All of lore.kernel.org
 help / color / mirror / Atom feed
From: Aleksandar Markovic <aleksandar.markovic@rt-rk.com>
To: qemu-devel@nongnu.org
Cc: arikalo@wavecomp.com
Subject: [PATCH v2 07/20] target/mips: msa: Split helpers for <NLOC|NLZC>.<B|H|W|D>
Date: Wed, 25 Sep 2019 14:45:59 +0200	[thread overview]
Message-ID: <1569415572-19635-8-git-send-email-aleksandar.markovic@rt-rk.com> (raw)
In-Reply-To: <1569415572-19635-1-git-send-email-aleksandar.markovic@rt-rk.com>

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Achieves clearer code and slightly better performance.

Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
---
 target/mips/helper.h     |  14 +++-
 target/mips/msa_helper.c | 170 +++++++++++++++++++++++++++++++++++++++--------
 target/mips/translate.c  |  30 ++++++++-
 3 files changed, 181 insertions(+), 33 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index 51f0e1c..d709083 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -777,6 +777,18 @@ DEF_HELPER_FLAGS_3(wrdsp, 0, void, tl, tl, env)
 DEF_HELPER_FLAGS_2(rddsp, 0, tl, tl, env)
 
 /* MIPS SIMD Architecture */
+
+DEF_HELPER_3(msa_nloc_b, void, env, i32, i32)
+DEF_HELPER_3(msa_nloc_h, void, env, i32, i32)
+DEF_HELPER_3(msa_nloc_w, void, env, i32, i32)
+DEF_HELPER_3(msa_nloc_d, void, env, i32, i32)
+
+DEF_HELPER_3(msa_nlzc_b, void, env, i32, i32)
+DEF_HELPER_3(msa_nlzc_h, void, env, i32, i32)
+DEF_HELPER_3(msa_nlzc_w, void, env, i32, i32)
+DEF_HELPER_3(msa_nlzc_d, void, env, i32, i32)
+
+
 DEF_HELPER_4(msa_andi_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ori_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_nori_b, void, env, i32, i32, i32)
@@ -935,8 +947,6 @@ DEF_HELPER_4(msa_bmz_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_bsel_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_fill_df, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_pcnt_df, void, env, i32, i32, i32)
-DEF_HELPER_4(msa_nloc_df, void, env, i32, i32, i32)
-DEF_HELPER_4(msa_nlzc_df, void, env, i32, i32, i32)
 
