[PATCH 09/12] tcg/tcg-op: Add tcg_gen_hrev32_i64() and tcg_gen_hrev_i64()

[Philippe Mathieu-Daudé]

tcg_gen_hrev32_i64() is similar to tcg_gen_hrev64_i64() but
only modifies the lower 32-bit of a 64-bit value.

tcg_gen_hrev_i64() can be used when we don't know at build
time whether to clear the 32 high bits of the value or not.

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
 docs/devel/tcg-ops.rst      |  4 +++
 include/tcg/tcg-op-common.h |  2 ++
 include/tcg/tcg-op.h        |  2 ++
 tcg/tcg-op.c                | 49 +++++++++++++++++++++++++++----------
 4 files changed, 44 insertions(+), 13 deletions(-)

diff --git a/docs/devel/tcg-ops.rst b/docs/devel/tcg-ops.rst
index e8a2f8aacc..3a8104929c 100644
--- a/docs/devel/tcg-ops.rst
+++ b/docs/devel/tcg-ops.rst
@@ -496,6 +496,10 @@ Misc
 
      - | Byteswap each halfword within a 32/64-bit value.
 
+   * - hrev32_i64 *t0*, *t1*
+
+     - | Byteswap each halfword on the low bits of a 64-bit value.
+
    * - hswap_i32/i64 *t0*, *t1*
 
      - | Swap 16-bit halfwords within a 32/64-bit value.
diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h
index a9184caf9d..eb327ed964 100644
--- a/include/tcg/tcg-op-common.h
+++ b/include/tcg/tcg-op-common.h
@@ -562,7 +562,9 @@ void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int 
flags);
 void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_hswap_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_hrev32_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_hrev64_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_hrev_i64(TCGv_i64 ret, TCGv_i64 arg, int is64);
 void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h
index d63683c47b..3ac1d13b19 100644
--- a/include/tcg/tcg-op.h
+++ b/include/tcg/tcg-op.h
@@ -225,6 +225,7 @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64)
 #define tcg_gen_bswap_tl tcg_gen_bswap64_i64
 #define tcg_gen_hswap_tl tcg_gen_hswap_i64
 #define tcg_gen_wswap_tl tcg_gen_wswap_i64
+#define tcg_gen_hrev32_tl tcg_gen_hrev32_i64
 #define tcg_gen_concat_tl_i64 tcg_gen_concat32_i64
 #define tcg_gen_extr_i64_tl tcg_gen_extr32_i64
 #define tcg_gen_andc_tl tcg_gen_andc_i64
@@ -340,6 +341,7 @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64)
 #define tcg_gen_bswap32_tl(D, S, F) tcg_gen_bswap32_i32(D, S)
 #define tcg_gen_bswap_tl tcg_gen_bswap32_i32
 #define tcg_gen_hswap_tl tcg_gen_hswap_i32
+#define tcg_gen_hrev32_tl tcg_gen_hrev32_i32
 #define tcg_gen_concat_tl_i64 tcg_gen_concat_i32_i64
 #define tcg_gen_extr_i64_tl tcg_gen_extr_i64_i32
 #define tcg_gen_andc_tl tcg_gen_andc_i32
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index 310acce410..75892e91ef 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -1931,6 +1931,41 @@ void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg)
     tcg_gen_rotli_i64(ret, arg, 32);
 }
 
+/*
+ * hrev_i64: Byteswap each halfwords within a 64-bit value.
+ *           If %is64 is not set, the 32 high bits are zeroed.
+ *
+ * Byte pattern:  hrev_i64(xxxxabcd, 0) -> ....badc
+ *                hrev_i64(abcdefgh, 1) -> badcfehg
+ */
+void tcg_gen_hrev_i64(TCGv_i64 ret, TCGv_i64 arg, int is64)
+{
+    TCGv_i64 mask = tcg_constant_i64(is64 ? 0x00ff00ff00ff00ffull : 
0x00ff00ff);
+    TCGv_i64 t1 = tcg_temp_ebb_new_i64();
+    TCGv_i64 t2 = tcg_temp_ebb_new_i64();
+
+                                        /*        is64=0      is64=1  */
+                                        /* arg = xxxxabcd    abcdefgh */
+    tcg_gen_shri_i64(t1, arg, 8);       /*  t1 = .xxxxabc    .abcdefg */
+    tcg_gen_and_i64(t2, t1, mask);      /*  t2 = .....a.c    .a.c.e.g */
+    tcg_gen_and_i64(t1, arg, mask);     /*  t1 = .....b.d    .b.d.f.h */
+    tcg_gen_shli_i64(t1, t1, 8);        /*  t1 = ....b.d.    b.d.f.h. */
+    tcg_gen_or_i64(ret, t1, t2);        /* ret = ....badc    badcfehg */
+
+    tcg_temp_free_i64(t1);
+    tcg_temp_free_i64(t2);
+}
+
+/*
+ * hrev32_i64: Byteswap each halfword on the low bits of a 64-bit value.
+ *
+ * Byte pattern:  hrev32_i64(xxxxabcd) -> ....badc
+ */
+void tcg_gen_hrev32_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    tcg_gen_hrev_i64(ret, arg, false);
+}
+
 /*
  * hrev64_i64: Byteswap each halfwords within a 64-bit value.
  *
@@ -1938,19 +1973,7 @@ void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg)
  */
 void tcg_gen_hrev64_i64(TCGv_i64 ret, TCGv_i64 arg)
 {
-    TCGv_i64 mask = tcg_constant_i64(0x00ff00ff00ff00ffull);
-    TCGv_i64 t1 = tcg_temp_ebb_new_i64();
-    TCGv_i64 t2 = tcg_temp_ebb_new_i64();
-
-                                        /* arg = abcdefgh */
-    tcg_gen_shri_i64(t1, arg, 8);       /*  t1 = .abcdefg */
-    tcg_gen_and_i64(t2, t1, mask);      /*  t2 = .a.c.e.g */
-    tcg_gen_and_i64(t1, arg, mask);     /*  t1 = .b.d.f.h */
-    tcg_gen_shli_i64(t1, t1, 8);        /*  t1 = b.d.f.h. */
-    tcg_gen_or_i64(ret, t1, t2);        /* ret = badcfehg */
-
-    tcg_temp_free_i64(t1);
-    tcg_temp_free_i64(t2);
+    tcg_gen_hrev_i64(ret, arg, true);
 }
 
 void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg)
-- 
2.41.0