Mesa (master): radeon/llvm: Add support for fneg on SI

[Tom Stellard]

Module: Mesa
Branch: master
Commit: a35eea786823f0130b925cb25486d7d162f2d68c
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=a35eea786823f0130b925cb25486d7d162f2d68c

Author: Tom Stellard <thomas.stellard at amd.com>
Date:   Thu Aug  2 14:05:20 2012 -0400

radeon/llvm: Add support for fneg on SI

---

 src/gallium/drivers/radeon/SIISelLowering.cpp |   15 +++++++++++++++
 src/gallium/drivers/radeon/SIInstructions.td  |    1 +
 2 files changed, 16 insertions(+), 0 deletions(-)

diff --git a/src/gallium/drivers/radeon/SIISelLowering.cpp b/src/gallium/drivers/radeon/SIISelLowering.cpp
index a14cb6f..3e08e88 100644
--- a/src/gallium/drivers/radeon/SIISelLowering.cpp
+++ b/src/gallium/drivers/radeon/SIISelLowering.cpp
@@ -99,6 +99,21 @@ MachineBasicBlock * SITargetLowering::EmitInstrWithCustomInserter(
     MI->eraseFromParent();
     break;
 
+  case AMDGPU::FNEG_SI:
+    BuildMI(*BB, I, BB->findDebugLoc(I), TII->get(AMDGPU::V_MOV_B32_e64))
+                 .addOperand(MI->getOperand(0))
+                 .addOperand(MI->getOperand(1))
+                 // VSRC1-2 are unused, but we still need to fill all the
+                 // operand slots, so we just reuse the VSRC0 operand
+                 .addOperand(MI->getOperand(1))
+                 .addOperand(MI->getOperand(1))
+                 .addImm(0) // ABS
+                 .addImm(0) // CLAMP
+                 .addImm(0) // OMOD
+                 .addImm(1); // NEG
+    MI->eraseFromParent();
+    break;
+
   case AMDGPU::SI_INTERP:
     LowerSI_INTERP(MI, *BB, I, MRI);
     break;
diff --git a/src/gallium/drivers/radeon/SIInstructions.td b/src/gallium/drivers/radeon/SIInstructions.td
index 1f03ea5..c753943 100644
--- a/src/gallium/drivers/radeon/SIInstructions.td
+++ b/src/gallium/drivers/radeon/SIInstructions.td
@@ -1017,6 +1017,7 @@ def : Pat <
 
 def CLAMP_SI : CLAMP<VReg_32>;
 def FABS_SI : FABS<VReg_32>;
+def FNEG_SI : FNEG<VReg_32>;
 
 def : Extract_Element <f32, v4f32, VReg_128, 0, sel_x>;
 def : Extract_Element <f32, v4f32, VReg_128, 1, sel_y>;