glsl: Skip making a temporary for assignments when we don't need one.

While we wish our optimization passes could identify all the cases where
we can coalesce our variables, we miss out on a lot of opportunities.

total instructions in shared programs: 1673849 -> 1673166 (-0.04%)
instructions in affected programs:     299521 -> 298838 (-0.23%)
GAINED:                                7
LOST:                                  0

Note that many programs are "hurt".  The notable ones are where we produce
unrolling in cases we didn't before (presumably just because of the lower
instruction count).  But there are also some cases where pushing things
right into the variables prevents copy propagation and tree grafting,
since we don't split our variable usage webs apart.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This commit is contained in:
Eric Anholt
2014-03-05 17:05:54 -08:00
parent dff3439fef
commit e9822f77a9
2 changed files with 123 additions and 61 deletions

View File

@@ -217,6 +217,13 @@ public:
virtual ir_rvalue *hir(exec_list *instructions,
struct _mesa_glsl_parse_state *state);
virtual void hir_no_rvalue(exec_list *instructions,
struct _mesa_glsl_parse_state *state);
ir_rvalue *do_hir(exec_list *instructions,
struct _mesa_glsl_parse_state *state,
bool needs_rvalue);
virtual void print(void) const;
enum ast_operators oper;
@@ -287,6 +294,9 @@ public:
virtual ir_rvalue *hir(exec_list *instructions,
struct _mesa_glsl_parse_state *state);
virtual void hir_no_rvalue(exec_list *instructions,
struct _mesa_glsl_parse_state *state);
private:
/**
* Is this function call actually a constructor?
@@ -359,6 +369,9 @@ public:
virtual ir_rvalue *hir(exec_list *instructions,
struct _mesa_glsl_parse_state *state);
virtual void hir_no_rvalue(exec_list *instructions,
struct _mesa_glsl_parse_state *state);
};
/**