Also handle undefined behaviour for sqrt(x) where x < 0
and rsq(x) where x <= 0.
This gives us some reduction in instruction count on three
Dungeon Defenders shaders as they are doing: max(exp(x), 0)
v2: Change to use new IS_CONSTANT() macro
Fix high unintenionally not being returned
Add some air for readability
Comment on the exploit of undefined behavior
Constify mem_ctx
---
src/glsl/opt_minmax.cpp | 31 +++++++++++++++++++++++++++++++
1 file changed, 31 insertions(+)
diff --git a/src/glsl/opt_minmax.cpp b/src/glsl/opt_minmax.cpp
index 56805c0..2faa3c3 100644
--- a/src/glsl/opt_minmax.cpp
+++ b/src/glsl/opt_minmax.cpp
@@ -274,9 +274,40 @@ get_range(ir_rvalue *rval)
minmax_range r0;
minmax_range r1;
+ void *const mem_ctx = ralloc_parent(rval);
+
+ ir_constant *low = NULL;
+ ir_constant *high = NULL;
+
if (expr) {
switch (expr->operation) {
+ case ir_unop_exp:
+ case ir_unop_exp2:
+ case ir_unop_sqrt:
+ case ir_unop_rsq:
+ r0 = get_range(expr->operands[0]);
+
+ /* The spec says sqrt is undefined if x < 0
+ * We can use this to set the range to whatever we want
+ */
+ if (expr->operation == ir_unop_sqrt &&
+ IS_CONSTANT(r0.high, <, 0.0f))
+ high = new(mem_ctx) ir_constant(0.0f);
+
+ /* The spec says rsq is undefined if x <= 0
+ * We can use this to set the range to whatever we want
+ */
+ if (expr->operation == ir_unop_rsq &&
+ IS_CONSTANT(r0.high, <=, 0.0f))
+ high = new(mem_ctx) ir_constant(0.0f);
+
+ /* TODO: If we know, i.e, the lower range of the operand
+ * we can calculate the lower range
+ */
+ low = new(mem_ctx) ir_constant(0.0f);
+ return minmax_range(low, high);
+
case ir_binop_min:
case ir_binop_max:
r0 = get_range(expr->operands[0]);
--
2.2.1
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
