Merge git://github.com/hw-claudio/qemu-aarch64-queue into tcg-next

[qemu.git] / tcg / tcg-op.h

diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index dac3b4ed9f42e94c72600d2ef791fcb0d79b6bdb..364964d8d4d2e0fd90e478fda90b65e3d3618d91 100644 (file)
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -731,8 +731,14 @@ static inline void tcg_gen_div_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
 
 static inline void tcg_gen_rem_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
 {
-    if (TCG_TARGET_HAS_div_i32) {
+    if (TCG_TARGET_HAS_rem_i32) {
         tcg_gen_op3_i32(INDEX_op_rem_i32, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_op3_i32(INDEX_op_div_i32, t0, arg1, arg2);
+        tcg_gen_mul_i32(t0, t0, arg2);
+        tcg_gen_sub_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
     } else if (TCG_TARGET_HAS_div2_i32) {
         TCGv_i32 t0 = tcg_temp_new_i32();
         tcg_gen_sari_i32(t0, arg1, 31);
@@ -769,8 +775,14 @@ static inline void tcg_gen_divu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
 
 static inline void tcg_gen_remu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
 {
-    if (TCG_TARGET_HAS_div_i32) {
+    if (TCG_TARGET_HAS_rem_i32) {
         tcg_gen_op3_i32(INDEX_op_remu_i32, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_op3_i32(INDEX_op_divu_i32, t0, arg1, arg2);
+        tcg_gen_mul_i32(t0, t0, arg2);
+        tcg_gen_sub_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
     } else if (TCG_TARGET_HAS_div2_i32) {
         TCGv_i32 t0 = tcg_temp_new_i32();
         tcg_gen_movi_i32(t0, 0);
@@ -1361,8 +1373,14 @@ static inline void tcg_gen_div_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
 
 static inline void tcg_gen_rem_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
 {
-    if (TCG_TARGET_HAS_div_i64) {
+    if (TCG_TARGET_HAS_rem_i64) {
         tcg_gen_op3_i64(INDEX_op_rem_i64, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_op3_i64(INDEX_op_div_i64, t0, arg1, arg2);
+        tcg_gen_mul_i64(t0, t0, arg2);
+        tcg_gen_sub_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
     } else if (TCG_TARGET_HAS_div2_i64) {
         TCGv_i64 t0 = tcg_temp_new_i64();
         tcg_gen_sari_i64(t0, arg1, 63);
@@ -1399,8 +1417,14 @@ static inline void tcg_gen_divu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
 
 static inline void tcg_gen_remu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
 {
-    if (TCG_TARGET_HAS_div_i64) {
+    if (TCG_TARGET_HAS_rem_i64) {
         tcg_gen_op3_i64(INDEX_op_remu_i64, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_op3_i64(INDEX_op_divu_i64, t0, arg1, arg2);
+        tcg_gen_mul_i64(t0, t0, arg2);
+        tcg_gen_sub_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
     } else if (TCG_TARGET_HAS_div2_i64) {
         TCGv_i64 t0 = tcg_temp_new_i64();
         tcg_gen_movi_i64(t0, 0);
@@ -2188,9 +2212,9 @@ static inline void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1,
 
 #if TCG_TARGET_REG_BITS == 32
     if (ofs >= 32) {
-        tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg1));
         tcg_gen_deposit_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1),
                             TCGV_LOW(arg2), ofs - 32, len);
+        tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg1));
         return;
     }
     if (ofs + len <= 32) {
@@ -2396,6 +2420,26 @@ static inline void tcg_gen_muls2_i32(TCGv_i32 rl, TCGv_i32 rh,
         tcg_gen_op4_i32(INDEX_op_muls2_i32, rl, rh, arg1, arg2);
         /* Allow the optimizer room to replace muls2 with two moves.  */
         tcg_gen_op0(INDEX_op_nop);
+    } else if (TCG_TARGET_REG_BITS == 32 && TCG_TARGET_HAS_mulu2_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
+        TCGv_i32 t2 = tcg_temp_new_i32();
+        TCGv_i32 t3 = tcg_temp_new_i32();
+        tcg_gen_op4_i32(INDEX_op_mulu2_i32, t0, t1, arg1, arg2);
+        /* Allow the optimizer room to replace mulu2 with two moves.  */
+        tcg_gen_op0(INDEX_op_nop);
+        /* Adjust for negative inputs.  */
+        tcg_gen_sari_i32(t2, arg1, 31);
+        tcg_gen_sari_i32(t3, arg2, 31);
+        tcg_gen_and_i32(t2, t2, arg2);
+        tcg_gen_and_i32(t3, t3, arg1);
+        tcg_gen_sub_i32(rh, t1, t2);
+        tcg_gen_sub_i32(rh, rh, t3);
+        tcg_gen_mov_i32(rl, t0);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+        tcg_temp_free_i32(t2);
+        tcg_temp_free_i32(t3);
     } else {
         TCGv_i64 t0 = tcg_temp_new_i64();
         TCGv_i64 t1 = tcg_temp_new_i64();
@@ -2455,6 +2499,26 @@ static inline void tcg_gen_mulu2_i64(TCGv_i64 rl, TCGv_i64 rh,
         tcg_gen_op4_i64(INDEX_op_mulu2_i64, rl, rh, arg1, arg2);
         /* Allow the optimizer room to replace mulu2 with two moves.  */
         tcg_gen_op0(INDEX_op_nop);
+    } else if (TCG_TARGET_HAS_mulu2_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        TCGv_i64 t2 = tcg_temp_new_i64();
+        TCGv_i64 t3 = tcg_temp_new_i64();
+        tcg_gen_op4_i64(INDEX_op_mulu2_i64, t0, t1, arg1, arg2);
+        /* Allow the optimizer room to replace mulu2 with two moves.  */
+        tcg_gen_op0(INDEX_op_nop);
+        /* Adjust for negative inputs.  */
+        tcg_gen_sari_i64(t2, arg1, 63);
+        tcg_gen_sari_i64(t3, arg2, 63);
+        tcg_gen_and_i64(t2, t2, arg2);
+        tcg_gen_and_i64(t3, t3, arg1);
+        tcg_gen_sub_i64(rh, t1, t2);
+        tcg_gen_sub_i64(rh, rh, t3);
+        tcg_gen_mov_i64(rl, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+        tcg_temp_free_i64(t2);
+        tcg_temp_free_i64(t3);
     } else {
         TCGv_i64 t0 = tcg_temp_new_i64();
         int sizemask = 0;