 DEF_HELPER_4(msa_copy_s_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_copy_s_h, void, env, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index f24061e..8c27c1b 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -65,7 +65,147 @@
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Bit Count group helpers here */
+static inline int64_t msa_nlzc_df(uint32_t df, int64_t arg)
+{
+    uint64_t x, y;
+    int n, c;
+
+    x = UNSIGNED(arg, df);
+    n = DF_BITS(df);
+    c = DF_BITS(df) / 2;
+
+    do {
+        y = x >> c;
+        if (y != 0) {
+            n = n - c;
+            x = y;
+        }
+        c = c >> 1;
+    } while (c != 0);
+
+    return n - x;
+}
+
+static inline int64_t msa_nloc_df(uint32_t df, int64_t arg)
+{
+    return msa_nlzc_df(df, UNSIGNED((~arg), df));
+}
+
+void helper_msa_nloc_b(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    pwd->b[0]  = msa_nloc_df(DF_BYTE, pws->b[0]);
+    pwd->b[1]  = msa_nloc_df(DF_BYTE, pws->b[1]);
+    pwd->b[2]  = msa_nloc_df(DF_BYTE, pws->b[2]);
+    pwd->b[3]  = msa_nloc_df(DF_BYTE, pws->b[3]);
+    pwd->b[4]  = msa_nloc_df(DF_BYTE, pws->b[4]);
+    pwd->b[5]  = msa_nloc_df(DF_BYTE, pws->b[5]);
+    pwd->b[6]  = msa_nloc_df(DF_BYTE, pws->b[6]);
+    pwd->b[7]  = msa_nloc_df(DF_BYTE, pws->b[7]);
+    pwd->b[8]  = msa_nloc_df(DF_BYTE, pws->b[8]);
+    pwd->b[9]  = msa_nloc_df(DF_BYTE, pws->b[9]);
+    pwd->b[10] = msa_nloc_df(DF_BYTE, pws->b[10]);
+    pwd->b[11] = msa_nloc_df(DF_BYTE, pws->b[11]);
+    pwd->b[12] = msa_nloc_df(DF_BYTE, pws->b[12]);
+    pwd->b[13] = msa_nloc_df(DF_BYTE, pws->b[13]);
+    pwd->b[14] = msa_nloc_df(DF_BYTE, pws->b[14]);
+    pwd->b[15] = msa_nloc_df(DF_BYTE, pws->b[15]);
+}
+
+void helper_msa_nloc_h(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    pwd->h[0]  = msa_nloc_df(DF_HALF, pws->h[0]);
+    pwd->h[1]  = msa_nloc_df(DF_HALF, pws->h[1]);
+    pwd->h[2]  = msa_nloc_df(DF_HALF, pws->h[2]);
+    pwd->h[3]  = msa_nloc_df(DF_HALF, pws->h[3]);
+    pwd->h[4]  = msa_nloc_df(DF_HALF, pws->h[4]);
+    pwd->h[5]  = msa_nloc_df(DF_HALF, pws->h[5]);
+    pwd->h[6]  = msa_nloc_df(DF_HALF, pws->h[6]);
+    pwd->h[7]  = msa_nloc_df(DF_HALF, pws->h[7]);
+}
+
+void helper_msa_nloc_w(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    pwd->w[0]  = msa_nloc_df(DF_WORD, pws->w[0]);
+    pwd->w[1]  = msa_nloc_df(DF_WORD, pws->w[1]);
+    pwd->w[2]  = msa_nloc_df(DF_WORD, pws->w[2]);
+    pwd->w[3]  = msa_nloc_df(DF_WORD, pws->w[3]);
+}
+
+void helper_msa_nloc_d(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    pwd->d[0]  = msa_nloc_df(DF_DOUBLE, pws->d[0]);
+    pwd->d[1]  = msa_nloc_df(DF_DOUBLE, pws->d[1]);
+}
+
+void helper_msa_nlzc_b(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    pwd->b[0]  = msa_nlzc_df(DF_BYTE, pws->b[0]);
+    pwd->b[1]  = msa_nlzc_df(DF_BYTE, pws->b[1]);
+    pwd->b[2]  = msa_nlzc_df(DF_BYTE, pws->b[2]);
+    pwd->b[3]  = msa_nlzc_df(DF_BYTE, pws->b[3]);
+    pwd->b[4]  = msa_nlzc_df(DF_BYTE, pws->b[4]);
+    pwd->b[5]  = msa_nlzc_df(DF_BYTE, pws->b[5]);
+    pwd->b[6]  = msa_nlzc_df(DF_BYTE, pws->b[6]);
+    pwd->b[7]  = msa_nlzc_df(DF_BYTE, pws->b[7]);
+    pwd->b[8]  = msa_nlzc_df(DF_BYTE, pws->b[8]);
+    pwd->b[9]  = msa_nlzc_df(DF_BYTE, pws->b[9]);
+    pwd->b[10] = msa_nlzc_df(DF_BYTE, pws->b[10]);
+    pwd->b[11] = msa_nlzc_df(DF_BYTE, pws->b[11]);
+    pwd->b[12] = msa_nlzc_df(DF_BYTE, pws->b[12]);
+    pwd->b[13] = msa_nlzc_df(DF_BYTE, pws->b[13]);
+    pwd->b[14] = msa_nlzc_df(DF_BYTE, pws->b[14]);
+    pwd->b[15] = msa_nlzc_df(DF_BYTE, pws->b[15]);
+}
+
+void helper_msa_nlzc_h(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    pwd->h[0]  = msa_nlzc_df(DF_HALF, pws->h[0]);
+    pwd->h[1]  = msa_nlzc_df(DF_HALF, pws->h[1]);
+    pwd->h[2]  = msa_nlzc_df(DF_HALF, pws->h[2]);
+    pwd->h[3]  = msa_nlzc_df(DF_HALF, pws->h[3]);
+    pwd->h[4]  = msa_nlzc_df(DF_HALF, pws->h[4]);
+    pwd->h[5]  = msa_nlzc_df(DF_HALF, pws->h[5]);
+    pwd->h[6]  = msa_nlzc_df(DF_HALF, pws->h[6]);
+    pwd->h[7]  = msa_nlzc_df(DF_HALF, pws->h[7]);
+}
+
+void helper_msa_nlzc_w(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    pwd->w[0]  = msa_nlzc_df(DF_WORD, pws->w[0]);
+    pwd->w[1]  = msa_nlzc_df(DF_WORD, pws->w[1]);
+    pwd->w[2]  = msa_nlzc_df(DF_WORD, pws->w[2]);
+    pwd->w[3]  = msa_nlzc_df(DF_WORD, pws->w[3]);
+}
+
+void helper_msa_nlzc_d(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    pwd->d[0]  = msa_nlzc_df(DF_DOUBLE, pws->d[0]);
+    pwd->d[1]  = msa_nlzc_df(DF_DOUBLE, pws->d[1]);
+}
 
 
 /*
@@ -2524,32 +2664,6 @@ static inline int64_t msa_pcnt_df(uint32_t df, int64_t arg)
     return x;
 }
 
-static inline int64_t msa_nlzc_df(uint32_t df, int64_t arg)
-{
-    uint64_t x, y;
-    int n, c;
-
-    x = UNSIGNED(arg, df);
-    n = DF_BITS(df);
-    c = DF_BITS(df) / 2;
-
-    do {
-        y = x >> c;
-        if (y != 0) {
-            n = n - c;
-            x = y;
-        }
-        c = c >> 1;
-    } while (c != 0);
-
-    return n - x;
-}
-
-static inline int64_t msa_nloc_df(uint32_t df, int64_t arg)
-{
-    return msa_nlzc_df(df, UNSIGNED((~arg), df));
-}
-
 void helper_msa_fill_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
                         uint32_t rs)
 {
@@ -2633,8 +2747,6 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df,         \
     }                                                                   \
 }
 
