[PATCH v1 03/19] target/arm: Use tcg_gen_qemu_{st, ld}_i128 for do_fp_{st, ld}

[Richard Henderson]

While we don't require 16-byte atomicity here, using a single
larger operation simplifies the code.

Signed-off-by: Richard Henderson <richard.hender...@linaro.org>
---
 target/arm/translate-a64.c | 38 ++++++++++++++------------------------
 1 file changed, 14 insertions(+), 24 deletions(-)

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index d7d4b68328..edf92a728f 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -965,25 +965,20 @@ static void do_fp_st(DisasContext *s, int srcidx, 
TCGv_i64 tcg_addr, int size)
 
     tcg_gen_ld_i64(tmplo, cpu_env, fp_reg_offset(s, srcidx, MO_64));
 
-    if (size < 4) {
+    if (size < MO_128) {
         mop = finalize_memop(s, size);
         tcg_gen_qemu_st_i64(tmplo, tcg_addr, get_mem_index(s), mop);
     } else {
-        bool be = s->be_data == MO_BE;
-        TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
         TCGv_i64 tmphi = tcg_temp_new_i64();
+        TCGv_i128 t16 = tcg_temp_new_i128();
 
         tcg_gen_ld_i64(tmphi, cpu_env, fp_reg_hi_offset(s, srcidx));
-
-        mop = s->be_data | MO_UQ;
-        tcg_gen_qemu_st_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s),
-                            mop | (s->align_mem ? MO_ALIGN_16 : 0));
-        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
-        tcg_gen_qemu_st_i64(be ? tmplo : tmphi, tcg_hiaddr,
-                            get_mem_index(s), mop);
-
-        tcg_temp_free_i64(tcg_hiaddr);
+        tcg_gen_concat_i64_i128(t16, tmplo, tmphi);
         tcg_temp_free_i64(tmphi);
+
+        mop = finalize_memop(s, size);
+        tcg_gen_qemu_st_i128(t16, tcg_addr, get_mem_index(s), mop);
+        tcg_temp_free_i128(t16);
     }
 
     tcg_temp_free_i64(tmplo);
@@ -999,23 +994,18 @@ static void do_fp_ld(DisasContext *s, int destidx, 
TCGv_i64 tcg_addr, int size)
     TCGv_i64 tmphi = NULL;
     MemOp mop;
 
-    if (size < 4) {
+    if (size < MO_128) {
         mop = finalize_memop(s, size);
         tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), mop);
     } else {
-        bool be = s->be_data == MO_BE;
-        TCGv_i64 tcg_hiaddr;
+        TCGv_i128 t16 = tcg_temp_new_i128();
+
+        mop = finalize_memop(s, size);
+        tcg_gen_qemu_ld_i128(t16, tcg_addr, get_mem_index(s), mop);
 
         tmphi = tcg_temp_new_i64();
-        tcg_hiaddr = tcg_temp_new_i64();
-
-        mop = s->be_data | MO_UQ;
-        tcg_gen_qemu_ld_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s),
-                            mop | (s->align_mem ? MO_ALIGN_16 : 0));
-        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
-        tcg_gen_qemu_ld_i64(be ? tmplo : tmphi, tcg_hiaddr,
-                            get_mem_index(s), mop);
-        tcg_temp_free_i64(tcg_hiaddr);
+        tcg_gen_extr_i128_i64(tmplo, tmphi, t16);
+        tcg_temp_free_i128(t16);
     }
 
     tcg_gen_st_i64(tmplo, cpu_env, fp_reg_offset(s, destidx, MO_64));
-- 
2.34.1