From bcbcdf84485192c0f6b44d94a423d80ba204bb4b Mon Sep 17 00:00:00 2001
From: Rhys Perry <pendingchaos02@gmail.com>
Date: Wed, 13 Jun 2018 16:21:56 +0100
Subject: [PATCH] gm107/ir: add support for OP_XMAD on GM107+

v4: make the immediate field 16 bits
v5: don't ever emit h1 flags for immediates

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
---
 .../nouveau/codegen/nv50_ir_emit_gm107.cpp    | 65 +++++++++++++++++++
 .../nouveau/codegen/nv50_ir_target_gm107.cpp  |  6 +-
 .../nouveau/codegen/nv50_ir_target_nvc0.cpp   |  1 +
 3 files changed, 71 insertions(+), 1 deletion(-)

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 5e8c22cd54b..b2e22195ec5 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
@@ -156,6 +156,7 @@ private:
    void emitIMUL();
    void emitIMAD();
    void emitISCADD();
+   void emitXMAD();
    void emitIMNMX();
    void emitICMP();
    void emitISET();
@@ -1893,6 +1894,67 @@ CodeEmitterGM107::emitISCADD()
    emitGPR (0x00, insn->def(0));
 }
 
+void
+CodeEmitterGM107::emitXMAD()
+{
+   assert(insn->src(0).getFile() == FILE_GPR);
+
+   bool constbuf = false;
+   bool psl_mrg = true;
+   bool immediate = false;
+   if (insn->src(2).getFile() == FILE_MEMORY_CONST) {
+      assert(insn->src(1).getFile() == FILE_GPR);
+      constbuf = true;
+      psl_mrg = false;
+      emitInsn(0x51000000);
+      emitGPR(0x27, insn->src(1));
+      emitCBUF(0x22, -1, 0x14, 16, 2, insn->src(2));
+   } else if (insn->src(1).getFile() == FILE_MEMORY_CONST) {
+      assert(insn->src(2).getFile() == FILE_GPR);
+      constbuf = true;
+      emitInsn(0x4e000000);
+      emitCBUF(0x22, -1, 0x14, 16, 2, insn->src(1));
+      emitGPR(0x27, insn->src(2));
+   } else if (insn->src(1).getFile() == FILE_IMMEDIATE) {
+      assert(insn->src(2).getFile() == FILE_GPR);
+      assert(!(insn->subOp & NV50_IR_SUBOP_XMAD_H1(1)));
+      immediate = true;
+      emitInsn(0x36000000);
+      emitIMMD(0x14, 16, insn->src(1));
+      emitGPR(0x27, insn->src(2));
+   } else {
+      assert(insn->src(1).getFile() == FILE_GPR);
+      assert(insn->src(2).getFile() == FILE_GPR);
+      emitInsn(0x5b000000);
+      emitGPR(0x14, insn->src(1));
+      emitGPR(0x27, insn->src(2));
+   }
+
+   if (psl_mrg)
+      emitField(constbuf ? 0x37 : 0x24, 2, insn->subOp & 0x3);
+
+   unsigned cmode = (insn->subOp & NV50_IR_SUBOP_XMAD_CMODE_MASK);
+   cmode >>= NV50_IR_SUBOP_XMAD_CMODE_SHIFT;
+   emitField(0x32, constbuf ? 2 : 3, cmode);
+
+   emitX(constbuf ? 0x36 : 0x26);
+   emitCC(0x2f);
+
+   emitGPR(0x0, insn->def(0));
+   emitGPR(0x8, insn->src(0));
+
+   // source flags
+   if (isSignedType(insn->sType)) {
+      uint16_t h1s = insn->subOp & NV50_IR_SUBOP_XMAD_H1_MASK;
+      emitField(0x30, 2, h1s >> NV50_IR_SUBOP_XMAD_H1_SHIFT);
+   }
+   emitField(0x35, 1, insn->subOp & NV50_IR_SUBOP_XMAD_H1(0) ? 1 : 0);
+   if (!immediate) {
+      bool h1 = insn->subOp & NV50_IR_SUBOP_XMAD_H1(1);
+      emitField(constbuf ? 0x34 : 0x23, 1, h1);
+   }
+}
+
 void
 CodeEmitterGM107::emitIMNMX()
 {
@@ -3267,6 +3329,9 @@ CodeEmitterGM107::emitInstruction(Instruction *i)
    case OP_SHLADD:
       emitISCADD();
       break;
+   case OP_XMAD:
+      emitXMAD();
+      break;
    case OP_MIN:
    case OP_MAX:
       if (isFloatType(insn->dType)) {
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_gm107.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_gm107.cpp
index 2dd12322a89..de07ad1de89 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_gm107.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_gm107.cpp
@@ -59,12 +59,15 @@ TargetGM107::isOpSupported(operation op, DataType ty) const
    case OP_POW:
    case OP_DIV:
    case OP_MOD:
-   case OP_XMAD:
       return false;
    case OP_SQRT:
       if (ty == TYPE_F64)
          return false;
       return chipset >= NVISA_GM200_CHIPSET;
+   case OP_XMAD:
+      if (isFloatType(ty))
+         return false;
+      break;
    default:
       break;
    }
@@ -235,6 +238,7 @@ TargetGM107::getLatency(const Instruction *insn) const
    case OP_SUB:
    case OP_VOTE:
    case OP_XOR:
+   case OP_XMAD:
       if (insn->dType != TYPE_F64)
          return 6;
       break;
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp
index 8e040695363..60134b445db 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp
@@ -162,6 +162,7 @@ static const struct opProperties _initPropsGM107[] = {
    { OP_SUSTP,   0x0, 0x0, 0x0, 0x0, 0x0, 0x4 },
    { OP_SUREDB,  0x0, 0x0, 0x0, 0x0, 0x0, 0x4 },
    { OP_SUREDP,  0x0, 0x0, 0x0, 0x0, 0x0, 0x4 },
+   { OP_XMAD,    0x0, 0x0, 0x0, 0x0, 0x6, 0x2 },
 };
 
 void TargetNVC0::initProps(const struct opProperties *props, int size)
-- 
2.30.2