All of lore.kernel.org
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Subject: [Qemu-devel] [PATCH v2 03/10] tcg: Add write_aofs to GVecGen4
Date: Sat,  5 Jan 2019 08:31:09 +1000	[thread overview]
Message-ID: <20190104223116.14037-4-richard.henderson@linaro.org> (raw)
In-Reply-To: <20190104223116.14037-1-richard.henderson@linaro.org>

This allows writing 2 output, 3 input operations.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/tcg-op-gvec.h |  2 ++
 tcg/tcg-op-gvec.c | 27 +++++++++++++++++++--------
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/tcg/tcg-op-gvec.h b/tcg/tcg-op-gvec.h
index d65b9d9d4c..2cb447112e 100644
--- a/tcg/tcg-op-gvec.h
+++ b/tcg/tcg-op-gvec.h
@@ -181,6 +181,8 @@ typedef struct {
     uint8_t vece;
     /* Prefer i64 to v64.  */
     bool prefer_i64;
+    /* Write aofs as a 2nd dest operand.  */
+    bool write_aofs;
 } GVecGen4;
 
 void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs,
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 81689d02f7..c10d3d7b26 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -665,7 +665,7 @@ static void expand_3_i32(uint32_t dofs, uint32_t aofs,
 
 /* Expand OPSZ bytes worth of three-operand operations using i32 elements.  */
 static void expand_4_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs,
-                         uint32_t cofs, uint32_t oprsz,
+                         uint32_t cofs, uint32_t oprsz, bool write_aofs,
                          void (*fni)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32))
 {
     TCGv_i32 t0 = tcg_temp_new_i32();
@@ -680,6 +680,9 @@ static void expand_4_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs,
         tcg_gen_ld_i32(t3, cpu_env, cofs + i);
         fni(t0, t1, t2, t3);
         tcg_gen_st_i32(t0, cpu_env, dofs + i);
+        if (write_aofs) {
+            tcg_gen_st_i32(t1, cpu_env, aofs + i);
+        }
     }
     tcg_temp_free_i32(t3);
     tcg_temp_free_i32(t2);
@@ -769,7 +772,7 @@ static void expand_3_i64(uint32_t dofs, uint32_t aofs,
 
 /* Expand OPSZ bytes worth of three-operand operations using i64 elements.  */
 static void expand_4_i64(uint32_t dofs, uint32_t aofs, uint32_t bofs,
-                         uint32_t cofs, uint32_t oprsz,
+                         uint32_t cofs, uint32_t oprsz, bool write_aofs,
                          void (*fni)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64))
 {
     TCGv_i64 t0 = tcg_temp_new_i64();
@@ -784,6 +787,9 @@ static void expand_4_i64(uint32_t dofs, uint32_t aofs, uint32_t bofs,
         tcg_gen_ld_i64(t3, cpu_env, cofs + i);
         fni(t0, t1, t2, t3);
         tcg_gen_st_i64(t0, cpu_env, dofs + i);
+        if (write_aofs) {
+            tcg_gen_st_i64(t1, cpu_env, aofs + i);
+        }
     }
     tcg_temp_free_i64(t3);
     tcg_temp_free_i64(t2);
@@ -880,7 +886,7 @@ static void expand_3_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
 /* Expand OPSZ bytes worth of four-operand operations using host vectors.  */
 static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
                          uint32_t bofs, uint32_t cofs, uint32_t oprsz,
-                         uint32_t tysz, TCGType type,
+                         uint32_t tysz, TCGType type, bool write_aofs,
                          void (*fni)(unsigned, TCGv_vec, TCGv_vec,
                                      TCGv_vec, TCGv_vec))
 {
@@ -896,6 +902,9 @@ static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
         tcg_gen_ld_vec(t3, cpu_env, cofs + i);
         fni(vece, t0, t1, t2, t3);
         tcg_gen_st_vec(t0, cpu_env, dofs + i);
+        if (write_aofs) {
+            tcg_gen_st_vec(t1, cpu_env, aofs + i);
+        }
     }
     tcg_temp_free_vec(t3);
     tcg_temp_free_vec(t2);
@@ -1187,7 +1196,7 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs,
          */
         some = QEMU_ALIGN_DOWN(oprsz, 32);
         expand_4_vec(g->vece, dofs, aofs, bofs, cofs, some,
-                     32, TCG_TYPE_V256, g->fniv);
+                     32, TCG_TYPE_V256, g->write_aofs, g->fniv);
         if (some == oprsz) {
             break;
         }
@@ -1200,18 +1209,20 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs,
         /* fallthru */
     case TCG_TYPE_V128:
         expand_4_vec(g->vece, dofs, aofs, bofs, cofs, oprsz,
-                     16, TCG_TYPE_V128, g->fniv);
+                     16, TCG_TYPE_V128, g->write_aofs, g->fniv);
         break;
     case TCG_TYPE_V64:
         expand_4_vec(g->vece, dofs, aofs, bofs, cofs, oprsz,
-                     8, TCG_TYPE_V64, g->fniv);
+                     8, TCG_TYPE_V64, g->write_aofs, g->fniv);
         break;
 
     case 0:
         if (g->fni8 && check_size_impl(oprsz, 8)) {
-            expand_4_i64(dofs, aofs, bofs, cofs, oprsz, g->fni8);
+            expand_4_i64(dofs, aofs, bofs, cofs, oprsz,
+                         g->write_aofs, g->fni8);
         } else if (g->fni4 && check_size_impl(oprsz, 4)) {
-            expand_4_i32(dofs, aofs, bofs, cofs, oprsz, g->fni4);
+            expand_4_i32(dofs, aofs, bofs, cofs, oprsz,
+                         g->write_aofs, g->fni4);
         } else {
             assert(g->fno != NULL);
             tcg_gen_gvec_4_ool(dofs, aofs, bofs, cofs,
-- 
2.17.2

  parent reply	other threads:[~2019-01-04 22:31 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-04 22:31 [Qemu-devel] [PATCH v2 00/10] tcg vector improvements Richard Henderson
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 01/10] tcg: Add logical simplifications during gvec expand Richard Henderson
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 02/10] tcg: Add gvec expanders for nand, nor, eqv Richard Henderson
2019-01-04 22:31 ` Richard Henderson [this message]
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 04/10] tcg: Add opcodes for vector saturated arithmetic Richard Henderson
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 05/10] tcg: Add opcodes for vector minmax arithmetic Richard Henderson
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 06/10] tcg/i386: Split subroutines out of tcg_expand_vec_op Richard Henderson
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 07/10] tcg/i386: Implement vector saturating arithmetic Richard Henderson
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 08/10] tcg/i386: Implement vector minmax arithmetic Richard Henderson
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 09/10] tcg/aarch64: Implement vector saturating arithmetic Richard Henderson
2019-01-04 22:31 ` [Qemu-devel] [PATCH v2 10/10] tcg/aarch64: Implement vector minmax arithmetic Richard Henderson
2019-01-07 13:11 ` [Qemu-devel] [PATCH v2 00/10] tcg vector improvements Mark Cave-Ayland
2019-01-23  5:09   ` Richard Henderson
2019-02-05 21:29     ` Mark Cave-Ayland
2019-02-06  3:37       ` Richard Henderson
2019-02-06  7:15         ` Mark Cave-Ayland
2019-02-06 15:44           ` BALATON Zoltan
2019-02-07 22:31       ` Mark Cave-Ayland

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=20190104223116.14037-4-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --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.