[Qemu-ppc] [PULL 10/42] target/ppc: Optimize emulation of vclzd instruction

[David Gibson]

From: Stefan Brankovic <address@hidden>

Optimize Altivec instruction vclzd (Vector Count Leading Zeros Doubleword).
This instruction counts the number of leading zeros of each doubleword element
in source register and places result in the appropriate doubleword element of
destination register.

Using tcg-s count leading zeros instruction two times(once for each
doubleword element of source register vB) and placing result in
appropriate doubleword element of destination register vD.

Signed-off-by: Stefan Brankovic <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
Message-Id: <address@hidden>
Signed-off-by: David Gibson <address@hidden>
---
 target/ppc/helper.h                 |  1 -
 target/ppc/int_helper.c             |  3 ---
 target/ppc/translate/vmx-impl.inc.c | 28 +++++++++++++++++++++++++++-
 3 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 9b486a0c37..e203f76bf1 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -311,7 +311,6 @@ DEF_HELPER_4(vctsxs, void, env, avr, avr, i32)
 DEF_HELPER_2(vclzb, void, avr, avr)
 DEF_HELPER_2(vclzh, void, avr, avr)
 DEF_HELPER_2(vclzw, void, avr, avr)
-DEF_HELPER_2(vclzd, void, avr, avr)
 DEF_HELPER_2(vctzb, void, avr, avr)
 DEF_HELPER_2(vctzh, void, avr, avr)
 DEF_HELPER_2(vctzw, void, avr, avr)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index a265cb07c5..b82765db33 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1820,17 +1820,14 @@ VUPK(lsw, s64, s32, UPKLO)
 #define clzb(v) ((v) ? clz32((uint32_t)(v) << 24) : 8)
 #define clzh(v) ((v) ? clz32((uint32_t)(v) << 16) : 16)
 #define clzw(v) clz32((v))
-#define clzd(v) clz64((v))
 
 VGENERIC_DO(clzb, u8)
 VGENERIC_DO(clzh, u16)
 VGENERIC_DO(clzw, u32)
-VGENERIC_DO(clzd, u64)
 
 #undef clzb
 #undef clzh
 #undef clzw
-#undef clzd
 
 #define ctzb(v) ((v) ? ctz32(v) : 8)
 #define ctzh(v) ((v) ? ctz32(v) : 16)
diff --git a/target/ppc/translate/vmx-impl.inc.c 
b/target/ppc/translate/vmx-impl.inc.c
index 13153352e4..3372c2c3d3 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -742,6 +742,32 @@ static void trans_vgbbd(DisasContext *ctx)
     tcg_temp_free_i64(avr[1]);
 }
 
+/*
+ * vclzd VRT,VRB - Vector Count Leading Zeros Doubleword
+ *
+ * Counting the number of leading zero bits of each doubleword element in 
source
+ * register and placing result in appropriate doubleword element of destination
+ * register.
+ */
+static void trans_vclzd(DisasContext *ctx)
+{
+    int VT = rD(ctx->opcode);
+    int VB = rB(ctx->opcode);
+    TCGv_i64 avr = tcg_temp_new_i64();
+
+    /* high doubleword */
+    get_avr64(avr, VB, true);
+    tcg_gen_clzi_i64(avr, avr, 64);
+    set_avr64(VT, avr, true);
+
+    /* low doubleword */
+    get_avr64(avr, VB, false);
+    tcg_gen_clzi_i64(avr, avr, 64);
+    set_avr64(VT, avr, false);
+
+    tcg_temp_free_i64(avr);
+}
+
 GEN_VXFORM(vmuloub, 4, 0);
 GEN_VXFORM(vmulouh, 4, 1);
 GEN_VXFORM(vmulouw, 4, 2);
@@ -1258,7 +1284,7 @@ GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23)
 GEN_VXFORM_NOA(vclzb, 1, 28)
 GEN_VXFORM_NOA(vclzh, 1, 29)
 GEN_VXFORM_NOA(vclzw, 1, 30)
-GEN_VXFORM_NOA(vclzd, 1, 31)
+GEN_VXFORM_TRANS(vclzd, 1, 31)
 GEN_VXFORM_NOA_2(vnegw, 1, 24, 6)
 GEN_VXFORM_NOA_2(vnegd, 1, 24, 7)
 GEN_VXFORM_NOA_2(vextsb2w, 1, 24, 16)
-- 
2.21.0