Displaying 15 results from an estimated 15 matches for "rglobal".
Did you mean:
global
2015 Dec 22
0
Translating tests/trivial/compute.c gallium tests to opencl (input / help wanted)
...quot;
" UMUL TEMP[0].x, TEMP[0], IMM[0]\n"
- " STORE RES[0].xyzw, TEMP[0], SV[0]\n"
+ " LOAD TEMP[1].x, RINPUT, IMM[2]\n"
+ " UADD TEMP[0].x, TEMP[0], TEMP[1]\n"
+ " STORE RGLOBAL.xyzw, TEMP[0], SV[0]\n"
" UADD TEMP[0].x, TEMP[0], IMM[1]\n"
- " STORE RES[0].xyzw, TEMP[0], SV[1]\n"
+ " STORE RGLOBAL.xyzw, TEMP[0], SV[1]\n"
" UADD TEMP[0].x, TEMP[0], IMM[1]\n"
-...
2016 Feb 22
2
Dealing with opencl kernel parameters in nouveau now that RES support is gone
...;> COMP
>> DCL SV[0], THREAD_ID[0]
>> DCL TEMP[0], LOCAL
>> DCL TEMP[1], LOCAL
>> IMM UINT32 { 8, 0, 0, 0 }
>>
>> BGNSUB\n"
>> UMUL TEMP[0], SV[0], IMM[0]
>> LOAD TEMP[1].xy, RINPUT, TEMP[0]
>> LOAD TEMP[0].x, RGLOBAL, TEMP[1].yyyy
>> UADD TEMP[1].x, TEMP[0], -TEMP[1]
>> STORE RGLOBAL.x, TEMP[1].yyyy, TEMP[1]
>> RET
>> ENDSUB
>>
>>
>> Where by RINPUT and RGLOBAL get replaces by processing the
>> code with cpp and the following defines:
&...
2016 Feb 22
4
Dealing with opencl kernel parameters in nouveau now that RES support is gone
...TEMP[0], LOCAL
>>>> DCL TEMP[1], LOCAL
>>>> IMM UINT32 { 8, 0, 0, 0 }
>>>>
>>>> BGNSUB\n"
>>>> UMUL TEMP[0], SV[0], IMM[0]
>>>> LOAD TEMP[1].xy, RINPUT, TEMP[0]
>>>> LOAD TEMP[0].x, RGLOBAL, TEMP[1].yyyy
>>>> UADD TEMP[1].x, TEMP[0], -TEMP[1]
>>>> STORE RGLOBAL.x, TEMP[1].yyyy, TEMP[1]
>>>> RET
>>>> ENDSUB
>>>>
>>>>
>>>> Where by RINPUT and RGLOBAL get replaces by processing...
2016 Feb 22
2
Dealing with opencl kernel parameters in nouveau now that RES support is gone
...again.
Currently the test_input_global() test uses the following bit of
TGSI code:
COMP
DCL SV[0], THREAD_ID[0]
DCL TEMP[0], LOCAL
DCL TEMP[1], LOCAL
IMM UINT32 { 8, 0, 0, 0 }
BGNSUB\n"
UMUL TEMP[0], SV[0], IMM[0]
LOAD TEMP[1].xy, RINPUT, TEMP[0]
LOAD TEMP[0].x, RGLOBAL, TEMP[1].yyyy
UADD TEMP[1].x, TEMP[0], -TEMP[1]
STORE RGLOBAL.x, TEMP[1].yyyy, TEMP[1]
RET
ENDSUB
Where by RINPUT and RGLOBAL get replaces by processing the
code with cpp and the following defines:
#define RGLOBAL RES[32767]
#define RLOCAL RES[32766]
#d...
2016 Feb 22
0
Dealing with opencl kernel parameters in nouveau now that RES support is gone
...>> DCL TEMP[1], LOCAL
>>>>> IMM UINT32 { 8, 0, 0, 0 }
>>>>>
>>>>> BGNSUB\n"
>>>>> UMUL TEMP[0], SV[0], IMM[0]
>>>>> LOAD TEMP[1].xy, RINPUT, TEMP[0]
>>>>> LOAD TEMP[0].x, RGLOBAL, TEMP[1].yyyy
>>>>> UADD TEMP[1].x, TEMP[0], -TEMP[1]
>>>>> STORE RGLOBAL.x, TEMP[1].yyyy, TEMP[1]
>>>>> RET
>>>>> ENDSUB
>>>>>
>>>>>
>>>>> Where by RINPUT and RGLOBA...
