prog_optimize: Add reads without writes optimization passnew-register-allocator

This pass scans programs for instructions that read registers that have
not been written and replaces these reads with a read from a constant
register with the value of zero.  This pass prevents phantom
dependencies from being introduced by the register allocator and
improves the efficiency of subsequent optimization passes.

1 files changed, 81 insertions, 0 deletions

diff --git a/src/mesa/program/prog_optimize.c b/src/mesa/program/prog_optimize.c
index b5f0fb31896..bc698fb5a06 100644
--- a/src/mesa/program/prog_optimize.c
+++ b/src/mesa/program/prog_optimize.c
@@ -30,6 +30,7 @@
 #include "program.h"
 #include "prog_instruction.h"
 #include "prog_optimize.h"
+#include "prog_parameter.h"
 #include "prog_print.h"
 
 
@@ -1225,6 +1226,85 @@ print_it(struct gl_context *ctx, struct gl_program *program, const char *txt) {
 }
 #endif
 
+/** This pass searches for registers that are read before they are written
+ * and replaces reads from these registers with a read from a constant
+ * register with the value of zero.  This pass will not change the program
+ * if it has already been run, so it only needs to be run once per program.
+ *
+ * When CMP instructions are translated from GLSL IR to Mesa IR, usually
+ * source register 1 or source register 2 is set to value of the destination
+ * register.  When the registers are reallocated by
+ * _mesa_reallocate_registers() there is the possibility of creating phantom
+ * dependencies where a source register is remapped so that it reads from a
+ * register that has been written by an instruction that is no longer live.
+ * Here is an example:
+ *
+ * 0: MUL TEMP[0], CONST[0] IN[0]
+ * 1: RCP TEMP[1], TEMP[0]
+ * 2: CMP TEMP[2], TEMP[1] CONST[0] TEMP[2]
+ * ...
+ *
+ * _mesa_reallocate_registers will remap registers 0->0, 1->1, 2->0 and
+ * the program will look like this:
+ *
+ * 0: MUL TEMP[0], CONST[0], IN[0]
+ * 1: RCP TEMP[1], TEMP[0]
+ * 2: CMP TEMP[0], TEMP[1] CONST[0] TEMP[0]
+ * ...
+ *
+ * This creates a phantom dependency, because instruction 2 now depends
+ * on the result of instruction 0 which was not the case in the original
+ * program.
+ */
+static void
+_mesa_reads_without_writes(struct gl_program * program)
+{
+   GLfloat zeroArray[4] = {0.0f, 0.0f, 0.0f, 0.0f};
+   GLuint zeroSwizzle;
+   struct prog_src_register zeroReg;
+   GLuint regWrites[REG_ALLOCATE_MAX_PROGRAM_TEMPS];
+   GLuint i;
+
+   if (dbg) {
+      printf("Optimize: Begin reads without writes\n");
+      _mesa_print_program(program);
+   }
+
+   for (i = 0; i < REG_ALLOCATE_MAX_PROGRAM_TEMPS; i++) {
+      regWrites[i] = 0;
+   }
+
+   memset(&zeroReg, 0, sizeof(zeroReg));
+   zeroReg.File = PROGRAM_CONSTANT;
+   zeroReg.Index = _mesa_add_unnamed_constant(program->Parameters, zeroArray,
+                                              1, &zeroSwizzle);
+   zeroReg.Swizzle = zeroSwizzle;
+
+   for (i = 0; i < program->NumInstructions; i++) {
+      struct prog_instruction *inst = program->Instructions + i;
+      GLuint numSrc = _mesa_num_inst_src_regs(inst->Opcode);
+      GLuint j;
+      for (j = 0; j < numSrc; j++) {
+         if (inst->SrcReg[j].File == PROGRAM_TEMPORARY) {
+            const GLuint index = inst->SrcReg[j].Index;
+            if (!inst->SrcReg[j].RelAddr
+                && !(regWrites[index] & get_src_arg_mask(inst, j, NO_MASK))) {
+               inst->SrcReg[j] = zeroReg;
+            }
+         }
+      }
+      if (inst->DstReg.File == PROGRAM_TEMPORARY) {
+         if (inst->DstReg.RelAddr) {
+            return;
+         }
+         regWrites[inst->DstReg.Index] |= inst->DstReg.WriteMask;
+      }
+   }
+   if (dbg) {
+      printf("Optimize: End reads without writes\n");
+      _mesa_print_program(program);
+   }
+}
 
 /**
  * Apply optimizations to the given program to eliminate unnecessary
@@ -1235,6 +1315,7 @@ _mesa_optimize_program(struct gl_context *ctx, struct gl_program *program)
 {
    GLboolean any_change;
 
+   _mesa_reads_without_writes(program);
    /* Stop when no modifications were output */
    do {
       any_change = GL_FALSE;