nir: Allow opt_peephole_sel to be more aggressive in flattening IFs.

VC4 was running into a major performance regression from enabling control
flow in the glmark2 conditionals test, because of short if statements
containing an ffract.

This pass seems like it was was trying to ensure that we only flattened
IFs that should be entirely a win by guaranteeing that there would be
fewer bcsels than there were MOVs otherwise.  However, if the number of
ALU ops is small, we can avoid the overhead of branching (which itself
costs cycles) and still get a win, even if it means moving real
instructions out of the THEN/ELSE blocks.

For now, just turn on aggressive flattening on vc4.  i965 will need some
tuning to avoid regressions.  It does looks like this may be useful to
replace freedreno code.

Improves glmark2 -b conditionals:fragment-steps=5:vertex-steps=0 from 47
fps to 95 fps on vc4.

vc4 shader-db:
total instructions in shared programs: 101282 -> 99543 (-1.72%)
instructions in affected programs:     17365 -> 15626 (-10.01%)
total uniforms in shared programs: 31295 -> 31172 (-0.39%)
uniforms in affected programs:     3580 -> 3457 (-3.44%)
total estimated cycles in shared programs: 225182 -> 223746 (-0.64%)
estimated cycles in affected programs:     26085 -> 24649 (-5.51%)

v2: Update shader-db output.

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com> (v1)

src/compiler/nir/nir.h

@@ -2600,7 +2600,7 @@ bool nir_opt_dead_cf(nir_shader *shader);
 
 bool nir_opt_gcm(nir_shader *shader, bool value_number);
 
-bool nir_opt_peephole_select(nir_shader *shader);
+bool nir_opt_peephole_select(nir_shader *shader, unsigned limit);
 
 bool nir_opt_remove_phis(nir_shader *shader);
 

src/compiler/nir/nir_opt_peephole_select.c

@@ -32,23 +32,33 @@
  * Implements a small peephole optimization that looks for
  *
  * if (cond) {
- *    <empty>
+ *    <then SSA defs>
  * } else {
- *    <empty>
+ *    <else SSA defs>
  * }
  * phi
  * ...
  * phi
  *
- * and replaces it with a series of selects.  It can also handle the case
- * where, instead of being empty, the if may contain some move operations
- * whose only use is one of the following phi nodes.  This happens all the
- * time when the SSA form comes from a conditional assignment with a
- * swizzle.
+ * and replaces it with:
+ *
+ * <then SSA defs>
+ * <else SSA defs>
+ * bcsel
+ * ...
+ * bcsel
+ *
+ * where the SSA defs are ALU operations or other cheap instructions (not
+ * texturing, for example).
+ *
+ * If the number of ALU operations in the branches is greater than the limit
+ * parameter, then the optimization is skipped.  In limit=0 mode, the SSA defs
+ * must only be MOVs which we expect to get copy-propagated away once they're
+ * out of the inner blocks.
  */
 
 static bool
-block_check_for_allowed_instrs(nir_block *block)
+block_check_for_allowed_instrs(nir_block *block, unsigned *count, bool alu_ok)
 {
    nir_foreach_instr(instr, block) {
       switch (instr->type) {
@@ -67,6 +77,11 @@ block_check_for_allowed_instrs(nir_block *block)
             }
             break;
 
+         case nir_intrinsic_load_uniform:
+            if (!alu_ok)
+               return false;
+            break;
+
          default:
             return false;
          }
@@ -89,20 +104,26 @@ block_check_for_allowed_instrs(nir_block *block)
          case nir_op_vec2:
          case nir_op_vec3:
          case nir_op_vec4:
-            /* It must be a move-like operation. */
             break;
          default:
+            if (!alu_ok) {
+               /* It must be a move-like operation. */
                return false;
             }
-
-         /* Can't handle saturate */
-         if (mov->dest.saturate)
-            return false;
+            break;
+         }
 
          /* It must be SSA */
          if (!mov->dest.dest.is_ssa)
             return false;
 
