All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stefan Brankovic <stefan.brankovic@rt-rk.com>
To: qemu-devel@nongnu.org
Cc: david@gibson.dropbear.id.au
Subject: [Qemu-devel] [PATCH v3 5/8] target/ppc: Optimize emulation of vclzd instruction
Date: Fri, 21 Jun 2019 13:07:09 +0200	[thread overview]
Message-ID: <1561115232-17155-6-git-send-email-stefan.brankovic@rt-rk.com> (raw)
In-Reply-To: <1561115232-17155-1-git-send-email-stefan.brankovic@rt-rk.com>

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 <stefan.brankovic@rt-rk.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 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 0aa1e05..3b92e3b 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -306,7 +306,6 @@ 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 1e32549..3134798 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1803,17 +1803,14 @@ 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 00896ec..1953c65 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -839,6 +839,32 @@ 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);
@@ -1355,7 +1381,7 @@ 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)
-- 
2.7.4



  parent reply	other threads:[~2019-06-21 11:22 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-21 11:07 [Qemu-devel] [PATCH v3 0/8] target/ppc: Optimize emulation of some Altivec Stefan Brankovic
2019-06-21 11:07 ` [Qemu-devel] [PATCH v3 1/8] target/ppc: Optimize emulation of lvsl and lvsr instructions Stefan Brankovic
2019-06-26 16:03   ` Richard Henderson
2019-06-21 11:07 ` [Qemu-devel] [PATCH v3 2/8] target/ppc: Optimize emulation of vsl and vsr instructions Stefan Brankovic
2019-06-21 11:07 ` [Qemu-devel] [PATCH v3 3/8] target/ppc: Optimize emulation of vpkpx instruction Stefan Brankovic
2019-06-21 11:07 ` [Qemu-devel] [PATCH v3 4/8] target/ppc: Optimize emulation of vgbbd instruction Stefan Brankovic
2019-06-21 11:07 ` Stefan Brankovic [this message]
2019-06-21 11:07 ` [Qemu-devel] [PATCH v3 6/8] target/ppc: Optimize emulation of vclzw instruction Stefan Brankovic
2019-06-21 11:07 ` [Qemu-devel] [PATCH v3 7/8] target/ppc: Optimize emulation of vclzh and vclzb instructions Stefan Brankovic
2019-06-21 11:07 ` [Qemu-devel] [PATCH v3 8/8] target/ppc: Refactor emulation of vmrgew and vmrgow instructions Stefan Brankovic

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1561115232-17155-6-git-send-email-stefan.brankovic@rt-rk.com \
    --to=stefan.brankovic@rt-rk.com \
    --cc=david@gibson.dropbear.id.au \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.