2016 Feb 22
0
Dealing with opencl kernel parameters in nouveau now that RES support is gone
...>> DCL TEMP[1], LOCAL
>>>>> IMM UINT32 { 8, 0, 0, 0 }
>>>>>
>>>>> BGNSUB\n"
>>>>> UMUL TEMP[0], SV[0], IMM[0]
>>>>> LOAD TEMP[1].xy, RINPUT, TEMP[0]
>>>>> LOAD TEMP[0].x, RGLOBAL, TEMP[1].yyyy
>>>>> UADD TEMP[1].x, TEMP[0], -TEMP[1]
>>>>> STORE RGLOBAL.x, TEMP[1].yyyy, TEMP[1]
>>>>> RET
>>>>> ENDSUB
>>>>>
>>>>>
>>>>> Where by RINPUT and RGLOBA...
2016 Feb 22
0
Dealing with opencl kernel parameters in nouveau now that RES support is gone
...HREAD_ID[0]
>>> DCL TEMP[0], LOCAL
>>> DCL TEMP[1], LOCAL
>>> IMM UINT32 { 8, 0, 0, 0 }
>>>
>>> BGNSUB\n"
>>> UMUL TEMP[0], SV[0], IMM[0]
>>> LOAD TEMP[1].xy, RINPUT, TEMP[0]
>>> LOAD TEMP[0].x, RGLOBAL, TEMP[1].yyyy
>>> UADD TEMP[1].x, TEMP[0], -TEMP[1]
>>> STORE RGLOBAL.x, TEMP[1].yyyy, TEMP[1]
>>> RET
>>> ENDSUB
>>>
>>>
>>> Where by RINPUT and RGLOBAL get replaces by processing the
>>> code with...
2016 Jan 11
4
Some llvm questions (for tgsi backend)
...0, 0, 0 }
IMM UINT32 { 4, 0, 0, 0 }
IMM UINT32 { 128, 0, 0, 0 }
BGNSUB
LOAD TEMP[0].xy, RINPUT, IMM[0]
UMUL TEMP[1].x, SV[0], IMM[1]
UADD TEMP[0].x, TEMP[0], TEMP[1]
UMUL TEMP[1].x, SV[0], IMM[2]
UADD TEMP[0].y, TEMP[0], TEMP[1].xxxx
LOAD TEMP[1].x, RGLOBAL, TEMP[0]
LOAD TEMP[0].x, RGLOBAL, TEMP[0].yyyy
UADD TEMP[1].x, TEMP[0], -TEMP[1]
STORE RGLOBAL.x, TEMP[0].yyyy, TEMP[1]
RET
ENDSUB;
So my questions (I'm still quite green when it comes to llvm):
1) As you can see a proper tgsi program needs a header
to declare...
2016 Jan 12
1
Some llvm questions (for tgsi backend)
...t;
>> BGNSUB
>> LOAD TEMP[0].xy, RINPUT, IMM[0]
>> UMUL TEMP[1].x, SV[0], IMM[1]
>> UADD TEMP[0].x, TEMP[0], TEMP[1]
>> UMUL TEMP[1].x, SV[0], IMM[2]
>> UADD TEMP[0].y, TEMP[0], TEMP[1].xxxx
>> LOAD TEMP[1].x, RGLOBAL, TEMP[0]
>> LOAD TEMP[0].x, RGLOBAL, TEMP[0].yyyy
>> UADD TEMP[1].x, TEMP[0], -TEMP[1]
>> STORE RGLOBAL.x, TEMP[0].yyyy, TEMP[1]
>> RET
>> ENDSUB;
>>
>> So my questions (I'm still quite green when it comes to llvm):
>&...
2016 Feb 22
0
Dealing with opencl kernel parameters in nouveau now that RES support is gone
...ollowing bit of
> TGSI code:
>
> COMP
> DCL SV[0], THREAD_ID[0]
> DCL TEMP[0], LOCAL
> DCL TEMP[1], LOCAL
> IMM UINT32 { 8, 0, 0, 0 }
>
> BGNSUB\n"
> UMUL TEMP[0], SV[0], IMM[0]
> LOAD TEMP[1].xy, RINPUT, TEMP[0]
> LOAD TEMP[0].x, RGLOBAL, TEMP[1].yyyy
> UADD TEMP[1].x, TEMP[0], -TEMP[1]
> STORE RGLOBAL.x, TEMP[1].yyyy, TEMP[1]
> RET
> ENDSUB
>
>
> Where by RINPUT and RGLOBAL get replaces by processing the
> code with cpp and the following defines:
>
> #define RGLOBAL...
