nvc0/ir: Emit OP_SHFL

v2: (Samuel Pitoiset)
Add an assertion to check if the target is Kepler
Make sure that asImm() is not NULL

v3: (Ilia Mirkin)
Check the range of immediate value of OP_SHFL
Use the new setPDSTL API

Signed-off-by: Boyan Ding <boyan.j.ding@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
index a578e947ec621cf7789d2ea161a0535c1dfbb69e..f4c39a168bed810c3617194fb5500b31a0386597 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
@@ -150,6 +150,8 @@ private:
 
    void emitPIXLD(const Instruction *);
 
+   void emitSHFL(const Instruction *);
+
    void emitVOTE(const Instruction *);
 
    inline void defId(const ValueDef&, const int pos);
@@ -2530,6 +2532,54 @@ CodeEmitterNVC0::emitPIXLD(const Instruction *i)
    code[1] |= 0x00e00000;
 }
 
+void
+CodeEmitterNVC0::emitSHFL(const Instruction *i)
+{
+   const ImmediateValue *imm;
+
+   assert(targ->getChipset() >= NVISA_GK104_CHIPSET);
+
+   code[0] = 0x00000005;
+   code[1] = 0x88000000 | (i->subOp << 23);
+
+   emitPredicate(i);
+
+   defId(i->def(0), 14);
+   srcId(i->src(0), 20);
+
+   switch (i->src(1).getFile()) {
+   case FILE_GPR:
+      srcId(i->src(1), 26);
+      break;
+   case FILE_IMMEDIATE:
+      imm = i->getSrc(1)->asImm();
+      assert(imm && imm->reg.data.u32 < 0x20);
+      code[0] |= imm->reg.data.u32 << 26;
+      code[0] |= 1 << 5;
+      break;
+   default:
+      assert(!"invalid src1 file");
+      break;
+   }
+
+   switch (i->src(2).getFile()) {
+   case FILE_GPR:
+      srcId(i->src(2), 49);
+      break;
+   case FILE_IMMEDIATE:
+      imm = i->getSrc(2)->asImm();
+      assert(imm && imm->reg.data.u32 < 0x2000);
+      code[1] |= imm->reg.data.u32 << 10;
+      code[0] |= 1 << 6;
+      break;
+   default:
+      assert(!"invalid src2 file");
+      break;
+   }
+
+   setPDSTL(i, i->defExists(1) ? 1 : -1);
+}
+
 void
 CodeEmitterNVC0::emitVOTE(const Instruction *i)
 {
@@ -2839,6 +2889,9 @@ CodeEmitterNVC0::emitInstruction(Instruction *insn)
    case OP_PIXLD:
       emitPIXLD(insn);
       break;
+   case OP_SHFL:
+      emitSHFL(insn);
+      break;
    case OP_VOTE:
       emitVOTE(insn);
       break;