[Qemu-devel] [PULL v2 for-2.8 5/9] tcg: Add tcg_gen_mulsu2_{i32, i64, tl}

[Richard Henderson <rth@twiddle.net>]

This multiply has one signed input and one unsigned input,
producing the full double-width result.

Signed-off-by: Richard Henderson <rth@twiddle.net>
Message-Id: <1475011433-24456-2-git-send-email-rth@twiddle.net>
---
 tcg/tcg-op.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 tcg/tcg-op.h |  4 ++++
 2 files changed, 47 insertions(+)

diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index bb2bfee..4d125df 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -678,6 +678,33 @@ void tcg_gen_muls2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2)
     }
 }
 
+void tcg_gen_mulsu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
+        TCGv_i32 t2 = tcg_temp_new_i32();
+        tcg_gen_mulu2_i32(t0, t1, arg1, arg2);
+        /* Adjust for negative input for the signed arg1.  */
+        tcg_gen_sari_i32(t2, arg1, 31);
+        tcg_gen_and_i32(t2, t2, arg2);
+        tcg_gen_sub_i32(rh, t1, t2);
+        tcg_gen_mov_i32(rl, t0);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+        tcg_temp_free_i32(t2);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        tcg_gen_ext_i32_i64(t0, arg1);
+        tcg_gen_extu_i32_i64(t1, arg2);
+        tcg_gen_mul_i64(t0, t0, t1);
+        tcg_gen_extr_i64_i32(rl, rh, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
 void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg)
 {
     if (TCG_TARGET_HAS_ext8s_i32) {
@@ -1748,6 +1775,22 @@ void tcg_gen_muls2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2)
     }
 }
 
+void tcg_gen_mulsu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+    TCGv_i64 t2 = tcg_temp_new_i64();
+    tcg_gen_mulu2_i64(t0, t1, arg1, arg2);
+    /* Adjust for negative input for the signed arg1.  */
+    tcg_gen_sari_i64(t2, arg1, 63);
+    tcg_gen_and_i64(t2, t2, arg2);
+    tcg_gen_sub_i64(rh, t1, t2);
+    tcg_gen_mov_i64(rl, t0);
+    tcg_temp_free_i64(t0);
+    tcg_temp_free_i64(t1);
+    tcg_temp_free_i64(t2);
+}
+
 /* Size changing operations.  */
 
 void tcg_gen_extrl_i64_i32(TCGv_i32 ret, TCGv_i64 arg)
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index 89b59e8..6d044b7 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -306,6 +306,7 @@ void tcg_gen_sub2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al,
                       TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh);
 void tcg_gen_mulu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_muls2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_mulsu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_ext16s_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg);
@@ -482,6 +483,7 @@ void tcg_gen_sub2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al,
                       TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh);
 void tcg_gen_mulu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_muls2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_mulsu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_ext8s_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_ext16s_i64(TCGv_i64 ret, TCGv_i64 arg);
@@ -956,6 +958,7 @@ void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp);
 #define tcg_gen_sub2_tl tcg_gen_sub2_i64
 #define tcg_gen_mulu2_tl tcg_gen_mulu2_i64
 #define tcg_gen_muls2_tl tcg_gen_muls2_i64
+#define tcg_gen_mulsu2_tl tcg_gen_mulsu2_i64
 #define tcg_gen_atomic_cmpxchg_tl tcg_gen_atomic_cmpxchg_i64
 #define tcg_gen_atomic_xchg_tl tcg_gen_atomic_xchg_i64
 #define tcg_gen_atomic_fetch_add_tl tcg_gen_atomic_fetch_add_i64
@@ -1043,6 +1046,7 @@ void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp);
 #define tcg_gen_sub2_tl tcg_gen_sub2_i32
 #define tcg_gen_mulu2_tl tcg_gen_mulu2_i32
 #define tcg_gen_muls2_tl tcg_gen_muls2_i32
+#define tcg_gen_mulsu2_tl tcg_gen_mulsu2_i32
 #define tcg_gen_atomic_cmpxchg_tl tcg_gen_atomic_cmpxchg_i32
 #define tcg_gen_atomic_xchg_tl tcg_gen_atomic_xchg_i32
 #define tcg_gen_atomic_fetch_add_tl tcg_gen_atomic_fetch_add_i32
-- 
2.7.4