target/mips/translate: Simplify PCPYH using deposit_i64()

Simplify the PCPYH (Parallel Copy Halfword) instruction by using
multiple calls to deposit_i64() which can be optimized by some
TCG backends.

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20210214175912.732946-11-f4bug@amsat.org>

diff --git a/target/mips/translate.c b/target/mips/translate.c
index d4316c1..1967c12 100644 (file)
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -24091,36 +24091,10 @@ static void gen_mmi_pcpyh(DisasContext *ctx)
         tcg_gen_movi_i64(cpu_gpr[rd], 0);
         tcg_gen_movi_i64(cpu_gpr_hi[rd], 0);
     } else {
-        TCGv_i64 t0 = tcg_temp_new();
-        TCGv_i64 t1 = tcg_temp_new();
-        uint64_t mask = (1ULL << 16) - 1;
-
-        tcg_gen_andi_i64(t0, cpu_gpr[rt], mask);
-        tcg_gen_movi_i64(t1, 0);
-        tcg_gen_or_i64(t1, t0, t1);
-        tcg_gen_shli_i64(t0, t0, 16);
-        tcg_gen_or_i64(t1, t0, t1);
-        tcg_gen_shli_i64(t0, t0, 16);
-        tcg_gen_or_i64(t1, t0, t1);
-        tcg_gen_shli_i64(t0, t0, 16);
-        tcg_gen_or_i64(t1, t0, t1);
-
-        tcg_gen_mov_i64(cpu_gpr[rd], t1);
-
-        tcg_gen_andi_i64(t0, cpu_gpr_hi[rt], mask);
-        tcg_gen_movi_i64(t1, 0);
-        tcg_gen_or_i64(t1, t0, t1);
-        tcg_gen_shli_i64(t0, t0, 16);
-        tcg_gen_or_i64(t1, t0, t1);
-        tcg_gen_shli_i64(t0, t0, 16);
-        tcg_gen_or_i64(t1, t0, t1);
-        tcg_gen_shli_i64(t0, t0, 16);
-        tcg_gen_or_i64(t1, t0, t1);
-
-        tcg_gen_mov_i64(cpu_gpr_hi[rd], t1);
-
-        tcg_temp_free(t0);
-        tcg_temp_free(t1);
+        tcg_gen_deposit_i64(cpu_gpr[rd], cpu_gpr[rt], cpu_gpr[rt], 16, 16);
+        tcg_gen_deposit_i64(cpu_gpr[rd], cpu_gpr[rd], cpu_gpr[rd], 32, 32);
+        tcg_gen_deposit_i64(cpu_gpr_hi[rd], cpu_gpr_hi[rt], cpu_gpr_hi[rt], 16, 16);
+        tcg_gen_deposit_i64(cpu_gpr_hi[rd], cpu_gpr_hi[rd], cpu_gpr_hi[rd], 32, 32);
     }
 }