-MSA_UNOP_DF(nlzc)
-MSA_UNOP_DF(nloc)
 MSA_UNOP_DF(pcnt)
 #undef MSA_UNOP_DF
 
diff --git a/target/mips/translate.c b/target/mips/translate.c
index cc5af2a..6de4609 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28962,10 +28962,36 @@ static void gen_msa_2r(CPUMIPSState *env, DisasContext *ctx)
         gen_helper_msa_pcnt_df(cpu_env, tdf, twd, tws);
         break;
     case OPC_NLOC_df:
-        gen_helper_msa_nloc_df(cpu_env, tdf, twd, tws);
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_nloc_b(cpu_env, twd, tws);
+            break;
+        case DF_HALF:
+            gen_helper_msa_nloc_h(cpu_env, twd, tws);
+            break;
+        case DF_WORD:
+            gen_helper_msa_nloc_w(cpu_env, twd, tws);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_nloc_d(cpu_env, twd, tws);
+            break;
+        }
         break;
     case OPC_NLZC_df:
-        gen_helper_msa_nlzc_df(cpu_env, tdf, twd, tws);
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_nlzc_b(cpu_env, twd, tws);
+            break;
+        case DF_HALF:
+            gen_helper_msa_nlzc_h(cpu_env, twd, tws);
+            break;
+        case DF_WORD:
+            gen_helper_msa_nlzc_w(cpu_env, twd, tws);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_nlzc_d(cpu_env, twd, tws);
+            break;
+        }
         break;
     default:
         MIPS_INVAL("MSA instruction");
-- 
2.7.4



  parent reply	other threads:[~2019-09-25 12:57 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-25 12:45 [PATCH v2 00/20] target/mips: Misc cleanups for September/October 2019 Aleksandar Markovic
2019-09-25 12:45 ` [PATCH v2 01/20] target/mips: Clean up helper.c Aleksandar Markovic
2019-09-25 15:27   ` Philippe Mathieu-Daudé
2019-09-27  4:32     ` Aleksandar Markovic
2019-09-27  8:55       ` Philippe Mathieu-Daudé
2019-09-27 12:03       ` Markus Armbruster
2019-09-27 12:22         ` Peter Maydell
2019-09-27 13:11           ` Aleksandar Markovic
2019-09-28 14:54             ` Markus Armbruster
2019-09-25 12:45 ` [PATCH v2 02/20] target/mips: Clean up internal.h Aleksandar Markovic
2019-09-25 15:07   ` Philippe Mathieu-Daudé
2019-09-25 12:45 ` [PATCH v2 03/20] target/mips: Clean up kvm_mips.h Aleksandar Markovic
2019-09-25 15:08   ` Philippe Mathieu-Daudé
2019-09-25 12:45 ` [PATCH v2 04/20] target/mips: Clean up mips-defs.h Aleksandar Markovic
2019-09-25 15:10   ` Philippe Mathieu-Daudé
2019-09-25 12:45 ` [PATCH v2 05/20] target/mips: Clean up op_helper.c Aleksandar Markovic
2019-09-25 15:24   ` Philippe Mathieu-Daudé
2019-09-25 12:45 ` [PATCH v2 06/20] target/mips: Clean up translate.c Aleksandar Markovic
2019-09-25 12:45 ` Aleksandar Markovic [this message]
2019-09-25 12:46 ` [PATCH v2 08/20] target/mips: msa: Split helpers for PCNT.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 09/20] target/mips: msa: Split helpers for BINS<L|R>.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 10/20] target/mips: msa: Unroll loops and demacro <BMNZ|BMZ|BSEL>.V Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 11/20] target/mips: msa: Split helpers for B<CLR|NEG|SEL>.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 12/20] target/mips: msa: Split helpers for AVE_<S|U>.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 13/20] target/mips: msa: Split helpers for AVER_<S|U>.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 14/20] target/mips: msa: Split helpers for CEQ.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 15/20] target/mips: msa: Split helpers for CLE_<S|U>.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 16/20] target/mips: msa: Split helpers for CLT_<S|U>.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 17/20] target/mips: msa: Split helpers for DIV_<S|U>.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 18/20] target/mips: msa: Split helpers for MOD_<S|U>.<B|H|W|D> Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 19/20] target/mips: msa: Simplify and move helper for MOVE.V Aleksandar Markovic
2019-09-25 12:46 ` [PATCH v2 20/20] target/mips: msa: Move helpers for <AND|NOR|OR|XOR>.V Aleksandar Markovic
2019-09-25 14:09 ` [EXTERNAL][PATCH v2 00/20] target/mips: Misc cleanups for September/October 2019 Aleksandar Rikalo
2019-09-25 14:13 ` Aleksandar Rikalo
2019-10-01 15:26 ` [PATCH " Aleksandar Markovic

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=1569415572-19635-8-git-send-email-aleksandar.markovic@rt-rk.com \
    --to=aleksandar.markovic@rt-rk.com \
    --cc=arikalo@wavecomp.com \
    --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.