110/exa: Remove depbars
...$r0 0x0 0x1 t2d 0xc
sched (st 0x0) (st 0x0) (st 0x0)
-depbar le 0x5 0x1 0x1
fmul ftz $r5 $r4 c0[0x0]
fadd ftz $r3 $r5 c0[0x4]
-sched (st 0x0) (st 0x0) (st 0x0)
fadd ftz $r4 $r5 c0[0x8]
-fadd ftz $r5 $r5 c0[0xc]
-depbar le 0x5 0x0 0x0
sched (st 0x0) (st 0x0) (st 0x0)
+fadd ftz $r5 $r5 c0[0xc]
ffma ftz $r3 $r0 c0[0x10] $r3
ffma ftz $r4 $r0 c0[0x14] $r4
-ffma ftz $r5 $r0 c0[0x18] $r5
sched (st 0x0) (st 0x0) (st 0x0)
+ffma ftz $r5 $r0 c0[0x18] $r5
ffma ftz $r0 $r1 c0[0x1c] $r3
ffma ftz $r2 $r1 c0[0x24] $r5
-ffma ftz $r1 $r1 c0[0x20] $r4
sched (st 0x0) (st 0x0) (st 0x0)
+ffma ftz $r1 $r1 c0...
2018 Sep 08
0
[PATCH] maxwell,pascal: add scheduling data to shaders
...0x1)
depbar le 0x5 0x1 0x1
fmul ftz $r5 $r4 c0[0x0]
fadd ftz $r3 $r5 c0[0x4]
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x1) (st 0x1) (st 0x3)
fadd ftz $r4 $r5 c0[0x8]
fadd ftz $r5 $r5 c0[0xc]
depbar le 0x5 0x0 0x0
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x1 wt 0x1) (st 0x1) (st 0x4)
ffma ftz $r3 $r0 c0[0x10] $r3
ffma ftz $r4 $r0 c0[0x14] $r4
ffma ftz $r5 $r0 c0[0x18] $r5
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x2) (st 0x1) (st 0x1)
ffma ftz $r0 $r1 c0[0x1c] $r3
ffma ftz $r2 $r1 c0[0x24] $r5
ffma ftz $r1 $r1 c0[0x20] $r4
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0xf wt...
2017 Jun 27
4
[PATCH v4] nv110/exa: update sched codes
...0x1)
depbar le 0x5 0x1 0x1
fmul ftz $r5 $r4 c0[0x0]
fadd ftz $r3 $r5 c0[0x4]
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6) (st 0x6) (st 0xf)
fadd ftz $r4 $r5 c0[0x8]
fadd ftz $r5 $r5 c0[0xc]
depbar le 0x5 0x0 0x0
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6 wt 0x1) (st 0x1) (st 0x1)
ffma ftz $r3 $r0 c0[0x10] $r3
ffma ftz $r4 $r0 c0[0x14] $r4
ffma ftz $r5 $r0 c0[0x18] $r5
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x1) (st 0x1) (st 0x6)
ffma ftz $r0 $r1 c0[0x1c] $r3
ffma ftz $r2 $r1 c0[0x24] $r5
ffma ftz $r1 $r1 c0[0x20] $r4
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0xf) (...
2017 Jun 10
2
[PATCH v3] nv110/exa: update sched codes
...0x6)
depbar le 0x5 0x1 0x1
fmul ftz $r5 $r4 c0[0x0]
fadd ftz $r3 $r5 c0[0x4]
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6) (st 0x6) (st 0xf)
fadd ftz $r4 $r5 c0[0x8]
fadd ftz $r5 $r5 c0[0xc]
depbar le 0x5 0x0 0x0
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6 wt 0x2) (st 0x1) (st 0x1)
ffma ftz $r3 $r0 c0[0x10] $r3
ffma ftz $r4 $r0 c0[0x14] $r4
ffma ftz $r5 $r0 c0[0x18] $r5
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x1) (st 0x1) (st 0x6)
ffma ftz $r0 $r1 c0[0x1c] $r3
ffma ftz $r2 $r1 c0[0x24] $r5
ffma ftz $r1 $r1 c0[0x20] $r4
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0xf) (...
