Merge remote-tracking branch 'origin/master' into pipe-video

Conflicts:
	src/gallium/drivers/r600/r600_pipe.c
	src/gallium/drivers/r600/r600_state_inlines.h

6 files changed, 153 insertions, 11 deletions

diff --git a/src/gallium/auxiliary/draw/draw_llvm.c b/src/gallium/auxiliary/draw/draw_llvm.c
index f33c9078c9c..8bb87440497 100644
--- a/src/gallium/auxiliary/draw/draw_llvm.c
+++ b/src/gallium/auxiliary/draw/draw_llvm.c
@@ -1235,7 +1235,8 @@ draw_llvm_generate(struct draw_llvm *llvm, struct draw_llvm_variant *variant)
       draw_llvm_variant_key_samplers(&variant->key),
       context_ptr);
 
-   fetch_max = LLVMBuildSub(builder, count,
+   /* fetch_max = start + count - 1 */
+   fetch_max = LLVMBuildSub(builder, end,
                             lp_build_const_int32(gallivm, 1),
                             "fetch_max");
 
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_debug.cpp b/src/gallium/auxiliary/gallivm/lp_bld_debug.cpp
index 01e660ef7d9..29dfb868d95 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_debug.cpp
+++ b/src/gallium/auxiliary/gallivm/lp_bld_debug.cpp
@@ -207,21 +207,13 @@ lp_disassemble(const void* func)
    }
 
    raw_debug_ostream Out;
-#if HAVE_LLVM >= 0x0300
-   TargetMachine *TM = T->createTargetMachine(Triple, sys::getHostCPUName(), "");
-#else
-   TargetMachine *TM = T->createTargetMachine(Triple, "");
-#endif
 
 #if HAVE_LLVM >= 0x0300
    unsigned int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
 #else
    int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
 #endif
-#if HAVE_LLVM >= 0x0300
-   OwningPtr<MCInstPrinter> Printer(
-         T->createMCInstPrinter(*TM, AsmPrinterVariant, *AsmInfo));
-#elif HAVE_LLVM >= 0x0208
+#if HAVE_LLVM >= 0x0208
    OwningPtr<MCInstPrinter> Printer(
          T->createMCInstPrinter(AsmPrinterVariant, *AsmInfo));
 #else
@@ -233,6 +225,12 @@ lp_disassemble(const void* func)
       return;
    }
 
+#if HAVE_LLVM >= 0x0300
+   TargetMachine *TM = T->createTargetMachine(Triple, sys::getHostCPUName(), "");
+#else
+   TargetMachine *TM = T->createTargetMachine(Triple, "");
+#endif
+
    const TargetInstrInfo *TII = TM->getInstrInfo();
 
    /*
diff --git a/src/gallium/auxiliary/tgsi/tgsi_exec.c b/src/gallium/auxiliary/tgsi/tgsi_exec.c
index 9cf74a838fe..712e8aca794 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_exec.c
+++ b/src/gallium/auxiliary/tgsi/tgsi_exec.c
@@ -1839,6 +1839,17 @@ exec_tex(struct tgsi_exec_machine *mach,
       assert(0);
    }
 
+#if 0
+   debug_printf("fetch r: %g %g %g %g\n",
+         r[0].f[0], r[0].f[1], r[0].f[2], r[0].f[3]);
+   debug_printf("fetch g: %g %g %g %g\n",
+         r[1].f[0], r[1].f[1], r[1].f[2], r[1].f[3]);
+   debug_printf("fetch b: %g %g %g %g\n",
+         r[2].f[0], r[2].f[1], r[2].f[2], r[2].f[3]);
+   debug_printf("fetch a: %g %g %g %g\n",
+         r[3].f[0], r[3].f[1], r[3].f[2], r[3].f[3]);
+#endif
+
    for (chan = 0; chan < NUM_CHANNELS; chan++) {
       if (inst->Dst[0].Register.WriteMask & (1 << chan)) {
          store_dest(mach, &r[chan], &inst->Dst[0], inst, chan, TGSI_EXEC_DATA_FLOAT);
diff --git a/src/gallium/auxiliary/util/u_pack_color.h b/src/gallium/auxiliary/util/u_pack_color.h
index 5378f2d782f..9391f1b80e0 100644
--- a/src/gallium/auxiliary/util/u_pack_color.h
+++ b/src/gallium/auxiliary/util/u_pack_color.h
@@ -458,6 +458,19 @@ util_pack_mask_z(enum pipe_format format, uint32_t z)
    }
 }
 
+
+static INLINE uint64_t
+util_pack64_mask_z(enum pipe_format format, uint32_t z)
+{
+   switch (format) {
+   case PIPE_FORMAT_Z32_FLOAT_S8X24_USCALED:
+      return z;
+   default:
+      return util_pack_mask_z(format, z);
+   }
+}
+
+
 static INLINE uint32_t
 util_pack_mask_z_stencil(enum pipe_format format, uint32_t z, uint8_t s)
 {
@@ -481,6 +494,21 @@ util_pack_mask_z_stencil(enum pipe_format format, uint32_t z, uint8_t s)
 }
 
 
+static INLINE uint64_t
+util_pack64_mask_z_stencil(enum pipe_format format, uint32_t z, uint8_t s)
+{
+   uint64_t packed;
+
+   switch (format) {
+   case PIPE_FORMAT_Z32_FLOAT_S8X24_USCALED:
+      packed = util_pack64_mask_z(format, z);
+      packed |= (uint64_t)s << 32ull;
+      return packed;
+   default:
+      return util_pack_mask_z_stencil(format, z, s);
+   }
+}
+
 
