target-ppc: Clean up mullwo

Simplify the implementation of mullwo.  For 64 bit CPUs, the result is
the concatenation of the upper and lower parts of the muls2_i32 operation,
which may be slightly better than deposit.  For 32 bit CPUs, the lower part
of the muls_i32 operation is moved into the target GPR.

Signed-off-by: Tom Musta <tommusta@gmail.com>
Suggested-by: Richard Henderson <rth@twiddle.net>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Alexander Graf <agraf@suse.de>

diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index ced295f079268559f6e589addd998ecb4d75f5e5..106263477a1f035e85b4ca754e78265279121af4 100644 (file)
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -1150,19 +1150,14 @@ static void gen_mullwo(DisasContext *ctx)
 {
     TCGv_i32 t0 = tcg_temp_new_i32();
     TCGv_i32 t1 = tcg_temp_new_i32();
-#if defined(TARGET_PPC64)
-    TCGv_i64 t2 = tcg_temp_new_i64();
-#endif
 
     tcg_gen_trunc_tl_i32(t0, cpu_gpr[rA(ctx->opcode)]);
     tcg_gen_trunc_tl_i32(t1, cpu_gpr[rB(ctx->opcode)]);
     tcg_gen_muls2_i32(t0, t1, t0, t1);
-    tcg_gen_ext_i32_tl(cpu_gpr[rD(ctx->opcode)], t0);
 #if defined(TARGET_PPC64)
-    tcg_gen_ext_i32_tl(t2, t1);
-    tcg_gen_deposit_i64(cpu_gpr[rD(ctx->opcode)],
-                        cpu_gpr[rD(ctx->opcode)], t2, 32, 32);
-    tcg_temp_free(t2);
+    tcg_gen_concat_i32_i64(cpu_gpr[rD(ctx->opcode)], t0, t1);
+#else
+    tcg_gen_mov_i32(cpu_gpr[rD(ctx->opcode)], t0);
 #endif
 
     tcg_gen_sari_i32(t0, t0, 31);