[Mesa-dev] [PATCH 2/6] nvc0/ir: add emission for SHLADD

[Samuel Pitoiset]

Unfortunately, we can't use the emit helpers for GF100/GK110
because src1 and src2 are swapped.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
---
 .../drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp | 53 ++++++++++++++++++++++
 .../drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp | 32 +++++++++++++
 .../drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp  | 44 ++++++++++++++++++
 3 files changed, 129 insertions(+)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
index 61c450b..2c4e3a7 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
@@ -96,6 +96,7 @@ private:
    void emitDMUL(const Instruction *);
    void emitIMAD(const Instruction *);
    void emitISAD(const Instruction *);
+   void emitSHLADD(const Instruction *);
    void emitFMAD(const Instruction *);
    void emitDMAD(const Instruction *);
    void emitMADSP(const Instruction *i);
@@ -757,6 +758,55 @@ CodeEmitterGK110::emitISAD(const Instruction *i)
 }
 
 void
+CodeEmitterGK110::emitSHLADD(const Instruction *i)
+{
+   uint8_t addOp =
+      (i->src(2).mod.neg() << 1) | (i->src(0).mod.neg() ^ i->src(1).mod.neg());
+   const ImmediateValue *imm = i->src(1).get()->asImm();
+   assert(imm);
+
+   if (i->src(2).getFile() == FILE_IMMEDIATE) {
+      code[0] = 0x1;
+      code[1] = 0xc0c << 20;
+   } else {
+      code[0] = 0x2;
+      code[1] = 0x20c << 20;
+   }
+   code[1] |= addOp << 19;
+
+   emitPredicate(i);
+
+   defId(i->def(0), 2);
+   srcId(i->src(0), 10);
+
+   if (i->flagsDef >= 0)
+      code[1] |= 1 << 18;
+
+   assert(!(imm->reg.data.u32 & 0xffffffe0));
+   code[1] |= imm->reg.data.u32 << 10;
+
+   switch (i->src(2).getFile()) {
+   case FILE_GPR:
+      assert(code[0] & 0x2);
+      code[1] |= 0xc << 28;
+      srcId(i->src(2), 23);
+      break;
+   case FILE_MEMORY_CONST:
+      assert(code[0] & 0x2);
+      code[1] |= 0x4 << 28;
+      setCAddress14(i->src(2));
+      break;
+   case FILE_IMMEDIATE:
+      assert(code[0] & 0x1);
+      setShortImmediate(i, 2);
+      break;
+   default:
+      assert(!"bad src2 file");
+      break;
+   }
+}
+
+void
 CodeEmitterGK110::emitNOT(const Instruction *i)
 {
    code[0] = 0x0003fc02; // logop(mov2) dst, 0, not src
@@ -2403,6 +2453,9 @@ CodeEmitterGK110::emitInstruction(Instruction *insn)
    case OP_SAD:
       emitISAD(insn);
       break;
+   case OP_SHLADD:
+      emitSHLADD(insn);
+      break;
    case OP_NOT:
       emitNOT(insn);
       break;
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
index cfde66c..973a105 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
@@ -152,6 +152,7 @@ private:
    void emitIADD();
    void emitIMUL();
    void emitIMAD();
+   void emitSHLADD();
    void emitIMNMX();
    void emitICMP();
    void emitISET();
@@ -1813,6 +1814,34 @@ CodeEmitterGM107::emitIMAD()
 }
 
 void
+CodeEmitterGM107::emitSHLADD()
+{
+   switch (insn->src(2).getFile()) {
+   case FILE_GPR:
+      emitInsn(0x5c180000);
+      emitGPR (0x14, insn->src(2));
+      break;
+   case FILE_MEMORY_CONST:
+      emitInsn(0x4c180000);
+      emitCBUF(0x22, -1, 0x14, 16, 2, insn->src(2));
+      break;
+   case FILE_IMMEDIATE:
+      emitInsn(0x38180000);
+      emitIMMD(0x14, 19, insn->src(2));
+      break;
+   default:
+      assert(!"bad src1 file");
+      break;
+   }
+   emitNEG (0x31, insn->src(0));
+   emitNEG (0x30, insn->src(2));
+   emitCC  (0x2f);
+   emitIMMD(0x27, 5, insn->src(1));
+   emitGPR (0x08, insn->src(0));
+   emitGPR (0x00, insn->def(0));
+}
+
+void
 CodeEmitterGM107::emitIMNMX()
 {
    switch (insn->src(1).getFile()) {
@@ -3098,6 +3127,9 @@ CodeEmitterGM107::emitInstruction(Instruction *i)
          emitIMAD();
       }
       break;
+   case OP_SHLADD:
+      emitSHLADD();
+      break;
    case OP_MIN:
    case OP_MAX:
       if (isFloatType(insn->dType)) {
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 d8ca6ab..c874b86 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
@@ -101,6 +101,7 @@ private:
    void emitDMUL(const Instruction *);
    void emitIMAD(const Instruction *);
    void emitISAD(const Instruction *);
+   void emitSHLADD(const Instruction *a);
    void emitFMAD(const Instruction *);
    void emitDMAD(const Instruction *);
    void emitMADSP(const Instruction *);
@@ -759,6 +760,46 @@ CodeEmitterNVC0::emitIMAD(const Instruction *i)
 }
 
 void
+CodeEmitterNVC0::emitSHLADD(const Instruction *i)
+{
+   uint8_t addOp =
+      (i->src(2).mod.neg() << 1) | (i->src(0).mod.neg() ^ i->src(1).mod.neg());
+   const ImmediateValue *imm = i->src(1).get()->asImm();
+   assert(imm);
+
+   code[0] = 0x00000003;
+   code[1] = 0x40000000 | addOp << 23;
+
+   emitPredicate(i);
+
+   defId(i->def(0), 14);
+   srcId(i->src(0), 20);
+
+   if (i->flagsDef >= 0)
+      code[1] |= 1 << 16;
+
+   assert(!(imm->reg.data.u32 & 0xffffffe0));
+   code[0] |= imm->reg.data.u32 << 5;
+
+   switch (i->src(2).getFile()) {
+   case FILE_GPR:
+      srcId(i->src(2), 26);
+      break;
+   case FILE_MEMORY_CONST:
+      code[1] |= 0x4000;
+      code[1] |= i->getSrc(2)->reg.fileIndex << 10;
+      setAddress16(i->src(2));
+      break;
+   case FILE_IMMEDIATE:
+      setImmediate(i, 2);
+      break;
+   default:
+      assert(!"bad src2 file");
+      break;
+   }
+}
+
+void
 CodeEmitterNVC0::emitMADSP(const Instruction *i)
 {
    assert(targ->getChipset() >= NVISA_GK104_CHIPSET);
@@ -2603,6 +2644,9 @@ CodeEmitterNVC0::emitInstruction(Instruction *insn)
    case OP_SAD:
       emitISAD(insn);
       break;
+   case OP_SHLADD:
+      emitSHLADD(insn);
+      break;
    case OP_NOT:
       emitNOT(insn);
       break;
-- 
2.10.0