AMDGPU: Make v2i16/v2f16 legal on VI
This usually results in better code. Fixes using
inline asm with short2, and also fixes having a different
ABI for function parameters between VI and gfx9.
Partially cleans up the mess used for lowering of the d16
operations. Making v4f16 legal will help clean this up more,
but this requires additional work.
llvm-svn: 332953
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index db7a4ab..84768e6 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -799,6 +799,9 @@
def HasVOP3PInsts : Predicate<"Subtarget->hasVOP3PInsts()">,
AssemblerPredicate<"FeatureVOP3P">;
+def NotHasVOP3PInsts : Predicate<"!Subtarget->hasVOP3PInsts()">,
+ AssemblerPredicate<"!FeatureVOP3P">;
+
def HasSDWA : Predicate<"Subtarget->hasSDWA()">,
AssemblerPredicate<"FeatureSDWA,FeatureVolcanicIslands">;