2017 Jun 03
2
[PATCH v2] nv110/exa: update sched codes
...0x6)
depbar le 0x5 0x1 0x1
fmul ftz $r5 $r4 c0[0x0]
fadd ftz $r3 $r5 c0[0x4]
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6) (st 0x6) (st 0xf)
fadd ftz $r4 $r5 c0[0x8]
fadd ftz $r5 $r5 c0[0xc]
depbar le 0x5 0x0 0x0
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6 wt 0x2) (st 0x1) (st 0x1)
ffma ftz $r3 $r0 c0[0x10] $r3
ffma ftz $r4 $r0 c0[0x14] $r4
ffma ftz $r5 $r0 c0[0x18] $r5
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x1) (st 0x1) (st 0x6)
ffma ftz $r0 $r1 c0[0x1c] $r3
ffma ftz $r2 $r1 c0[0x24] $r5
ffma ftz $r1 $r1 c0[0x20] $r4
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0xf) (...
2014 Apr 30
2
Proper gl_SampleMask output
...00000
>
> which, with "nvdisas -b SM30 -raw" decodes to
>
> /*0008*/ IPA.PASS R0, a[0x70], RZ;
> /*0010*/ IPA.PASS R1, a[0x74], RZ;
> /*0018*/ MOV R2, c[0x0][0x4];
> /*0020*/ FFMA R1, R1, c[0x0][0x0], R2;
> /*0028*/ F2I.S32.F32.TRUNC R0, R0;
> /*0030*/ IMUL32I.U32.U32 R0, R0, 0x10204081;
> /*0038*/ F2I.S32.F32.TRUNC R1, R1;
> /*0048*/ IMUL32I.U32.U32 R1, R1, 0x1010101;
>...
2016 Oct 16
2
[PATCH] exa: add GM10x acceleration support
...0x0 t2d 0x8
+tex nodep $r0 $r0 0x0 0x1 t2d 0xc
+sched (st 0x0) (st 0x0) (st 0x0)
+depbar le 0x5 0x1 0x1
+fmul ftz $r5 $r4 c0[0x0]
+fadd ftz $r3 $r5 c0[0x4]
+sched (st 0x0) (st 0x0) (st 0x0)
+fadd ftz $r4 $r5 c0[0x8]
+fadd ftz $r5 $r5 c0[0xc]
+depbar le 0x5 0x0 0x0
+sched (st 0x0) (st 0x0) (st 0x0)
+ffma ftz $r3 $r0 c0[0x10] $r3
+ffma ftz $r4 $r0 c0[0x14] $r4
+ffma ftz $r5 $r0 c0[0x18] $r5
+sched (st 0x0) (st 0x0) (st 0x0)
+ffma ftz $r0 $r1 c0[0x1c] $r3
+ffma ftz $r2 $r1 c0[0x24] $r5
+ffma ftz $r1 $r1 c0[0x20] $r4
+sched (st 0x0) (st 0x0) (st 0x0)
+exit
+#endif
diff --git a/src/shader/videonv110.fp...
