X-Git-Url: https://repo.jachan.dev/qemu.git/blobdiff_plain/fce1296f135669eca85dc42154a2a352c818ad76..c4e4b0fa598ddc9cee6ba7a06899ce0a8dae6c61:/tcg/tcg-op.c

diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index deacc63e3b..587d092238 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -23,7 +23,6 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu-common.h"
 #include "cpu.h"
 #include "exec/exec-all.h"
 #include "tcg.h"
@@ -611,9 +610,22 @@ void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
         return;
     }
 
-    mask = (1u << len) - 1;
     t1 = tcg_temp_new_i32();
 
+    if (TCG_TARGET_HAS_extract2_i32) {
+        if (ofs + len == 32) {
+            tcg_gen_shli_i32(t1, arg1, len);
+            tcg_gen_extract2_i32(ret, t1, arg2, len);
+            goto done;
+        }
+        if (ofs == 0) {
+            tcg_gen_extract2_i32(ret, arg1, arg2, len);
+            tcg_gen_rotli_i32(ret, ret, len);
+            goto done;
+        }
+    }
+
+    mask = (1u << len) - 1;
     if (ofs + len < 32) {
         tcg_gen_andi_i32(t1, arg2, mask);
         tcg_gen_shli_i32(t1, t1, ofs);
@@ -622,7 +634,7 @@ void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
     }
     tcg_gen_andi_i32(ret, arg1, ~(mask << ofs));
     tcg_gen_or_i32(ret, ret, t1);
-
+ done:
     tcg_temp_free_i32(t1);
 }
 
@@ -1078,6 +1090,16 @@ void tcg_gen_umax_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b)
     tcg_gen_movcond_i32(TCG_COND_LTU, ret, a, b, b, a);
 }
 
+void tcg_gen_abs_i32(TCGv_i32 ret, TCGv_i32 a)
+{
+    TCGv_i32 t = tcg_temp_new_i32();
+
+    tcg_gen_sari_i32(t, a, 31);
+    tcg_gen_xor_i32(ret, a, t);
+    tcg_gen_sub_i32(ret, ret, t);
+    tcg_temp_free_i32(t);
+}
+
 /* 64-bit ops */
 
 #if TCG_TARGET_REG_BITS == 32
@@ -1355,31 +1377,32 @@ static inline void tcg_gen_shifti_i64(TCGv_i64 ret, TCGv_i64 arg1,
             tcg_gen_shli_i32(TCGV_HIGH(ret), TCGV_LOW(arg1), c);
             tcg_gen_movi_i32(TCGV_LOW(ret), 0);
         }
-    } else {
-        TCGv_i32 t0, t1;
-
-        t0 = tcg_temp_new_i32();
-        t1 = tcg_temp_new_i32();
-        if (right) {
-            tcg_gen_shli_i32(t0, TCGV_HIGH(arg1), 32 - c);
-            if (arith) {
-                tcg_gen_sari_i32(t1, TCGV_HIGH(arg1), c);
-            } else {
-                tcg_gen_shri_i32(t1, TCGV_HIGH(arg1), c);
-            }
+    } else if (right) {
+        if (TCG_TARGET_HAS_extract2_i32) {
+            tcg_gen_extract2_i32(TCGV_LOW(ret),
+                                 TCGV_LOW(arg1), TCGV_HIGH(arg1), c);
+        } else {
             tcg_gen_shri_i32(TCGV_LOW(ret), TCGV_LOW(arg1), c);
-            tcg_gen_or_i32(TCGV_LOW(ret), TCGV_LOW(ret), t0);
-            tcg_gen_mov_i32(TCGV_HIGH(ret), t1);
+            tcg_gen_deposit_i32(TCGV_LOW(ret), TCGV_LOW(ret),
+                                TCGV_HIGH(arg1), 32 - c, c);
+        }
+        if (arith) {
+            tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), c);
+        } else {
+            tcg_gen_shri_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), c);
+        }
+    } else {
+        if (TCG_TARGET_HAS_extract2_i32) {
+            tcg_gen_extract2_i32(TCGV_HIGH(ret),
+                                 TCGV_LOW(arg1), TCGV_HIGH(arg1), 32 - c);
         } else {
+            TCGv_i32 t0 = tcg_temp_new_i32();
             tcg_gen_shri_i32(t0, TCGV_LOW(arg1), 32 - c);
-            /* Note: ret can be the same as arg1, so we use t1 */
-            tcg_gen_shli_i32(t1, TCGV_LOW(arg1), c);
-            tcg_gen_shli_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), c);
-            tcg_gen_or_i32(TCGV_HIGH(ret), TCGV_HIGH(ret), t0);
-            tcg_gen_mov_i32(TCGV_LOW(ret), t1);
+            tcg_gen_deposit_i32(TCGV_HIGH(ret), t0,
+                                TCGV_HIGH(arg1), c, 32 - c);
+            tcg_temp_free_i32(t0);
         }
-        tcg_temp_free_i32(t0);
-        tcg_temp_free_i32(t1);
+        tcg_gen_shli_i32(TCGV_LOW(ret), TCGV_LOW(arg1), c);
     }
 }
 
@@ -2023,9 +2046,22 @@ void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
         }
     }
 
-    mask = (1ull << len) - 1;
     t1 = tcg_temp_new_i64();
 
+    if (TCG_TARGET_HAS_extract2_i64) {
+        if (ofs + len == 64) {
+            tcg_gen_shli_i64(t1, arg1, len);
+            tcg_gen_extract2_i64(ret, t1, arg2, len);
+            goto done;
+        }
+        if (ofs == 0) {
+            tcg_gen_extract2_i64(ret, arg1, arg2, len);
+            tcg_gen_rotli_i64(ret, ret, len);
+            goto done;
+        }
+    }
+
+    mask = (1ull << len) - 1;
     if (ofs + len < 64) {
         tcg_gen_andi_i64(t1, arg2, mask);
         tcg_gen_shli_i64(t1, t1, ofs);
@@ -2034,7 +2070,7 @@ void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
     }
     tcg_gen_andi_i64(ret, arg1, ~(mask << ofs));
     tcg_gen_or_i64(ret, ret, t1);
-
+ done:
     tcg_temp_free_i64(t1);
 }
 
@@ -2521,6 +2557,16 @@ void tcg_gen_umax_i64(TCGv_i64 ret, TCGv_i64 a, TCGv_i64 b)
     tcg_gen_movcond_i64(TCG_COND_LTU, ret, a, b, b, a);
 }
 
+void tcg_gen_abs_i64(TCGv_i64 ret, TCGv_i64 a)
+{
+    TCGv_i64 t = tcg_temp_new_i64();
+
+    tcg_gen_sari_i64(t, a, 63);
+    tcg_gen_xor_i64(ret, a, t);
+    tcg_gen_sub_i64(ret, ret, t);
+    tcg_temp_free_i64(t);
+}
+
 /* Size changing operations.  */
 
 void tcg_gen_extrl_i64_i32(TCGv_i32 ret, TCGv_i64 arg)