[PULL 29/29] target/i386: Use i128 for 128 and 256-bit loads and stores

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/i386/tcg/translate.c | 63 +++++++++++++++++--------------------
 1 file changed, 29 insertions(+), 34 deletions(-)

diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index d2061ec44a..0c81e066de 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -2918,59 +2918,54 @@ static inline void gen_stq_env_A0(DisasContext *s, int 
offset)
 
 static inline void gen_ldo_env_A0(DisasContext *s, int offset, bool align)
 {
+    MemOp atom = (s->cpuid_ext_features & CPUID_EXT_AVX
+                  ? MO_ATOM_IFALIGN : MO_ATOM_IFALIGN_PAIR);
+    MemOp mop = MO_128 | MO_LE | atom | (align ? MO_ALIGN_16 : 0);
     int mem_index = s->mem_index;
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->A0, mem_index,
-                        MO_LEUQ | (align ? MO_ALIGN_16 : 0));
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(XMMReg, XMM_Q(0)));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 8);
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(XMMReg, XMM_Q(1)));
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    tcg_gen_qemu_ld_i128(t, s->A0, mem_index, mop);
+    tcg_gen_st_i128(t, tcg_env, offset);
 }
 
 static inline void gen_sto_env_A0(DisasContext *s, int offset, bool align)
 {
+    MemOp atom = (s->cpuid_ext_features & CPUID_EXT_AVX
+                  ? MO_ATOM_IFALIGN : MO_ATOM_IFALIGN_PAIR);
+    MemOp mop = MO_128 | MO_LE | atom | (align ? MO_ALIGN_16 : 0);
     int mem_index = s->mem_index;
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(XMMReg, XMM_Q(0)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->A0, mem_index,
-                        MO_LEUQ | (align ? MO_ALIGN_16 : 0));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 8);
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(XMMReg, XMM_Q(1)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    tcg_gen_ld_i128(t, tcg_env, offset);
+    tcg_gen_qemu_st_i128(t, s->A0, mem_index, mop);
 }
 
 static void gen_ldy_env_A0(DisasContext *s, int offset, bool align)
 {
+    MemOp mop = MO_128 | MO_LE | MO_ATOM_IFALIGN_PAIR;
     int mem_index = s->mem_index;
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->A0, mem_index,
-                        MO_LEUQ | (align ? MO_ALIGN_32 : 0));
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(0)));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 8);
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(1)));
+    TCGv_i128 t0 = tcg_temp_new_i128();
+    TCGv_i128 t1 = tcg_temp_new_i128();
 
+    tcg_gen_qemu_ld_i128(t0, s->A0, mem_index, mop | (align ? MO_ALIGN_32 : 
0));
     tcg_gen_addi_tl(s->tmp0, s->A0, 16);
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(2)));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 24);
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(3)));
+    tcg_gen_qemu_ld_i128(t1, s->tmp0, mem_index, mop);
+
+    tcg_gen_st_i128(t0, tcg_env, offset + offsetof(YMMReg, YMM_X(0)));
+    tcg_gen_st_i128(t1, tcg_env, offset + offsetof(YMMReg, YMM_X(1)));
 }
 
 static void gen_sty_env_A0(DisasContext *s, int offset, bool align)
 {
+    MemOp mop = MO_128 | MO_LE | MO_ATOM_IFALIGN_PAIR;
     int mem_index = s->mem_index;
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(0)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->A0, mem_index,
-                        MO_LEUQ | (align ? MO_ALIGN_32 : 0));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 8);
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(1)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    tcg_gen_ld_i128(t, tcg_env, offset + offsetof(YMMReg, YMM_X(0)));
+    tcg_gen_qemu_st_i128(t, s->A0, mem_index, mop | (align ? MO_ALIGN_32 : 0));
     tcg_gen_addi_tl(s->tmp0, s->A0, 16);
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(2)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_addi_tl(s->tmp0, s->A0, 24);
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(3)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    tcg_gen_ld_i128(t, tcg_env, offset + offsetof(YMMReg, YMM_X(1)));
+    tcg_gen_qemu_st_i128(t, s->tmp0, mem_index, mop);
 }
 
 #include "decode-new.h"
-- 
2.34.1