llvm dev - Nov 2019 - Difference between clang -O1 -Xclang -disable-O0-optnone and clang -O0 -Xclang -disable-O0-optnone in LLVM 9

Hello,
I m trying to test individual O3 optimizations/ replicating O3 behavior on
IR. I took unoptimized IR (O0), used disable-o0-optnone via (*clang -O0
 -Xclang -disable-O0-optnone*). I read somewhere about *clang -O1  -Xclang
-disable-O0-optnone,* so I also tested on this initial IR.

I have observed by using individual optimizations, the performance (i.e
time) is better when the base/initial IR is generated via  *clang -O1
 -Xclang -disable-O0-optnone*. In case of *clang -O0  -Xclang
-disable-O0-optnone* initial IR, the performance is reduced.

What is the possible reason for this?

What is the right way?
Please guide.
Thank You
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20191113/9b4e1a44/attachment-0001.html>

Without actually trying it myself, I would say that the -O1 command line runs
optimization passes where the -O0 command line does not.  Thus, your “baseline”
IR is already somewhat optimized in the -O1 case.  If you want to see IR with no
optimizations run at all, you want to add `-Xclang -disable-llvm-passes` to your
command line for producing unoptimized IR.  I think this would produce the same
results for -O0 and -O1.
--paulr

From: llvm-dev <llvm-dev-bounces at lists.llvm.org> On Behalf Of hameeza
ahmed via llvm-dev
Sent: Wednesday, November 13, 2019 4:02 AM
To: llvm-dev <llvm-dev at lists.llvm.org>
Subject: [llvm-dev] Difference between clang -O1 -Xclang -disable-O0-optnone and
clang -O0 -Xclang -disable-O0-optnone in LLVM 9

Hello,
I m trying to test individual O3 optimizations/ replicating O3 behavior on IR. I
took unoptimized IR (O0), used disable-o0-optnone via (clang -O0  -Xclang
-disable-O0-optnone). I read somewhere about clang -O1  -Xclang
-disable-O0-optnone, so I also tested on this initial IR.

I have observed by using individual optimizations, the performance (i.e time) is
better when the base/initial IR is generated via  clang -O1  -Xclang
-disable-O0-optnone. In case of clang -O0  -Xclang -disable-O0-optnone initial
IR, the performance is reduced.

What is the possible reason for this?

What is the right way?
Please guide.
Thank You
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20191113/f7de2554/attachment.html>

On Wed, Nov 13, 2019 at 6:58 AM Robinson, Paul via llvm-dev <
llvm-dev at lists.llvm.org> wrote:
> Without actually trying it myself, I would say that the -O1 command line
> runs optimization passes where the -O0 command line does not.  Thus, your
> “baseline” IR is already somewhat optimized in the -O1 case.  If you want
> to see IR with no optimizations run at all, you want to add `-Xclang
> -disable-llvm-passes` to your command line for producing unoptimized IR.  I
> think this would produce the same results for -O0 and -O1.
>
Except then you'll get optnone on functions at -O0 (this is so that the -O0
in one compilation is respected in LTO situations where it may be merged
with another optimizing compilation)

While I don't think we have any guarantee that "clang <flags>
-Xclang
-disable-llvm-passes x.cpp -emit-llvm -o x.bc && clang <flags>
x.bc" (&
certainly not if the second step is opt, not clang) - it's certainly true
if you don't pass the same flags to both the first and second, you may get
different output (-O flags being the flagship here - it's not just the
optnone thing, but lifetime markers and other things in Clang's IRGen that
differ depending on optimization level).

> --paulr
>
>
>
> *From:* llvm-dev <llvm-dev-bounces at lists.llvm.org> *On Behalf Of
*hameeza
> ahmed via llvm-dev
> *Sent:* Wednesday, November 13, 2019 4:02 AM
> *To:* llvm-dev <llvm-dev at lists.llvm.org>
> *Subject:* [llvm-dev] Difference between clang -O1 -Xclang
> -disable-O0-optnone and clang -O0 -Xclang -disable-O0-optnone in LLVM 9
>
>
>
> Hello,
>
> I m trying to test individual O3 optimizations/ replicating O3 behavior on
> IR. I took unoptimized IR (O0), used disable-o0-optnone via (*clang -O0
>  -Xclang -disable-O0-optnone*). I read somewhere about *clang -O1
>  -Xclang -disable-O0-optnone,* so I also tested on this initial IR.
>
>
>
> I have observed by using individual optimizations, the performance (i.e
> time) is better when the base/initial IR is generated via  *clang -O1
>  -Xclang -disable-O0-optnone*. In case of *clang -O0  -Xclang
> -disable-O0-optnone* initial IR, the performance is reduced.
>
>
>
> What is the possible reason for this?
>
>
>
> What is the right way?
>
> Please guide.
>
> Thank You
> _______________________________________________
> LLVM Developers mailing list
> llvm-dev at lists.llvm.org
> https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20191113/4ab30239/attachment.html>