Displaying 20 results from an estimated 1568 matches for "lanes".
Did you mean:
lane
2017 Dec 20
2
[PATCH] gm107/ir: use lane 0 for manual textureGrad handling
This is parallel to the pre-SM50 change which does this. Adjusts the
shuffles / quadops to make the values correct relative to lane 0, and
then splat the results to all lanes for the final move into the target
register.
Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
Entirely untested beyond compilation. Should check
bin/tex-miplevel-selection textureGrad Cube
bin/tex-miplevel-selection textureGrad CubeShadow
bin/tex-miplevel-selection textureGrad Cube...
2017 Dec 20
0
[PATCH] gm107/ir: use lane 0 for manual textureGrad handling
On Tue, Dec 19, 2017 at 11:41 PM, Ilia Mirkin <imirkin at alum.mit.edu> wrote:
> This is parallel to the pre-SM50 change which does this. Adjusts the
> shuffles / quadops to make the values correct relative to lane 0, and
> then splat the results to all lanes for the final move into the target
> register.
>
> Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu>
> ---
>
> Entirely untested beyond compilation. Should check
>
> bin/tex-miplevel-selection textureGrad Cube
> bin/tex-miplevel-selection textureGrad CubeShadow
&...
2017 Sep 19
1
Describing subreg load for vectors without using vector_insert
Hi,
We are using a vector_insert in our target, to describe an instruction
performing a lane-load of a vector register as:
set $dstReg, (vector_insert $dstReg, (load $addr)), imm:$lane)
However, this means that the dstReg is also marked as used in the
instruction, which we do not want. We can do a direct lane-load to a part
of the vector register without disturbing the rest, and hence would
2020 Nov 06
2
Loop-vectorizer prototype for the EPI Project based on the RISC-V Vector Extension (Scalable vectors)
...s their targets. We can then concentrate on optimizing VP intrinsic code and all targets benefit.
- Simon
*: VE's packed mode (512 x 32bit elements) is a use case for a non-trivial setting of %mask and %evl at the same time (%evl for packs of two 32bit elements (ie %evl must be even for 32bit lanes), %mask for masking out inside packages).
Thoughts?
Kind regards,
--
Roger Ferrer Ibáñez
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20201106/72ccfa58/attachment-0001.html>
2013 Jun 19
1
[LLVMdev] Register coalescer and reg_sequence (virtual super-regs)
...s nice, but I don't think it'll work for me. I
have 8-element vector registers that can be grouped into virtual super regs
for bulk save/restore, and as soon as I have more than 4 in a tuple, the
unsigned int used to hold the lane masks overflows and switches over to the
"bit 31 set == lanes unresolvable" mode, and coalescing fails.
What about moving the lane masks to a BitVector, that wouldn't need to be
constrained artificially? Too much of a performance impact going that way?
I'd be open to any thoughts/suggestions. I studied the ARM
s_sub/d_sub/q_sub structure but th...
2014 Apr 16
16
[Bug 77529] New: NVS 510 DP-3 output doesn't work
https://bugs.freedesktop.org/show_bug.cgi?id=77529
Priority: medium
Bug ID: 77529
Assignee: nouveau at lists.freedesktop.org
Summary: NVS 510 DP-3 output doesn't work
QA Contact: xorg-team at lists.x.org
Severity: normal
Classification: Unclassified
OS: All
Reporter: tex at sergio.spb.ru
2012 Oct 18
13
[PATCH 00/10] extract dp helper functions
Hi all,
I've frustrated myself the last few days yelling at our link training code.
Comparing the i915 code to radeon and nouveau I've noticed the lack of a nice
set of dp helper functions. So I've started to extract a few.
There's lots more that we can do I think (link configuration selection, the i2c
over aux retry stuff which diverges already between i915 and radeon, maybe
2017 Oct 17
3
[RFC] Adding Intrinsics for Masked Vector Integer Division and Remainder
...;16 x i32> <b>, <16 x i1> <mask>, <16 x i32> <passthru>)
Overview:
Returns the quotient of its two operands per vector lane according to the provided mask. The mask holds a bit for each vector lane, and is used to prevent division in the masked-off lanes. The masked-off lanes in the result vector are taken from the corresponding lanes of the passthru operand.
Arguments:
The first two arguments must be vectors of integer values. Both arguments must have identical types. The third operand, mask, is a vector of boolean values with th...
2020 Nov 06
4
Loop-vectorizer prototype for the EPI Project based on the RISC-V Vector Extension (Scalable vectors)
...s their targets. We can then concentrate on optimizing VP intrinsic code and all targets benefit.
- Simon
*: VE's packed mode (512 x 32bit elements) is a use case for a non-trivial setting of %mask and %evl at the same time (%evl for packs of two 32bit elements (ie %evl must be even for 32bit lanes), %mask for masking out inside packages).
Thoughts?
Kind regards,
--
Roger Ferrer Ibáñez
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20201106/72f6e006/attachment-0001.html>
2013 May 16
1
[LLVMdev] Combining physical registers
...context here is an attempt to coalesce multiple loads/stores into fewer loads/stores using larger registers.
At the moment, there is no way of determining this, but I have a patch.
> It is my understanding that register lane masks are not exact in a sense that they will tell me if two register lanes alias, but not necessarily if a set of masks adds up to a full register. Is this correct?
That’s right.