2016 Oct 27
0
[PATCH v2 1/7] exa: add GM10x acceleration support
...0x0 t2d 0x8
+tex nodep $r0 $r0 0x0 0x1 t2d 0xc
+sched (st 0x0) (st 0x0) (st 0x0)
+depbar le 0x5 0x1 0x1
+fmul ftz $r5 $r4 c0[0x0]
+fadd ftz $r3 $r5 c0[0x4]
+sched (st 0x0) (st 0x0) (st 0x0)
+fadd ftz $r4 $r5 c0[0x8]
+fadd ftz $r5 $r5 c0[0xc]
+depbar le 0x5 0x0 0x0
+sched (st 0x0) (st 0x0) (st 0x0)
+ffma ftz $r3 $r0 c0[0x10] $r3
+ffma ftz $r4 $r0 c0[0x14] $r4
+ffma ftz $r5 $r0 c0[0x18] $r5
+sched (st 0x0) (st 0x0) (st 0x0)
+ffma ftz $r0 $r1 c0[0x1c] $r3
+ffma ftz $r2 $r1 c0[0x24] $r5
+ffma ftz $r1 $r1 c0[0x20] $r4
+sched (st 0x0) (st 0x0) (st 0x0)
+exit
+#endif
diff --git a/src/shader/videonv110.fp...
2016 Oct 17
0
[PATCH] exa: add GM10x acceleration support
...; +sched (st 0x0) (st 0x0) (st 0x0)
> +depbar le 0x5 0x1 0x1
> +fmul ftz $r5 $r4 c0[0x0]
> +fadd ftz $r3 $r5 c0[0x4]
> +sched (st 0x0) (st 0x0) (st 0x0)
> +fadd ftz $r4 $r5 c0[0x8]
> +fadd ftz $r5 $r5 c0[0xc]
> +depbar le 0x5 0x0 0x0
> +sched (st 0x0) (st 0x0) (st 0x0)
> +ffma ftz $r3 $r0 c0[0x10] $r3
> +ffma ftz $r4 $r0 c0[0x14] $r4
> +ffma ftz $r5 $r0 c0[0x18] $r5
> +sched (st 0x0) (st 0x0) (st 0x0)
> +ffma ftz $r0 $r1 c0[0x1c] $r3
> +ffma ftz $r2 $r1 c0[0x24] $r5
> +ffma ftz $r1 $r1 c0[0x20] $r4
> +sched (st 0x0) (st 0x0) (st 0x0)
> +exit
>...
2017 Jun 28
1
[PATCH v4] nv110/exa: update sched codes
...> > -sched (st 0x0) (st 0x0) (st 0x0)
> > +sched (st 0x6) (st 0x6) (st 0xf)
> > fadd ftz $r4 $r5 c0[0x8]
> > fadd ftz $r5 $r5 c0[0xc]
> > depbar le 0x5 0x0 0x0
> > -sched (st 0x0) (st 0x0) (st 0x0)
> > +sched (st 0x6 wt 0x1) (st 0x1) (st 0x1)
> > ffma ftz $r3 $r0 c0[0x10] $r3
> > ffma ftz $r4 $r0 c0[0x14] $r4
> > ffma ftz $r5 $r0 c0[0x18] $r5
> > -sched (st 0x0) (st 0x0) (st 0x0)
> > +sched (st 0x1) (st 0x1) (st 0x6)
> > ffma ftz $r0 $r1 c0[0x1c] $r3
> > ffma ftz $r2 $r1 c0[0x24] $r5
> > ffma ftz $r...
2017 Jun 07
2
[PATCH v2] nv110/exa: update sched codes
...0x4]
>> -sched (st 0x0) (st 0x0) (st 0x0)
>> +sched (st 0x6) (st 0x6) (st 0xf)
>> fadd ftz $r4 $r5 c0[0x8]
>> fadd ftz $r5 $r5 c0[0xc]
>> depbar le 0x5 0x0 0x0
>> -sched (st 0x0) (st 0x0) (st 0x0)
>> +sched (st 0x6 wt 0x2) (st 0x1) (st 0x1)
>> ffma ftz $r3 $r0 c0[0x10] $r3
>> ffma ftz $r4 $r0 c0[0x14] $r4
>> ffma ftz $r5 $r0 c0[0x18] $r5
>> -sched (st 0x0) (st 0x0) (st 0x0)
>> +sched (st 0x1) (st 0x1) (st 0x6)
>> ffma ftz $r0 $r1 c0[0x1c] $r3
>> ffma ftz $r2 $r1 c0[0x24] $r5
>> ffma ftz $r1...
