From 07e063e44c2348d23b2d7f249e7da3be56c20760 Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Mon, 6 Apr 2015 17:15:41 +0000
Subject: [PATCH] [DAGCombiner] Add support for FCEIL, FFLOOR and FTRUNC vector
 constant folding

Differential Revision: http://reviews.llvm.org/D8715

llvm-svn: 234179
---
 llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp |  9 ++--
 .../lib/CodeGen/SelectionDAG/SelectionDAG.cpp |  4 ++
 llvm/test/CodeGen/X86/vec_floor.ll            | 46 +++++++++++++++++++
 3 files changed, 53 insertions(+), 6 deletions(-)

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index e0866ef4ee75..71fae7b049a3 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -8194,11 +8194,10 @@ SDValue DAGCombiner::visitFP_EXTEND(SDNode *N) {
 
 SDValue DAGCombiner::visitFCEIL(SDNode *N) {
   SDValue N0 = N->getOperand(0);
-  ConstantFPSDNode *N0CFP = dyn_cast<ConstantFPSDNode>(N0);
   EVT VT = N->getValueType(0);
 
   // fold (fceil c1) -> fceil(c1)
-  if (N0CFP)
+  if (isConstantFPBuildVectorOrConstantFP(N0))
     return DAG.getNode(ISD::FCEIL, SDLoc(N), VT, N0);
 
   return SDValue();
@@ -8206,11 +8205,10 @@ SDValue DAGCombiner::visitFCEIL(SDNode *N) {
 
 SDValue DAGCombiner::visitFTRUNC(SDNode *N) {
   SDValue N0 = N->getOperand(0);
-  ConstantFPSDNode *N0CFP = dyn_cast<ConstantFPSDNode>(N0);
   EVT VT = N->getValueType(0);
 
   // fold (ftrunc c1) -> ftrunc(c1)
-  if (N0CFP)
+  if (isConstantFPBuildVectorOrConstantFP(N0))
     return DAG.getNode(ISD::FTRUNC, SDLoc(N), VT, N0);
 
   return SDValue();
@@ -8218,11 +8216,10 @@ SDValue DAGCombiner::visitFTRUNC(SDNode *N) {
 
 SDValue DAGCombiner::visitFFLOOR(SDNode *N) {
   SDValue N0 = N->getOperand(0);
-  ConstantFPSDNode *N0CFP = dyn_cast<ConstantFPSDNode>(N0);
   EVT VT = N->getValueType(0);
 
   // fold (ffloor c1) -> ffloor(c1)
-  if (N0CFP)
+  if (isConstantFPBuildVectorOrConstantFP(N0))
     return DAG.getNode(ISD::FFLOOR, SDLoc(N), VT, N0);
 
   return SDValue();
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 644411706f40..fdfdd15ad67d 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -2853,6 +2853,9 @@ SDValue SelectionDAG::getNode(unsigned Opcode, SDLoc DL,
         break;
       case ISD::FNEG:
       case ISD::FABS:
+      case ISD::FCEIL:
+      case ISD::FTRUNC:
+      case ISD::FFLOOR:
       case ISD::FP_EXTEND:
       case ISD::TRUNCATE:
       case ISD::UINT_TO_FP:
@@ -2870,6 +2873,7 @@ SDValue SelectionDAG::getNode(unsigned Opcode, SDLoc DL,
         }
         if (Ops.size() == VT.getVectorNumElements())
           return getNode(ISD::BUILD_VECTOR, DL, VT, Ops);
+        break;
       }
       }
     }
diff --git a/llvm/test/CodeGen/X86/vec_floor.ll b/llvm/test/CodeGen/X86/vec_floor.ll
index 4db68bd18223..f35c4ab4a76e 100644
--- a/llvm/test/CodeGen/X86/vec_floor.ll
+++ b/llvm/test/CodeGen/X86/vec_floor.ll
@@ -180,3 +180,49 @@ define <8 x float> @nearbyint_v8f32(<8 x float> %p)
   ret <8 x float> %t
 }
 declare <8 x float> @llvm.nearbyint.v8f32(<8 x float> %p)
+
+;
+; Constant Folding
+;
+
+define <2 x double> @const_floor_v2f64() {
+  ; CHECK: const_floor_v2f64
+  ; CHECK: movaps {{.*#+}} xmm0 = [-2.000000e+00,2.000000e+00]
+  %t = call <2 x double> @llvm.floor.v2f64(<2 x double> <double -1.5, double 2.5>)
+  ret <2 x double> %t
+}
+
+define <4 x float> @const_floor_v4f32() {
+  ; CHECK: const_floor_v4f32
+  ; CHECK: movaps {{.*#+}} xmm0 = [-4.000000e+00,6.000000e+00,-9.000000e+00,2.000000e+00]
+  %t = call <4 x float> @llvm.floor.v4f32(<4 x float> <float -3.5, float 6.0, float -9.0, float 2.5>)
+  ret <4 x float> %t
+}
+
+define <2 x double> @const_ceil_v2f64() {
+  ; CHECK: const_ceil_v2f64
+  ; CHECK: movaps {{.*#+}} xmm0 = [-1.000000e+00,3.000000e+00]
+  %t = call <2 x double> @llvm.ceil.v2f64(<2 x double> <double -1.5, double 2.5>)
+  ret <2 x double> %t
+}
+
+define <4 x float> @const_ceil_v4f32() {
+  ; CHECK: const_ceil_v4f32
+  ; CHECK: movaps {{.*#+}} xmm0 = [-3.000000e+00,6.000000e+00,-9.000000e+00,3.000000e+00]
+  %t = call <4 x float> @llvm.ceil.v4f32(<4 x float> <float -3.5, float 6.0, float -9.0, float 2.5>)
+  ret <4 x float> %t
+}
+
+define <2 x double> @const_trunc_v2f64() {
+  ; CHECK: const_trunc_v2f64
+  ; CHECK: movaps {{.*#+}} xmm0 = [-1.000000e+00,2.000000e+00]
+  %t = call <2 x double> @llvm.trunc.v2f64(<2 x double> <double -1.5, double 2.5>)
+  ret <2 x double> %t
+}
+
+define <4 x float> @const_trunc_v4f32() {
+  ; CHECK: const_trunc_v4f32
+  ; CHECK: movaps {{.*#+}} xmm0 = [-3.000000e+00,6.000000e+00,-9.000000e+00,2.000000e+00]
+  %t = call <4 x float> @llvm.trunc.v4f32(<4 x float> <float -3.5, float 6.0, float -9.0, float 2.5>)
+  ret <4 x float> %t
+}