[PATCH v2 08/69] target/arm: Convert CLZ, CLS to decodetree

[Richard Henderson]

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/translate-a64.c | 72 ++++++++++++++--------------------
 target/arm/tcg/a64.decode      |  3 ++
 2 files changed, 33 insertions(+), 42 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 1805d77f43..552b45b4e2 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -7738,6 +7738,32 @@ TRANS(REV16, gen_rr, a->rd, a->rn, a->sf ? gen_rev16_64 
: gen_rev16_32)
 TRANS(REV32, gen_rr, a->rd, a->rn, a->sf ? gen_rev32 : gen_rev_32)
 TRANS(REV64, gen_rr, a->rd, a->rn, tcg_gen_bswap64_i64)
 
+static void gen_clz32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn)
+{
+    TCGv_i32 t32 = tcg_temp_new_i32();
+
+    tcg_gen_extrl_i64_i32(t32, tcg_rn);
+    tcg_gen_clzi_i32(t32, t32, 32);
+    tcg_gen_extu_i32_i64(tcg_rd, t32);
+}
+
+static void gen_clz64(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn)
+{
+    tcg_gen_clzi_i64(tcg_rd, tcg_rn, 64);
+}
+
+static void gen_cls32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn)
+{
+    TCGv_i32 t32 = tcg_temp_new_i32();
+
+    tcg_gen_extrl_i64_i32(t32, tcg_rn);
+    tcg_gen_clrsb_i32(t32, t32);
+    tcg_gen_extu_i32_i64(tcg_rd, t32);
+}
+
+TRANS(CLZ, gen_rr, a->rd, a->rn, a->sf ? gen_clz64 : gen_clz32)
+TRANS(CLS, gen_rr, a->rd, a->rn, a->sf ? tcg_gen_clrsb_i64 : gen_cls32)
+
 /* Logical (shifted register)
  *   31  30 29 28       24 23   22 21  20  16 15    10 9    5 4    0
  * +----+-----+-----------+-------+---+------+--------+------+------+
@@ -8322,40 +8348,6 @@ static void disas_cond_select(DisasContext *s, uint32_t 
insn)
     }
 }
 
-static void handle_clz(DisasContext *s, unsigned int sf,
-                       unsigned int rn, unsigned int rd)
-{
-    TCGv_i64 tcg_rd, tcg_rn;
-    tcg_rd = cpu_reg(s, rd);
-    tcg_rn = cpu_reg(s, rn);
-
-    if (sf) {
-        tcg_gen_clzi_i64(tcg_rd, tcg_rn, 64);
-    } else {
-        TCGv_i32 tcg_tmp32 = tcg_temp_new_i32();
-        tcg_gen_extrl_i64_i32(tcg_tmp32, tcg_rn);
-        tcg_gen_clzi_i32(tcg_tmp32, tcg_tmp32, 32);
-        tcg_gen_extu_i32_i64(tcg_rd, tcg_tmp32);
-    }
-}
-
-static void handle_cls(DisasContext *s, unsigned int sf,
-                       unsigned int rn, unsigned int rd)
-{
-    TCGv_i64 tcg_rd, tcg_rn;
-    tcg_rd = cpu_reg(s, rd);
-    tcg_rn = cpu_reg(s, rn);
-
-    if (sf) {
-        tcg_gen_clrsb_i64(tcg_rd, tcg_rn);
-    } else {
-        TCGv_i32 tcg_tmp32 = tcg_temp_new_i32();
-        tcg_gen_extrl_i64_i32(tcg_tmp32, tcg_rn);
-        tcg_gen_clrsb_i32(tcg_tmp32, tcg_tmp32);
-        tcg_gen_extu_i32_i64(tcg_rd, tcg_tmp32);
-    }
-}
-
 /* Data-processing (1 source)
  *   31  30  29  28             21 20     16 15    10 9    5 4    0
  * +----+---+---+-----------------+---------+--------+------+------+
@@ -8381,14 +8373,6 @@ static void disas_data_proc_1src(DisasContext *s, 
uint32_t insn)
 #define MAP(SF, O2, O1) ((SF) | (O1 << 1) | (O2 << 7))
 
     switch (MAP(sf, opcode2, opcode)) {
-    case MAP(0, 0x00, 0x04): /* CLZ */
-    case MAP(1, 0x00, 0x04):
-        handle_clz(s, sf, rn, rd);
-        break;
-    case MAP(0, 0x00, 0x05): /* CLS */
-    case MAP(1, 0x00, 0x05):
-        handle_cls(s, sf, rn, rd);
-        break;
     case MAP(1, 0x01, 0x00): /* PACIA */
         if (s->pauth_active) {
             tcg_rd = cpu_reg(s, rd);
@@ -8542,6 +8526,10 @@ static void disas_data_proc_1src(DisasContext *s, 
uint32_t insn)
     case MAP(0, 0x00, 0x02): /* REV/REV32 */
     case MAP(1, 0x00, 0x02):
     case MAP(1, 0x00, 0x03): /* REV64 */
+    case MAP(0, 0x00, 0x04): /* CLZ */
+    case MAP(1, 0x00, 0x04):
+    case MAP(0, 0x00, 0x05): /* CLS */
+    case MAP(1, 0x00, 0x05):
         unallocated_encoding(s);
         break;
     }
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index dd44651f34..410eaa9333 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -696,6 +696,9 @@ REV16           . 10 11010110 00000 000001 ..... .....  
@rr_sf
 REV32           . 10 11010110 00000 000010 ..... .....  @rr_sf
 REV64           1 10 11010110 00000 000011 ..... .....  @rr
 
+CLZ             . 10 11010110 00000 000100 ..... .....  @rr_sf
+CLS             . 10 11010110 00000 000101 ..... .....  @rr_sf
+
 # Logical (shifted reg)
 # Add/subtract (shifted reg)
 # Add/subtract (extended reg)
-- 
2.43.0