Would this TRI function solve your problem?
/// The lane masks returned by getSubRegIndexLaneMask() above can only be
/// used to determine if sub-registers overlap - they can't be us...
2013 Aug 01
32
[Bug 67628] New: [BISECTED] Monitor on Display port shows distortions
https://bugs.freedesktop.org/show_bug.cgi?id=67628
Priority: medium
Bug ID: 67628
Assignee: nouveau at lists.freedesktop.org
Summary: [BISECTED] Monitor on Display port shows distortions
QA Contact: xorg-team at lists.x.org
Severity: major
Classification: Unclassified
OS: Linux (All)
Reporter:
2020 Nov 09
0
Loop-vectorizer prototype for the EPI Project based on the RISC-V Vector Extension (Scalable vectors)
...s their targets. We can then concentrate on optimizing VP intrinsic code and all targets benefit.
- Simon
*: VE's packed mode (512 x 32bit elements) is a use case for a non-trivial setting of %mask and %evl at the same time (%evl for packs of two 32bit elements (ie %evl must be even for 32bit lanes), %mask for masking out inside packages).
Thoughts?
Kind regards,
--
Roger Ferrer Ibáñez
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20201109/cb4c9986/attachment.html>
2016 Oct 03
5
Is this undefined behavior optimization legal?
...undefined behavior and the program would be broken.
This assumption is what causes it to remove the 'and' operation.
So effectively, what has happened here, is that by inserting the result of
an operation with undefined behavior into one lane of a vector, we have
overwritten all the other lanes of the vector.
Is this optimization legal? To me it seems wrong that undefined behavior
in one lane of a vector could affect another lane. However, given that LLVM IR
is SSA and we are technically creating a new vector and not modifying the old
one, then maybe it's OK. I'm just not sure...
2013 May 16
2
[LLVMdev] Combining physical registers
...le, on X86, AL and AH together form AX. On Hexagon, R0 and R1
are D0.
The context here is an attempt to coalesce multiple loads/stores into
fewer loads/stores using larger registers.
It is my understanding that register lane masks are not exact in a sense
that they will tell me if two register lanes alias, but not necessarily
if a set of masks adds up to a full register. Is this correct?
-Krzysztof
--
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
hosted by The Linux Foundation
2017 Jun 12
4
Implementing cross-thread reduction in the AMDGPU backend
...ean that we'd have a
separate intrinsic for every operation we care about, but I can't
think of a better way to express it. Is there a better way that
doesn't involve creating an intrinsic for each operation?
Next, there's the fact that this code sequence only works when the
active lanes are densely-packed, but we have to make this work even
when control flow is non-uniform. Essentially, we need to "skip over"
the inactive lanes by setting them to the identity, and then we need
to enable them in the exec mask when doing the reduction to make sure
they pass along the corre...
2020 Nov 06
0
Loop-vectorizer prototype for the EPI Project based on the RISC-V Vector Extension (Scalable vectors)
...s their targets. We can then concentrate on optimizing VP intrinsic code and all targets benefit.
- Simon
*: VE's packed mode (512 x 32bit elements) is a use case for a non-trivial setting of %mask and %evl at the same time (%evl for packs of two 32bit elements (ie %evl must be even for 32bit lanes), %mask for masking out inside packages).
Thoughts?
Kind regards,
--
Roger Ferrer Ibáñez
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20201106/24e204b1/attachment.html>
2018 Jan 28
1
semPLS package will not load seems to be failing on loading package lattice
Hi R Help Team
I recently updated my R installation to R 3.4.3 and updated to later version of R Studio and I found that the package semPLS will not load even though installed and it seems to be failing on loading package lattice
Getting the following error message:
library(semPLS)
Loading required package: lattice
Error: package or namespace load failed for 'lattice':
.onLoad failed in
2009 Oct 08
1
xyplot#strips like ggplot?
Dear all,
I want to split the strips in xyplot and push them into the margins ...
Tried to find this in common documentation (such as Deepayan's book) on
lattice ... but so far without success ...
Here is the situation:
xyplot(Speed~Count|Lane*Day,...)
where Speed and Count are numeric, Lane and Day are factors.
By default, this makes a double strip on top of each graph. I can change
2017 Jun 12
2
Implementing cross-thread reduction in the AMDGPU backend
...for every operation we care about, but I can't
>> think of a better way to express it. Is there a better way that
>> doesn't involve creating an intrinsic for each operation?
>>
>> Next, there's the fact that this code sequence only works when the
>> active lanes are densely-packed, but we have to make this work even
>> when control flow is non-uniform. Essentially, we need to "skip over"
>> the inactive lanes by setting them to the identity, and then we need
>> to enable them in the exec mask when doing the reduction to make sur...
2016 Sep 18
4
Addressing TableGen's error "Ran out of lanemask bits" in order to use more than 32 subregisters per register
...pe int1024_t from the boost
> library, header cpp_int.hpp) for LaneMask and change accordingly the
> methods handing the type.
> >
> > Is there are any limitation I am not aware of (maybe in LLVMV's
> register allocator) that would prevent me from using more than 32
> lanes/subregisters?
>
> There is no known limitation. I chose uint32_t out of concern for
> compiletime. Going up for uint64_t should be no problem, I'd be more
> concerned about bigger types; hopefully all code properly uses the
> LaneBitmask type instead of plain unsigned, you may ne...