[PATCH] D156301: [WIP] Support FAdd/FSub global atomics in AMDGPUAtomicOptimizer.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp:329
+    // TODO: Support for double type
+    if (!isScanStrategyIterative() || I.getType()->isDoubleTy()) {
+      return;
----------------
pravinjagtap wrote:
> arsenm wrote:
> > Doesn't consider half
> > 
> > Should also handle <2 x half>, but atomicrmw doesn't support vectors now (you need the intrinsics for those)
> > Doesn't consider half
> 
> Appears that `_Float16` is not supported for atomics in HIP: https://cuda.godbolt.org/z/Gf7so4Y9K
Doesn't matter, the IR does. You should select the types you do handle, not try to exclude ones you don't


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156301/new/

https://reviews.llvm.org/D156301