target/hppa: Optimize UADDCM with no condition

With r1 as zero is by far the most common usage of UADDCM, as the
easiest way to invert a register.  The compiler does occasionally
use the addition step as well, and we can simplify that to avoid
a temp and write directly into the destination.

Tested-by: Helge Deller <deller@gmx.de>
Reviewed-by: Helge Deller <deller@gmx.de>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

diff --git a/target/hppa/translate.c b/target/hppa/translate.c
index a3f425d8616e21acd8a469276648b8cbadd41d9d..3fc3e7754c77c154e4732660f26a9b50a4a5365c 100644 (file)
--- a/target/hppa/translate.c
+++ b/target/hppa/translate.c
@@ -2763,9 +2763,29 @@ static bool do_uaddcm(DisasContext *ctx, arg_rrr_cf_d *a, bool is_tc)
 {
     TCGv_i64 tcg_r1, tcg_r2, tmp;
 
-    if (a->cf) {
-        nullify_over(ctx);
+    if (a->cf == 0) {
+        tcg_r2 = load_gpr(ctx, a->r2);
+        tmp = dest_gpr(ctx, a->t);
+
+        if (a->r1 == 0) {
+            /* UADDCM r0,src,dst is the common idiom for dst = ~src. */
+            tcg_gen_not_i64(tmp, tcg_r2);
+        } else {
+            /*
+             * Recall that r1 - r2 == r1 + ~r2 + 1.
+             * Thus r1 + ~r2 == r1 - r2 - 1,
+             * which does not require an extra temporary.
+             */
+            tcg_r1 = load_gpr(ctx, a->r1);
+            tcg_gen_sub_i64(tmp, tcg_r1, tcg_r2);
+            tcg_gen_subi_i64(tmp, tmp, 1);
+        }
+        save_gpr(ctx, a->t, tmp);
+        cond_free(&ctx->null_cond);
+        return true;
     }
+
+    nullify_over(ctx);
     tcg_r1 = load_gpr(ctx, a->r1);
     tcg_r2 = load_gpr(ctx, a->r2);
     tmp = tcg_temp_new_i64();