+         if (alu_ok) {
+            (*count)++;
+         } else {
+            /* Can't handle saturate */
+            if (mov->dest.saturate)
+               return false;
+
             /* It cannot have any if-uses */
             if (!list_empty(&mov->dest.dest.ssa.if_uses))
                return false;
@@ -113,6 +134,7 @@ block_check_for_allowed_instrs(nir_block *block)
                    use->parent_instr->block != block->successors[0])
                   return false;
             }
+         }
          break;
       }
 
@@ -125,7 +147,7 @@ block_check_for_allowed_instrs(nir_block *block)
 }
 
 static bool
-nir_opt_peephole_select_block(nir_block *block, void *mem_ctx)
+nir_opt_peephole_select_block(nir_block *block, void *mem_ctx, unsigned limit)
 {
    if (nir_cf_node_is_first(&block->cf_node))
       return false;
@@ -147,8 +169,12 @@ nir_opt_peephole_select_block(nir_block *block, void *mem_ctx)
    nir_block *else_block = nir_cf_node_as_block(else_node);
 
    /* ... and those blocks must only contain "allowed" instructions. */
-   if (!block_check_for_allowed_instrs(then_block) ||
-       !block_check_for_allowed_instrs(else_block))
+   unsigned count = 0;
+   if (!block_check_for_allowed_instrs(then_block, &count, limit != 0) ||
+       !block_check_for_allowed_instrs(else_block, &count, limit != 0))
+      return false;
+
+   if (count > limit)
       return false;
 
    /* At this point, we know that the previous CFG node is an if-then
@@ -212,13 +238,13 @@ nir_opt_peephole_select_block(nir_block *block, void *mem_ctx)
 }
 
 static bool
-nir_opt_peephole_select_impl(nir_function_impl *impl)
+nir_opt_peephole_select_impl(nir_function_impl *impl, unsigned limit)
 {
    void *mem_ctx = ralloc_parent(impl);
    bool progress = false;
 
    nir_foreach_block_safe(block, impl) {
-      progress |= nir_opt_peephole_select_block(block, mem_ctx);
+      progress |= nir_opt_peephole_select_block(block, mem_ctx, limit);
    }
 
    if (progress)
@@ -228,13 +254,13 @@ nir_opt_peephole_select_impl(nir_function_impl *impl)
 }
 
 bool
-nir_opt_peephole_select(nir_shader *shader)
+nir_opt_peephole_select(nir_shader *shader, unsigned limit)
 {
    bool progress = false;
 
    nir_foreach_function(function, shader) {
       if (function->impl)
-         progress |= nir_opt_peephole_select_impl(function->impl);
+         progress |= nir_opt_peephole_select_impl(function->impl, limit);
    }
 
    return progress;

src/gallium/drivers/vc4/vc4_program.c

@@ -1430,7 +1430,7 @@ vc4_optimize_nir(struct nir_shader *s)
                 NIR_PASS(progress, s, nir_opt_dce);
                 NIR_PASS(progress, s, nir_opt_dead_cf);
                 NIR_PASS(progress, s, nir_opt_cse);
-                NIR_PASS(progress, s, nir_opt_peephole_select);
+                NIR_PASS(progress, s, nir_opt_peephole_select, 8);
                 NIR_PASS(progress, s, nir_opt_algebraic);
                 NIR_PASS(progress, s, nir_opt_constant_folding);
                 NIR_PASS(progress, s, nir_opt_undef);

src/mesa/drivers/dri/i965/brw_nir.c

@@ -416,7 +416,7 @@ nir_optimize(nir_shader *nir, bool is_scalar)
       OPT(nir_copy_prop);
       OPT(nir_opt_dce);
       OPT(nir_opt_cse);
-      OPT(nir_opt_peephole_select);
+      OPT(nir_opt_peephole_select, 0);
       OPT(nir_opt_algebraic);
       OPT(nir_opt_constant_folding);
       OPT(nir_opt_dead_cf);