vikramRH wrote:
Two different patch sets have been created here,
https://github.com/llvm/llvm-project/pull/72554
https://github.com/llvm/llvm-project/pull/72556
https://github.com/llvm/llvm-project/pull/70932
___
cfe-commits mailing list
b-sumner wrote:
@vikramRH I thought the plan was that the default would switch to hostcall, but
that the OpenCL runtime would override it if it detected that the target
doesn't support hostcall / PCIe.
https://github.com/llvm/llvm-project/pull/70932
https://github.com/vikramRH updated
https://github.com/llvm/llvm-project/pull/70932
>From 4c0467078b2f38e814569ad351f86129d1c1d5ee Mon Sep 17 00:00:00 2001
From: Vikram
Date: Wed, 4 Oct 2023 05:41:47 -0400
Subject: [PATCH] [WIP][AMDGPU] hostcall printf support for OpenCL
---
vikramRH wrote:
@arsenm, The choice of defaults is based on current state of printf. HIP uses
hostcalls and OpenCL uses buffered variant by default. However I'm willing to
make one of the two variants consistent (preferably hostcalls for me). Do note
that this would make all OpenCL printf to
arsenm wrote:
For point 1, I would prefer to decouple the printf implementation choice from
the language. I would expect consistent defaults regardless of the language.
This also contradicts point 2? I thought the clang emitted path used hostcall,
and the backend path did not.
As for
https://github.com/vikramRH created
https://github.com/llvm/llvm-project/pull/70932
Attempt to enable OpenCL hostcall printf (SWDEV-204804). I would like to have
some inputs regarding few key points listed here,
1. We continue to use "-mprintf-kind" option to decide the lowering scheme. It