2014 Apr 23
2
Proper gl_SampleMask output
Hello,
I've been trying to add ARB_sample_shading support to nouveau, and am
being defeated by the gl_SampleMask tests. Everything else works fine.
(And naturally the tests pass with the proprietary driver.) I'm trying
to do this for both GT21x, as well as GF100+.
In the GT21x case, it seems like the low bit of method 0x1928 needs to
be set (as well as the second-to-lowest bit), for
2017 Jul 01
0
[PATCH v5 2/2] nv110/exa: update sched codes
...0x0 0x0 t2d 0x8
tex nodep $r0 $r0 0x0 0x1 t2d 0xc
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6) (st 0x1) (st 0x6)
fmul ftz $r5 $r4 c0[0x0]
fadd ftz $r3 $r5 c0[0x4]
fadd ftz $r4 $r5 c0[0x8]
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6) (st 0x6 wt 0x1) (st 0x1)
fadd ftz $r5 $r5 c0[0xc]
ffma ftz $r3 $r0 c0[0x10] $r3
ffma ftz $r4 $r0 c0[0x14] $r4
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x1) (st 0x1) (st 0x1)
ffma ftz $r5 $r0 c0[0x18] $r5
ffma ftz $r0 $r1 c0[0x1c] $r3
ffma ftz $r2 $r1 c0[0x24] $r5
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6) (st 0xf) (st 0x0)
ffma ftz $r1...
2017 Jun 03
0
[PATCH] nv110/exa: update sched codes
...0x6)
depbar le 0x5 0x1 0x1
fmul ftz $r5 $r4 c0[0x0]
fadd ftz $r3 $r5 c0[0x4]
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6) (st 0x6) (st 0xf)
fadd ftz $r4 $r5 c0[0x8]
fadd ftz $r5 $r5 c0[0xc]
depbar le 0x5 0x0 0x0
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x6 wt 0x2) (st 0x1) (st 0x1)
ffma ftz $r3 $r0 c0[0x10] $r3
ffma ftz $r4 $r0 c0[0x14] $r4
ffma ftz $r5 $r0 c0[0x18] $r5
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0x1) (st 0x1) (st 0x6)
ffma ftz $r0 $r1 c0[0x1c] $r3
ffma ftz $r2 $r1 c0[0x24] $r5
ffma ftz $r1 $r1 c0[0x20] $r4
-sched (st 0x0) (st 0x0) (st 0x0)
+sched (st 0xf) (...
2017 Jun 29
0
[PATCH v4] nv110/exa: update sched codes
...0x0]
> fadd ftz $r3 $r5 c0[0x4]
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6) (st 0x6) (st 0xf)
> fadd ftz $r4 $r5 c0[0x8]
> fadd ftz $r5 $r5 c0[0xc]
> depbar le 0x5 0x0 0x0
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6 wt 0x1) (st 0x1) (st 0x1)
> ffma ftz $r3 $r0 c0[0x10] $r3
> ffma ftz $r4 $r0 c0[0x14] $r4
> ffma ftz $r5 $r0 c0[0x18] $r5
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x1) (st 0x1) (st 0x6)
> ffma ftz $r0 $r1 c0[0x1c] $r3
> ffma ftz $r2 $r1 c0[0x24] $r5
> ffma ftz $r1 $r1 c0[0x20] $r4
> -sched...
2017 Jun 10
0
[PATCH v3] nv110/exa: update sched codes
...4 c0[0x0]
> fadd ftz $r3 $r5 c0[0x4]
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6) (st 0x6) (st 0xf)
> fadd ftz $r4 $r5 c0[0x8]
> fadd ftz $r5 $r5 c0[0xc]
> depbar le 0x5 0x0 0x0
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6 wt 0x2) (st 0x1) (st 0x1)
> ffma ftz $r3 $r0 c0[0x10] $r3
> ffma ftz $r4 $r0 c0[0x14] $r4
> ffma ftz $r5 $r0 c0[0x18] $r5
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x1) (st 0x1) (st 0x6)
> ffma ftz $r0 $r1 c0[0x1c] $r3
> ffma ftz $r2 $r1 c0[0x24] $r5
> ffma ftz $r1 $r1 c0[0x20] $r4
> -sched (st...
