[AMDGPU] Add options -mamdgpu-ieee -mno-amdgpu-ieee

AMDGPU backend need to know whether floating point opcodes that support exception
flag gathering quiet and propagate signaling NaN inputs per IEEE754-2008, which is
conveyed by a function attribute "amdgpu-ieee". "amdgpu-ieee"="false" turns this off.
Without this function attribute backend assumes it is on for compute functions.

-mamdgpu-ieee and -mno-amdgpu-ieee are added to Clang to control this function attribute.
By default it is on. -mno-amdgpu-ieee requires -fno-honor-nans or equivalent.

Reviewed by: Matt Arsenault

Differential Revision: https://reviews.llvm.org/D77013

1 files changed, 5 insertions, 0 deletions

diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 2578c8c..b3e1e06 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -1944,6 +1944,11 @@ bool CompilerInvocation::ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args,
   else if (Args.hasArg(options::OPT_fno_finite_loops))
     Opts.FiniteLoops = CodeGenOptions::FiniteLoopsKind::Never;
 
+  Opts.EmitIEEENaNCompliantInsts =
+      Args.hasFlag(options::OPT_mamdgpu_ieee, options::OPT_mno_amdgpu_ieee);
+  if (!Opts.EmitIEEENaNCompliantInsts && !LangOptsRef.NoHonorNaNs)
+    Diags.Report(diag::err_drv_amdgpu_ieee_without_no_honor_nans);
+
   return Diags.getNumErrors() == NumErrorsBefore;
 }