<div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On Thu, May 21, 2015 at 8:03 AM, Mehdi Amini <span dir="ltr"><<a href="mailto:mehdi.amini@apple.com" target="_blank">mehdi.amini@apple.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word"><br><div><span class=""><blockquote type="cite"><div>On May 20, 2015, at 7:13 AM, Neil Henning <<a href="mailto:llvm@duskborn.com" target="_blank">llvm@duskborn.com</a>> wrote:</div><br><div>
<div text="#000000" bgcolor="#FFFFFF">
On 20/05/15 08:37, Owen Anderson wrote:<br>
<blockquote type="cite">
<br>
<div>
<blockquote type="cite">
<div>On May 19, 2015, at 7:32 PM, Sean Silva <<a href="mailto:chisophugis@gmail.com" target="_blank">chisophugis@gmail.com</a>> wrote:</div>
<br>
<div>
<div dir="ltr"><br>
<div class="gmail_extra"><br>
<div class="gmail_quote">On Tue, May 19, 2015 at 4:05
PM, Owen Anderson <span dir="ltr"><<a href="mailto:resistor@mac.com" target="_blank">resistor@mac.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div style="word-wrap:break-word"><span><br>
<div>
<blockquote type="cite">
<div>On May 19, 2015, at 9:48 AM,
Neil Henning <<a href="mailto:llvm@duskborn.com" target="_blank">llvm@duskborn.com</a>>
wrote:</div>
<br>
<div><span style="font-family:Helvetica;font-size:12px;font-style:normal;font-variant:normal;font-weight:normal;letter-spacing:normal;line-height:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;float:none;display:inline!important">The 'backend' in this context
is purely so that we can then enable
Clang to target SPIR-V in the same
consistent manner to all the other
targets it supports.</span><br style="font-family:Helvetica;font-size:12px;font-style:normal;font-variant:normal;font-weight:normal;letter-spacing:normal;line-height:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px">
</div>
</blockquote>
</div>
<br>
</span>
<div>This seems like a terrible reason to
choose the architecture of how it’s implemented
in LLVM. The clang driver is part of the LLVM
project. If we need to add support for some
kind of special SPIR-V flag akin to -emit-llvm,
we can do that. If a particular frontend vendor
wants to customize the flags, they can always do
so themselves.</div>
</div>
</blockquote>
<div><br>
</div>
<div>What do you envision as the triple and
datalayout when a frontend is compiling to SPIR-V?</div>
</div>
</div>
</div>
</div>
</blockquote>
<div><br>
</div>
<div>I’d recommend having its own Triple. Not that triples are
*not* linked to targets in LLVM. My understanding of SPIR-V
(and a look through the documentation seems to confirm) that
it doesn’t specify anything about data layouts, presumably
because it needs to accommodate both many GPUs with varying
ideas of what sizes and alignments should be. If anything
this pushes me even more strongly that you do *not* want to
run SPIR-V-destined IR through any more of LLVM (and
particularly the CodeGen infrastructure) than you have to,
since a lot of that will want to bake in DataLayout knowledge.</div>
</div>
</blockquote>
<br>
At present in SPIR-V we have a decoration for alignment, so a user
could decorate a type to specify a required alignment (which I would
have thought in turn would become part of the data layout). Also if
we are using a non-logical addressing mode the data layout would
have a different pointer width specified (similar to the SPIR/SPIR64
targets in Clang at present). I'll bring it up with the SPIR group
at Khronos what the expected behaviour of the alignment decoration
is in this context, but at present I would say it would be legal for
an LLVM module that is being turned into SPIR-V to have a
user-defined data layout.<br></div></div></blockquote><div><br></div></span><div>Are we supposed to be able to optimize this IR? I mean is a valid use-case: frontend->IR-(optimizer)->IR->SPIRV?</div></div></div></blockquote><div><br></div><div>I would hope that we would run at least mem2reg/sroa, do those need data layout?</div><div><br></div><div>-- Sean Silva</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word"><div><div>I think it has been acknowledged that the optimizer need to be aware of the data layout, and that optimizations/transformations that are performed on one data layout are not necessarily valid with another one.</div><div><br></div><div>If there is not a single blessed data layout for SPIR-V in the spec, and the front-end can chose one, it seems to me that it has to be “serialized” in SPIR-V as well, isn’t it?</div><div>The round-trip SPIR-V -> IR -> SPIR-V does not sound as usuful as it could be if the data layout is not specified.</div><div><br></div><div>— </div><span class="HOEnZb"><font color="#888888"><div>Mehdi</div><div><br></div><div><br></div><div><br></div><br></font></span><blockquote type="cite"><div><span class=""><div text="#000000" bgcolor="#FFFFFF">
<br>
<blockquote type="cite">
<div>
<blockquote type="cite">
<div>
<div dir="ltr">
<div class="gmail_extra">
<div class="gmail_quote">
<div>I'm pretty sure that a wide class of
frontends for SPIR-V will literally be interested in
just generating SPIR-V, with no knowledge about what
the ultimate GPU target is; it is in that sense that
they are "targeting" SPIR-V. That is, their frontend
isn't generating $SPECIFICGPU targeted IR, and then
being merely asking to have it serialized in a
specific way (a la -emit-llvm); they are generating
IR that is meant to be turned into SPIR-V. That is
fundamentally different from -emit-llvm (on the
other hand, it may not be a target; but it sure
smells like one).</div>
</div>
</div>
</div>
</div>
</blockquote>
<div><br>
</div>
I completely agree with you… except for the last sentence.</div>
<div><br>
</div>
<div>Honestly, the command line option aspect of this seems like a
complete red herring to me. We are talking about adding support
to a data format which we will need to support both serializing
IR to and deserializing IR from. This is exactly the same as
the bitcode use case, and not at all like the use case of a
target. We should structure the implementation according to the
ways it will actually be used; rewiring a clang driver command
line flag to “make it look pretty” is the most trivial part of
the entire process.</div>
</blockquote>
<br>
So it seems to me that we can at least agree on the location of the
mainstay of the code - it should reside in lib/SPIRV and be both a
reader and writer akin to the Bitcode reader/writer pair. Why don't
we at Khronos work on a patch to tip LLVM that will do that, and
then we can revisit how a user actually uses our code after that. We
should be able to easily follow Owen's approach and see how that
works out, worst case if it turns out to not work it would then be
trivial to turn that into a thin backend. Seem reasonable?<br>
<br>
Cheers,<br>
-Neil.<br>
</div></span><span class="">
_______________________________________________<br>LLVM Developers mailing list<br><a href="mailto:LLVMdev@cs.uiuc.edu" target="_blank">LLVMdev@cs.uiuc.edu</a> <a href="http://llvm.cs.uiuc.edu" target="_blank">http://llvm.cs.uiuc.edu</a><br><a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev" target="_blank">http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev</a><br></span></div></blockquote></div><br></div></blockquote></div><br></div></div>