2017 Jun 28
0
[PATCH v4] nv110/exa: update sched codes
...4 c0[0x0]
> fadd ftz $r3 $r5 c0[0x4]
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6) (st 0x6) (st 0xf)
> fadd ftz $r4 $r5 c0[0x8]
> fadd ftz $r5 $r5 c0[0xc]
> depbar le 0x5 0x0 0x0
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6 wt 0x1) (st 0x1) (st 0x1)
> ffma ftz $r3 $r0 c0[0x10] $r3
> ffma ftz $r4 $r0 c0[0x14] $r4
> ffma ftz $r5 $r0 c0[0x18] $r5
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x1) (st 0x1) (st 0x6)
> ffma ftz $r0 $r1 c0[0x1c] $r3
> ffma ftz $r2 $r1 c0[0x24] $r5
> ffma ftz $r1 $r1 c0[0x20] $r4
> -sched (st...
2017 Jun 05
0
[PATCH v2] nv110/exa: update sched codes
...0x0]
> fadd ftz $r3 $r5 c0[0x4]
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6) (st 0x6) (st 0xf)
> fadd ftz $r4 $r5 c0[0x8]
> fadd ftz $r5 $r5 c0[0xc]
> depbar le 0x5 0x0 0x0
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6 wt 0x2) (st 0x1) (st 0x1)
> ffma ftz $r3 $r0 c0[0x10] $r3
> ffma ftz $r4 $r0 c0[0x14] $r4
> ffma ftz $r5 $r0 c0[0x18] $r5
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x1) (st 0x1) (st 0x6)
> ffma ftz $r0 $r1 c0[0x1c] $r3
> ffma ftz $r2 $r1 c0[0x24] $r5
> ffma ftz $r1 $r1 c0[0x20] $r4
> -sched...
2017 Jun 08
1
[PATCH v2] nv110/exa: update sched codes
...+sched (st 0x6) (st 0x6) (st 0xf)
>> fadd ftz $r4 $r5 c0[0x8]
>> fadd ftz $r5 $r5 c0[0xc]
>> depbar le 0x5 0x0 0x0
>> -sched (st 0x0) (st 0x0) (st 0x0)
>> +sched (st 0x6 wt 0x2) (st 0x1) (st 0x1)
>> ffma ftz $r3 $r0 c0[0x10] $r3
>> ffma ftz $r4 $r0 c0[0x14] $r4
>> ffma ftz $r5 $r0 c0[0x18] $r5
>> -sched (st 0x0) (st 0x0) (st 0x0)
>> +sched (st 0x1) (st 0x1) (st 0x6)
>> ffma ftz $r0 $r1 c0[0x1c] $r3
>> ff...
2017 Jun 07
0
[PATCH v2] nv110/exa: update sched codes
...t 0x0) (st 0x0)
> +sched (st 0x6) (st 0x6) (st 0xf)
> fadd ftz $r4 $r5 c0[0x8]
> fadd ftz $r5 $r5 c0[0xc]
> depbar le 0x5 0x0 0x0
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x6 wt 0x2) (st 0x1) (st 0x1)
> ffma ftz $r3 $r0 c0[0x10] $r3
> ffma ftz $r4 $r0 c0[0x14] $r4
> ffma ftz $r5 $r0 c0[0x18] $r5
> -sched (st 0x0) (st 0x0) (st 0x0)
> +sched (st 0x1) (st 0x1) (st 0x6)
> ffma ftz $r0 $r1 c0[0x1c] $r3
> ffma ftz $r2 $r1 c0[0x24]...