US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation

classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|

US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation

Kristof Beyls via cfe-dev
Dear all,

I would like announce a round table planned for the upcoming LLVM Dev meeting next week that will cover various topics related to the use of LLVM in the compiler stacks for the GPUs.

Here is the initial list of discussion topics:
 - Canonicalization vs. GPUs: Type mutation;
 - Control flow mutation (graphics shaders are more sensitive to this);
 - Divergence/reconvergence sensitivity;
 - Address-space awareness;

The round table is preliminary planned for Tue 3-4pm or Wed 2-3pm. The exact slot will be listed in the online schedule soon: https://llvmdevmtg2019.sched.com/

Feel free to let us know of any other topics you would like to cover.

Kind regards,
Anastasia


_______________________________________________
cfe-dev mailing list
[hidden email]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-dev
Reply | Threaded
Open this post in threaded view
|

Re: US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation

Kristof Beyls via cfe-dev
Dear all,

Could I suggest adding one more topic to the list related to GPUs? We have just published a prototype for a LLVM backend generating SPIR-V at https://github.com/KhronosGroup/LLVM-SPIRV-Backend. While I won't be present at the round table, inputs from the LLVM community on how to upstream this backend to LLVM would be greatly appreciated.

Thank you.


Kind regards,
Marco


From: llvm-dev <[hidden email]> on behalf of Anastasia Stulova via llvm-dev <[hidden email]>
Sent: 18 October 2019 01:00
To: clang developer list <[hidden email]>; Simone Atzeni via llvm-dev <[hidden email]>
Cc: David Neto <[hidden email]>; nd <[hidden email]>; Diego Novillo <[hidden email]>
Subject: [llvm-dev] US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation
 
Dear all,

I would like announce a round table planned for the upcoming LLVM Dev meeting next week that will cover various topics related to the use of LLVM in the compiler stacks for the GPUs.

Here is the initial list of discussion topics:
 - Canonicalization vs. GPUs: Type mutation;
 - Control flow mutation (graphics shaders are more sensitive to this);
 - Divergence/reconvergence sensitivity;
 - Address-space awareness;

The round table is preliminary planned for Tue 3-4pm or Wed 2-3pm. The exact slot will be listed in the online schedule soon: https://llvmdevmtg2019.sched.com/

Feel free to let us know of any other topics you would like to cover.

Kind regards,
Anastasia


_______________________________________________
cfe-dev mailing list
[hidden email]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-dev
Reply | Threaded
Open this post in threaded view
|

Re: US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation

Kristof Beyls via cfe-dev
Thanks, Marco! If there is enough interest in this topic we can also organize a separate round table for this discussion.

Cheers,
Anastasia

From: Marco Antognini <[hidden email]>
Sent: 18 October 2019 14:42
To: Anastasia Stulova <[hidden email]>; Simone Atzeni via llvm-dev <[hidden email]>; clang developer list <[hidden email]>
Cc: David Neto <[hidden email]>; nd <[hidden email]>; Diego Novillo <[hidden email]>
Subject: Re: US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation
 
Dear all,

Could I suggest adding one more topic to the list related to GPUs? We have just published a prototype for a LLVM backend generating SPIR-V at https://github.com/KhronosGroup/LLVM-SPIRV-Backend. While I won't be present at the round table, inputs from the LLVM community on how to upstream this backend to LLVM would be greatly appreciated.

Thank you.


Kind regards,
Marco


From: llvm-dev <[hidden email]> on behalf of Anastasia Stulova via llvm-dev <[hidden email]>
Sent: 18 October 2019 01:00
To: clang developer list <[hidden email]>; Simone Atzeni via llvm-dev <[hidden email]>
Cc: David Neto <[hidden email]>; nd <[hidden email]>; Diego Novillo <[hidden email]>
Subject: [llvm-dev] US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation
 
Dear all,

I would like announce a round table planned for the upcoming LLVM Dev meeting next week that will cover various topics related to the use of LLVM in the compiler stacks for the GPUs.

Here is the initial list of discussion topics:
 - Canonicalization vs. GPUs: Type mutation;
 - Control flow mutation (graphics shaders are more sensitive to this);
 - Divergence/reconvergence sensitivity;
 - Address-space awareness;

The round table is preliminary planned for Tue 3-4pm or Wed 2-3pm. The exact slot will be listed in the online schedule soon: https://llvmdevmtg2019.sched.com/

Feel free to let us know of any other topics you would like to cover.

Kind regards,
Anastasia


_______________________________________________
cfe-dev mailing list
[hidden email]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-dev
Reply | Threaded
Open this post in threaded view
|

Re: US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation

Kristof Beyls via cfe-dev
+1 
I'm very interested.

On Sat, 19 Oct 2019, 05:15 Anastasia Stulova via cfe-dev, <[hidden email]> wrote:
Thanks, Marco! If there is enough interest in this topic we can also organize a separate round table for this discussion.