2016 Jan 11
0
Some llvm questions (for tgsi backend)
...gt; IMM UINT32 { 128, 0, 0, 0 }
>
> BGNSUB
> LOAD TEMP[0].xy, RINPUT, IMM[0]
> UMUL TEMP[1].x, SV[0], IMM[1]
> UADD TEMP[0].x, TEMP[0], TEMP[1]
> UMUL TEMP[1].x, SV[0], IMM[2]
> UADD TEMP[0].y, TEMP[0], TEMP[1].xxxx
> LOAD TEMP[1].x, RGLOBAL, TEMP[0]
> LOAD TEMP[0].x, RGLOBAL, TEMP[0].yyyy
> UADD TEMP[1].x, TEMP[0], -TEMP[1]
> STORE RGLOBAL.x, TEMP[0].yyyy, TEMP[1]
> RET
> ENDSUB;
>
> So my questions (I'm still quite green when it comes to llvm):
>
> 1) As you can see a proper...
2016 Jan 11
0
Some llvm questions (for tgsi backend)
...t; IMM UINT32 { 128, 0, 0, 0 }
>
> BGNSUB
> LOAD TEMP[0].xy, RINPUT, IMM[0]
> UMUL TEMP[1].x, SV[0], IMM[1]
> UADD TEMP[0].x, TEMP[0], TEMP[1]
> UMUL TEMP[1].x, SV[0], IMM[2]
> UADD TEMP[0].y, TEMP[0], TEMP[1].xxxx
> LOAD TEMP[1].x, RGLOBAL, TEMP[0]
> LOAD TEMP[0].x, RGLOBAL, TEMP[0].yyyy
> UADD TEMP[1].x, TEMP[0], -TEMP[1]
> STORE RGLOBAL.x, TEMP[0].yyyy, TEMP[1]
> RET
> ENDSUB;
>
> So my questions (I'm still quite green when it comes to llvm):
>
> 1) As you can see a prope...
2016 Feb 19
2
Dealing with opencl kernel parameters in nouveau now that RES support is gone
Hi,
On 18-02-16 17:39, Ilia Mirkin wrote:
> On Thu, Feb 18, 2016 at 9:45 AM, Hans de Goede <hdegoede at redhat.com> wrote:
>> But this does not seem to be hooked up yet for nouveau.
>
> Samuel has patches. See
> https://cgit.freedesktop.org/~hakzsam/mesa/log/?h=arb_compute_shader_v3
Cool, I will take a look at those.
>> So some questions:
>> -The commit by
2014 Jan 28
3
[LLVMdev] MergeFunctions: reduce complexity to O(log(N))
Hi Stepan,
Sorry for the delay. It's great that you are working on MergeFunctions
as well and I agree, we should definitely try to combine our efforts to
improve MergeFunctions.
Just to give you some context, the pass (with the similar function
merging patch) is already being used in a production setting. From my
point of view, it would be better if we focus on improving its
capability
2014 Jan 30
3
[LLVMdev] MergeFunctions: reduce complexity to O(log(N))
...0 0.01 15211
rem.ll 2 86540 0 0.01 86517 0 0.01 86517
renaming.ll 96 315158 5 0.03 313834 0 0.03 302813
reservoir.ll 4 16376 0 0.01 16345 0 0.01 16345
resolution.ll 24 37915 0 0.01 37898 0 0.01 37898
resolve.ll 2 31249 0 0.01 31218 0 0.01 31218
reversefile.ll 117 191493 10 0.02 190376 6 0.02 191097
rglobals.ll 0 2330 0 0.01 2297 0 0.01 2297
richards_benchmark.ll 15 42180 0 0.01 42165 0 0.01 42165
rk.ll 387 1950440 103 0.17 1871681 * * *
rmain.ll 1 44611 0 0.01 44578 0 0.01 44578
rmatmult3.ll 1 44876 0 0.01 44849 0 0.01 44849
rna.ll 7 143455 0 0.02 143440 0 0.02 134851
roadlet.ll 10 18018 0 0.01 17989...