tcg: Eliminate one store for in-place 128-bit dup_mem

Do not store back to the exact memory from which we just loaded.

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

diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 793d4ba64c3282b1c457e404ec99cf396d74693e..fcc25b04e6bc924b5feec17f2e670768a6922e19 100644 (file)
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -1581,7 +1581,7 @@ void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
             TCGv_vec in = tcg_temp_new_vec(TCG_TYPE_V128);
 
             tcg_gen_ld_vec(in, cpu_env, aofs);
-            for (i = 0; i < oprsz; i += 16) {
+            for (i = (aofs == dofs) * 16; i < oprsz; i += 16) {
                 tcg_gen_st_vec(in, cpu_env, dofs + i);
             }
             tcg_temp_free_vec(in);
@@ -1591,7 +1591,7 @@ void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
 
             tcg_gen_ld_i64(in0, cpu_env, aofs);
             tcg_gen_ld_i64(in1, cpu_env, aofs + 8);
-            for (i = 0; i < oprsz; i += 16) {
+            for (i = (aofs == dofs) * 16; i < oprsz; i += 16) {
                 tcg_gen_st_i64(in0, cpu_env, dofs + i);
                 tcg_gen_st_i64(in1, cpu_env, dofs + i + 8);
             }