AMDGPU: Add support for amdgpu-unsafe-fp-atomics attribute

If amdgpu-unsafe-fp-atomics is specified, allow {flat|global}_atomic_add_f32 even if atomic modes don't match.

Differential Revision: https://reviews.llvm.org/D95391

diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index e73f2b4..a8b5a9b 100644 (file)
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -11773,7 +11773,9 @@ SITargetLowering::shouldExpandAtomicRMWInIR(AtomicRMWInst *RMW) const {
     unsigned AS = RMW->getPointerAddressSpace();
 
     if (AS == AMDGPUAS::GLOBAL_ADDRESS && Subtarget->hasAtomicFaddInsts()) {
-      if (!fpModeMatchesGlobalFPAtomicMode(RMW))
+      if (!fpModeMatchesGlobalFPAtomicMode(RMW) ||
+          RMW->getFunction()->getFnAttribute("amdgpu-unsafe-fp-atomics")
+              .getValueAsString() != "true")
         return AtomicExpansionKind::CmpXChg;
 
       return RMW->use_empty() ? AtomicExpansionKind::None :

diff --git a/llvm/test/CodeGen/AMDGPU/global-atomics-fp.ll b/llvm/test/CodeGen/AMDGPU/global-atomics-fp.ll
index 0076685..3ad8558 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/global-atomics-fp.ll
+++ b/llvm/test/CodeGen/AMDGPU/global-atomics-fp.ll
@@ -61,5 +61,5 @@ define amdgpu_kernel void @global_atomic_fadd_noret_f32_wrong_subtarget(float ad
   ret void
 }
 
-attributes #0 = { "denormal-fp-math-f32"="preserve-sign,preserve-sign"}
+attributes #0 = { "denormal-fp-math-f32"="preserve-sign,preserve-sign" "amdgpu-unsafe-fp-atomics"="true" }
 attributes #1 = { "denormal-fp-math-f32"="preserve-sign,preserve-sign" "target-cpu"="gfx803" "target-features"="+atomic-fadd-insts" }

diff --git a/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll b/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll
index 78992ac..52af2b8 100644 (file)
--- a/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll
+++ b/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll
@@ -463,4 +463,4 @@ define double @test_atomicrmw_fadd_f64_local(double addrspace(3)* %ptr, double %
   ret double %res
 }
 
-attributes #0 = { "denormal-fp-math-f32"="preserve-sign,preserve-sign" }
+attributes #0 = { "denormal-fp-math-f32"="preserve-sign,preserve-sign" "amdgpu-unsafe-fp-atomics"="true" }