[llvm] b87e3e2 - AMDGPU: Don't create potentially dead rcp declarations

[Matt Arsenault via llvm-commits]

Author: Matt Arsenault
Date: 2020-02-11T18:11:39-05:00
New Revision: b87e3e2d0db8b0eb7a8f26525dad74cc7014b85f

URL: https://github.com/llvm/llvm-project/commit/b87e3e2d0db8b0eb7a8f26525dad74cc7014b85f
DIFF: https://github.com/llvm/llvm-project/commit/b87e3e2d0db8b0eb7a8f26525dad74cc7014b85f.diff

LOG: AMDGPU: Don't create potentially dead rcp declarations

This will introduce unused declarations if this doesn't reach any of
the paths that will really use it.

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
index e3cc2a4abdee..e6499afcd7a3 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
@@ -620,10 +620,12 @@ static Value *optimizeWithRcp(Value *Num, Value *Den, bool AllowInaccurateRcp,
     return nullptr;
 
   Type *Ty = Den->getType();
-  Function *Decl = Intrinsic::getDeclaration(Mod, Intrinsic::amdgcn_rcp, Ty);
   if (const ConstantFP *CLHS = dyn_cast<ConstantFP>(Num)) {
     if (AllowInaccurateRcp || RcpIsAccurate) {
       if (CLHS->isExactlyValue(1.0)) {
+        Function *Decl = Intrinsic::getDeclaration(
+          Mod, Intrinsic::amdgcn_rcp, Ty);
+
         // v_rcp_f32 and v_rsq_f32 do not support denormals, and according to
         // the CI documentation has a worst case error of 1 ulp.
         // OpenCL requires <= 2.5 ulp for 1.0 / x, so it should always be OK to
@@ -636,10 +638,13 @@ static Value *optimizeWithRcp(Value *Num, Value *Den, bool AllowInaccurateRcp,
 
         // 1.0 / x -> rcp(x)
         return Builder.CreateCall(Decl, { Den });
-       }
+      }
 
        // Same as for 1.0, but expand the sign out of the constant.
-       if (CLHS->isExactlyValue(-1.0)) {
+      if (CLHS->isExactlyValue(-1.0)) {
+        Function *Decl = Intrinsic::getDeclaration(
+          Mod, Intrinsic::amdgcn_rcp, Ty);
+
          // -1.0 / x -> rcp (fneg x)
          Value *FNeg = Builder.CreateFNeg(Den);
          return Builder.CreateCall(Decl, { FNeg });
@@ -648,6 +653,9 @@ static Value *optimizeWithRcp(Value *Num, Value *Den, bool AllowInaccurateRcp,
   }
 
   if (AllowInaccurateRcp) {
+    Function *Decl = Intrinsic::getDeclaration(
+      Mod, Intrinsic::amdgcn_rcp, Ty);
+
     // Turn into multiply by the reciprocal.
     // x / y -> x * (1.0 / y)
     Value *Recip = Builder.CreateCall(Decl, { Den });