DM: also run benches once.

Also:
  - make GrMemoryPoolBenches threadsafe
  - some tweaks to various DM code
  - rename GM::shortName() to getName() to match benches and tests

On my desktop, (289 GMs, 617 benches) x 4 configs, 227 tests takes 46s in Debug, 14s in Release.  (Still minutes faster than running tests && bench && gm.)  GPU singlethreading is definitely the limiting factor again; going to reexamine whether that's helpful to thread it again.

BUG=skia:
R=reed@google.com, bsalomon@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/178473006

git-svn-id: http://skia.googlecode.com/svn/trunk@13603 2bbb7eff-a529-9590-31e7-b0007b416f81
diff --git a/bench/SkBenchmark.h b/bench/SkBenchmark.h
index f1e317d..bf28689 100644
--- a/bench/SkBenchmark.h
+++ b/bench/SkBenchmark.h
@@ -15,10 +15,8 @@
 
 #define DEF_BENCH(code)                                                 \
 namespace {                                                             \
-class SK_MACRO_APPEND_LINE(F_CLASS) : public SkBenchmarkFactory {       \
-    virtual SkBenchmark* operator()() const SK_OVERRIDE { code; }       \
-} SK_MACRO_APPEND_LINE(g_F_);                                           \
-BenchRegistry SK_MACRO_APPEND_LINE(g_R_)(&SK_MACRO_APPEND_LINE(g_F_));  \
+static SkBenchmark* SK_MACRO_APPEND_LINE(factory)(void*) { code; }      \
+BenchRegistry SK_MACRO_APPEND_LINE(g_R_)(SK_MACRO_APPEND_LINE(factory)); \
 }
 
 /*
@@ -136,13 +134,6 @@
     typedef SkRefCnt INHERITED;
 };
 
-class SkBenchmarkFactory : public SkRefCnt {
-public:
-    // Creates a new SkBenchmark that is owned by the caller on each call.
-    virtual SkBenchmark* operator()() const = 0;
-    virtual ~SkBenchmarkFactory() {}
-};
-
-typedef SkTRegistry<SkBenchmarkFactory*> BenchRegistry;
+typedef SkTRegistry<SkBenchmark*(*)(void*)> BenchRegistry;
 
 #endif