nvc0/ir: Teach insnCanLoad about double immediates

Teach insnCanLoad about double immediates, together with the
"Add support for merge-s to the ConstantFolding pass"

This turns the following (nvc0) code:
  1: mov u32 $r2 0x00000000 (8)
  2: mov u32 $r3 0x3fe00000 (8)
  3: add f64 $r0d $r0d $r2d (8)

Into:
  1: add f64 $r0d $r0d 0.500000 (8)

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

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 27df0eba66bae660cfe025d1744ecfe46e73070a..8f59d86a72f2705c1a0e50a58da70c8f5047bff4 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp
@@ -338,17 +338,30 @@ TargetNVC0::insnCanLoad(const Instruction *i, int s,
    if (sf == FILE_IMMEDIATE) {
       Storage &reg = ld->getSrc(0)->asImm()->reg;
 
-      if (typeSizeof(i->sType) > 4)
-         return false;
-      if (opInfo[i->op].immdBits != 0xffffffff) {
-         if (i->sType == TYPE_F32) {
+      if (opInfo[i->op].immdBits != 0xffffffff || typeSizeof(i->sType) > 4) {
+         switch (i->sType) {
+         case TYPE_F64:
+            if (reg.data.u64 & 0x00000fffffffffffULL)
+               return false;
+            break;
+         case TYPE_F32:
             if (reg.data.u32 & 0xfff)
                return false;
-         } else
-         if (i->sType == TYPE_S32 || i->sType == TYPE_U32) {
+            break;
+         case TYPE_S32:
+         case TYPE_U32:
             // with u32, 0xfffff counts as 0xffffffff as well
             if (reg.data.s32 > 0x7ffff || reg.data.s32 < -0x80000)
                return false;
+            break;
+         case TYPE_U8:
+         case TYPE_S8:
+         case TYPE_U16:
+         case TYPE_S16:
+         case TYPE_F16:
+            break;
+         default:
+            return false;
          }
       } else
       if (i->op == OP_MAD || i->op == OP_FMA) {