[Nouveau] [PATCH v4] nv50/ir: Handle OP_CVT when folding constant expressions

[Tobias Klausmann]

Folding for conversions:
   F32->(U{16/32}, S{16/32})
   (U{16/32}, {S16/32})->F32
   U32 -> U16

Signed-off-by: Tobias Klausmann <tobias.johannes.klausmann at mni.thm.de>
---
V2: Split out F64 parts
V3: remove handling of saturate for (U/S)32
V4: handle U32->U16 for OP_TXF

 .../drivers/nouveau/codegen/nv50_ir_peephole.cpp   | 79 ++++++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 21d20ca..235aed9 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -997,6 +997,85 @@ ConstantFolding::opnd(Instruction *i, ImmediateValue &imm0, int s)
       i->op = OP_MOV;
       break;
    }
+   case OP_CVT: {
+      Storage res;
+      bld.setPosition(i, true); /* make sure bld is init'ed */
+      switch(i->dType) {
+      case TYPE_U16:
+         switch (i->sType) {
+         case TYPE_F32:
+            if (i->saturate)
+               res.data.u16 = util_iround(CLAMP(imm0.reg.data.f32, 0,
+                                                UINT16_MAX));
+            else
+              res.data.u16 = util_iround(imm0.reg.data.f32);
+            break;
+         case TYPE_U32:
+            if (i->saturate)
+               res.data.u16 = CLAMP(imm0.reg.data.u32, 0, UINT16_MAX);
+            else
+               res.data.u16 = imm0.reg.data.u32;
+            break;
+         default:
+            return;
+         }
+         i->setSrc(0, bld.mkImm(res.data.u16));
+         break;
+      case TYPE_U32:
+         assert(!i->saturate);
+         switch (i->sType) {
+         case TYPE_F32:
+            res.data.u32 = util_iround(imm0.reg.data.f32);
+            break;
+         default:
+            return;
+         }
+         i->setSrc(0, bld.mkImm(res.data.u32));
+         break;
+      case TYPE_S16:
+         switch (i->sType) {
+         case TYPE_F32:
+            if (i->saturate)
+               res.data.s16 = util_iround(CLAMP(imm0.reg.data.f32, INT16_MIN,
+                                                INT16_MAX));
+            else
+               res.data.s16 = util_iround(imm0.reg.data.f32);
+            break;
+         default:
+            return;
+         }
+         i->setSrc(0, bld.mkImm(res.data.s16));
+         break;
+      case TYPE_S32:
+         assert(!i->saturate);
+         switch (i->sType) {
+         case TYPE_F32:
+            res.data.s32 = util_iround(imm0.reg.data.f32);
+            break;
+         default:
+            return;
+         }
+         i->setSrc(0, bld.mkImm(res.data.s32));
+         break;
+      case TYPE_F32:
+         switch (i->sType) {
+         case TYPE_U16: res.data.f32 = (float) imm0.reg.data.u16; break;
+         case TYPE_U32: res.data.f32 = (float) imm0.reg.data.u32; break;
+         case TYPE_S16: res.data.f32 = (float) imm0.reg.data.s16; break;
+         case TYPE_S32: res.data.f32 = (float) imm0.reg.data.s32; break;
+         default:
+            return;
+         }
+         i->setSrc(0, bld.mkImm(res.data.f32));
+         break;
+      default:
+         return;
+      }
+      i->setType(i->dType); /* Remove i->sType, which we don't need anymore */
+      i->op = OP_MOV;
+      i->src(0).mod = Modifier(0); /* Clear the already applied modifier */
+      break;
+   }
    default:
       return;
    }
-- 
2.2.2