i965/fs: Lower 32x32 bit multiplication on BXT.

[mesa.git] / src / mesa / drivers / dri / i965 / brw_fs_copy_propagation.cpp

diff --git a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
index 54e9114fe6ba05a3781126e9f2aabb9ff63a0b8b..5445ad55670c943cc05f7be5cad56ac3895737ea 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
@@ -339,6 +339,14 @@ fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry)
    if (entry->src.stride * inst->src[arg].stride > 4)
       return false;
 
+   /* Bail if the instruction type is larger than the execution type of the
+    * copy, what implies that each channel is reading multiple channels of the
+    * destination of the copy, and simply replacing the sources would give a
+    * program with different semantics.
+    */
+   if (type_sz(entry->dst.type) < type_sz(inst->src[arg].type))
+      return false;
+
    /* Bail if the result of composing both strides cannot be expressed
     * as another stride. This avoids, for example, trying to transform
     * this:
@@ -526,6 +534,7 @@ fs_visitor::try_constant_propagate(fs_inst *inst, acp_entry *entry)
 
       case BRW_OPCODE_MACH:
       case BRW_OPCODE_MUL:
+      case SHADER_OPCODE_MULH:
       case BRW_OPCODE_ADD:
       case BRW_OPCODE_OR:
       case BRW_OPCODE_AND: