[PATCH v2 12/29] tcg/ppc: Use power10 byte-reverse instructions

[Richard Henderson]

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

diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc
index 33f0139519..ea1734d6be 100644
--- a/tcg/ppc/tcg-target.c.inc
+++ b/tcg/ppc/tcg-target.c.inc
@@ -413,6 +413,10 @@ static bool tcg_target_const_match(int64_t val, TCGType 
type, int ct)
 #define SRAD   XO31(794)
 #define SRADI  XO31(413<<1)
 
+#define BRH    XO31(219)
+#define BRW    XO31(155)
+#define BRD    XO31(187)
+
 #define TW     XO31( 4)
 #define TRAP   (TW | TO(31))
 
@@ -748,6 +752,11 @@ static inline void tcg_out_ext16s(TCGContext *s, TCGReg 
dst, TCGReg src)
     tcg_out32(s, EXTSH | RA(dst) | RS(src));
 }
 
+static inline void tcg_out_ext16u(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    tcg_out32(s, ANDI | SAI(src, dst, 0xffff));
+}
+
 static inline void tcg_out_ext32s(TCGContext *s, TCGReg dst, TCGReg src)
 {
     tcg_out32(s, EXTSW | RA(dst) | RS(src));
@@ -793,6 +802,16 @@ static void tcg_out_bswap16(TCGContext *s, TCGReg dst, 
TCGReg src, int flags)
 {
     TCGReg tmp = dst == src ? TCG_REG_R0 : dst;
 
+    if (have_isa_3_10) {
+        tcg_out32(s, BRH | RA(dst) | RS(src));
+        if (flags & TCG_BSWAP_OS) {
+            tcg_out_ext16s(s, dst, dst);
+        } else if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            tcg_out_ext16u(s, dst, dst);
+        }
+        return;
+    }
+
     /*
      * In the following,
      *   dep(a, b, m) -> (a & ~m) | (b & m)
@@ -815,6 +834,16 @@ static void tcg_out_bswap32(TCGContext *s, TCGReg dst, 
TCGReg src, int flags)
 {
     TCGReg tmp = dst == src ? TCG_REG_R0 : dst;
 
+    if (have_isa_3_10) {
+        tcg_out32(s, BRW | RA(dst) | RS(src));
+        if (flags & TCG_BSWAP_OS) {
+            tcg_out_ext32s(s, dst, src);
+        } else if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            tcg_out_ext32u(s, dst, dst);
+        }
+        return;
+    }
+
     /*
      * Stolen from gcc's builtin_bswap32.
      * In the following,
@@ -841,6 +870,11 @@ static void tcg_out_bswap64(TCGContext *s, TCGReg dst, 
TCGReg src)
     TCGReg t0 = dst == src ? TCG_REG_R0 : dst;
     TCGReg t1 = dst == src ? dst : TCG_REG_R0;
 
+    if (have_isa_3_10) {
+        tcg_out32(s, BRD | RA(dst) | RS(src));
+        return;
+    }
+
     /*
      * In the following,
      *   dep(a, b, m) -> (a & ~m) | (b & m)
-- 
2.25.1