Cheers,
Anastasia

From: Marco Antognini <[hidden email]>
Sent: 18 October 2019 14:42
To: Anastasia Stulova <[hidden email]>; Simone Atzeni via llvm-dev <[hidden email]>; clang developer list <[hidden email]>
Cc: David Neto <[hidden email]>; nd <[hidden email]>; Diego Novillo <[hidden email]>
Subject: Re: US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation
 
Dear all,

Could I suggest adding one more topic to the list related to GPUs? We have just published a prototype for a LLVM backend generating SPIR-V at https://github.com/KhronosGroup/LLVM-SPIRV-Backend. While I won't be present at the round table, inputs from the LLVM community on how to upstream this backend to LLVM would be greatly appreciated.

Thank you.


Kind regards,
Marco


From: llvm-dev <[hidden email]> on behalf of Anastasia Stulova via llvm-dev <[hidden email]>
Sent: 18 October 2019 01:00
To: clang developer list <[hidden email]>; Simone Atzeni via llvm-dev <[hidden email]>
Cc: David Neto <[hidden email]>; nd <[hidden email]>; Diego Novillo <[hidden email]>
Subject: [llvm-dev] US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation
 
Dear all,

I would like announce a round table planned for the upcoming LLVM Dev meeting next week that will cover various topics related to the use of LLVM in the compiler stacks for the GPUs.

Here is the initial list of discussion topics:
 - Canonicalization vs. GPUs: Type mutation;
 - Control flow mutation (graphics shaders are more sensitive to this);
 - Divergence/reconvergence sensitivity;
 - Address-space awareness;

The round table is preliminary planned for Tue 3-4pm or Wed 2-3pm. The exact slot will be listed in the online schedule soon: https://llvmdevmtg2019.sched.com/

Feel free to let us know of any other topics you would like to cover.

Kind regards,
Anastasia

_______________________________________________
cfe-dev mailing list
[hidden email]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-dev

_______________________________________________
cfe-dev mailing list
[hidden email]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-dev
Reply | Threaded
Open this post in threaded view
|

Re: US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation

Kristof Beyls via cfe-dev
Hi all,

The round table slot is now confirmed for Tue 3.10pm: https://llvmdevmtg2019.sched.com/event/WFbV

Cheers,
Anastasia


From: Praveen Velliengiri <[hidden email]>
Sent: 19 October 2019 08:00
To: Anastasia Stulova <[hidden email]>
Cc: Marco Antognini <[hidden email]>; llvm-dev <[hidden email]>; clang developer list <[hidden email]>; David Neto <[hidden email]>; nd <[hidden email]>; Diego Novillo <[hidden email]>
Subject: Re: [cfe-dev] US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation
 
+1 
I'm very interested.

On Sat, 19 Oct 2019, 05:15 Anastasia Stulova via cfe-dev, <[hidden email]> wrote:
Thanks, Marco! If there is enough interest in this topic we can also organize a separate round table for this discussion.

Cheers,
Anastasia

From: Marco Antognini <[hidden email]>
Sent: 18 October 2019 14:42
To: Anastasia Stulova <[hidden email]>; Simone Atzeni via llvm-dev <[hidden email]>; clang developer list <[hidden email]>
Cc: David Neto <[hidden email]>; nd <[hidden email]>; Diego Novillo <[hidden email]>
Subject: Re: US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation
 
Dear all,

Could I suggest adding one more topic to the list related to GPUs? We have just published a prototype for a LLVM backend generating SPIR-V at https://github.com/KhronosGroup/LLVM-SPIRV-Backend. While I won't be present at the round table, inputs from the LLVM community on how to upstream this backend to LLVM would be greatly appreciated.

Thank you.


Kind regards,
Marco


From: llvm-dev <[hidden email]> on behalf of Anastasia Stulova via llvm-dev <[hidden email]>
Sent: 18 October 2019 01:00
To: clang developer list <[hidden email]>; Simone Atzeni via llvm-dev <[hidden email]>
Cc: David Neto <[hidden email]>; nd <[hidden email]>; Diego Novillo <[hidden email]>
Subject: [llvm-dev] US LLVM Dev Meeting 2019 - Round Table - Challenges using LLVM for GPU compilation
 
Dear all,

I would like announce a round table planned for the upcoming LLVM Dev meeting next week that will cover various topics related to the use of LLVM in the compiler stacks for the GPUs.

Here is the initial list of discussion topics:
 - Canonicalization vs. GPUs: Type mutation;
 - Control flow mutation (graphics shaders are more sensitive to this);
 - Divergence/reconvergence sensitivity;
 - Address-space awareness;

The round table is preliminary planned for Tue 3-4pm or Wed 2-3pm. The exact slot will be listed in the online schedule soon: https://llvmdevmtg2019.sched.com/

Feel free to let us know of any other topics you would like to cover.

Kind regards,
Anastasia

_______________________________________________
cfe-dev mailing list
[hidden email]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-dev

_______________________________________________
cfe-dev mailing list
[hidden email]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-dev