 /**
  * Note: it's assumed that z is in [0,1]
@@ -525,6 +553,24 @@ util_pack_z(enum pipe_format format, double z)
       return 0;
    }
 }
+
+
+static INLINE uint64_t
+util_pack64_z(enum pipe_format format, double z)
+{
+   union fi fui;
+
+   if (z == 0)
+      return 0;
+
+   switch (format) {
+   case PIPE_FORMAT_Z32_FLOAT_S8X24_USCALED:
+      fui.f = (float)z;
+      return fui.ui;
+   default:
+      return util_pack_z(format, z);
+   }
+}
  
 
 /**
@@ -554,6 +600,24 @@ util_pack_z_stencil(enum pipe_format format, double z, uint8_t s)
 }
 
 
+static INLINE uint64_t
+util_pack64_z_stencil(enum pipe_format format, double z, uint8_t s)
+{
+   uint64_t packed;
+
+   switch (format) {
+   case PIPE_FORMAT_Z32_FLOAT_S8X24_USCALED:
+      packed = util_pack64_z(format, z);
+      packed |= (uint64_t)s << 32ull;
+      break;
+   default:
+      return util_pack_z_stencil(format, z, s);
+   }
+
+   return packed;
+}
+
+
 /**
  * Pack 4 ubytes into a 4-byte word
  */
diff --git a/src/gallium/auxiliary/util/u_surface.c b/src/gallium/auxiliary/util/u_surface.c
index 4c5cc4da182..8e123867da6 100644
--- a/src/gallium/auxiliary/util/u_surface.c
+++ b/src/gallium/auxiliary/util/u_surface.c
@@ -358,8 +358,41 @@ util_clear_depth_stencil(struct pipe_context *pipe,
                dst_map += dst_stride;
             }
          }
-        break;
+         break;
       case 8:
+      {
+         uint64_t zstencil = util_pack64_z_stencil(dst->texture->format,
+                                                   depth, stencil);
+
+         assert(dst->format == PIPE_FORMAT_Z32_FLOAT_S8X24_USCALED);
+
+         if (!need_rmw) {
+            for (i = 0; i < height; i++) {
+               uint64_t *row = (uint64_t *)dst_map;
+               for (j = 0; j < width; j++)
+                  *row++ = zstencil;
+               dst_map += dst_stride;
+            }
+         }
+         else {
+            uint64_t src_mask;
+
+            if (clear_flags & PIPE_CLEAR_DEPTH)
+               src_mask = 0x00000000ffffffffull;
+            else
+               src_mask = 0x000000ff00000000ull;
+
+            for (i = 0; i < height; i++) {
+               uint64_t *row = (uint64_t *)dst_map;
+               for (j = 0; j < width; j++) {
+                  uint64_t tmp = *row & ~src_mask;
+                  *row++ = tmp | (zstencil & src_mask);
+               }
+               dst_map += dst_stride;
+            }
+         }
+         break;
+      }
       default:
          assert(0);
          break;
diff --git a/src/gallium/auxiliary/util/u_tile.c b/src/gallium/auxiliary/util/u_tile.c
index e3c7085ba92..23f12e5f464 100644
--- a/src/gallium/auxiliary/util/u_tile.c
+++ b/src/gallium/auxiliary/util/u_tile.c
@@ -318,6 +318,32 @@ z32f_get_tile_rgba(const float *src,
    }
 }
 
+/*** PIPE_FORMAT_Z32_FLOAT_S8X24_USCALED ***/
+
+/**
+ * Return each Z value as four floats in [0,1].
+ */
+static void
+z32f_x24s8_get_tile_rgba(const float *src,
+                         unsigned w, unsigned h,
+                         float *p,
+                         unsigned dst_stride)
+{
+   unsigned i, j;
+
+   for (i = 0; i < h; i++) {
+      float *pRow = p;
+      for (j = 0; j < w; j++, pRow += 4) {
+         pRow[0] =
+         pRow[1] =
+         pRow[2] =
+         pRow[3] = *src;
+         src += 2;
+      }
+      p += dst_stride;
+   }
+}
+
 
 void
 pipe_tile_raw_to_rgba(enum pipe_format format,
@@ -352,6 +378,9 @@ pipe_tile_raw_to_rgba(enum pipe_format format,
    case PIPE_FORMAT_Z32_FLOAT:
       z32f_get_tile_rgba((float *) src, w, h, dst, dst_stride);
       break;
+   case PIPE_FORMAT_Z32_FLOAT_S8X24_USCALED:
+      z32f_x24s8_get_tile_rgba((float *) src, w, h, dst, dst_stride);
+      break;
    default:
       util_format_read_4f(format,
                           dst, dst_stride * sizeof(float),
@@ -445,6 +474,12 @@ pipe_put_tile_rgba_format(struct pipe_context *pipe,
    case PIPE_FORMAT_X8Z24_UNORM:
       /*z24s8_put_tile_rgba((unsigned *) packed, w, h, p, src_stride);*/
       break;
+   case PIPE_FORMAT_Z32_FLOAT:
+      /*z32f_put_tile_rgba((unsigned *) packed, w, h, p, src_stride);*/
+      break;
+   case PIPE_FORMAT_Z32_FLOAT_S8X24_USCALED:
+      /*z32f_s8x24_put_tile_rgba((unsigned *) packed, w, h, p, src_stride);*/
+      break;
    default:
       util_format_write_4f(format,
                            p, src_stride * sizeof(float),