qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Subject: [PATCH 41/48] tcg/optimize: Sink commutative operand swapping into fold functions
Date: Sun, 29 Aug 2021 23:24:44 -0700	[thread overview]
Message-ID: <20210830062451.639572-42-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210830062451.639572-1-richard.henderson@linaro.org>

Most of these are handled by creating a fold_const2_commutative
to handle all of the binary operators.  The rest were already
handled on a case-by-case basis in the switch, and have their
own fold function in which to place the call.

We now have only one major switch on TCGOpcode.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/optimize.c | 128 ++++++++++++++++++++++---------------------------
 1 file changed, 56 insertions(+), 72 deletions(-)

diff --git a/tcg/optimize.c b/tcg/optimize.c
index ba1e5631c3..a66ac77c29 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -695,6 +695,12 @@ static bool fold_const2(OptContext *ctx, TCGOp *op)
     return false;
 }
 
+static bool fold_const2_commutative(OptContext *ctx, TCGOp *op)
+{
+    swap_commutative(op->args[0], &op->args[1], &op->args[2]);
+    return fold_const2(ctx, op);
+}
+
 static bool fold_masks(OptContext *ctx, TCGOp *op)
 {
     uint64_t a_mask = ctx->a_mask;
@@ -831,7 +837,7 @@ static bool fold_xx_to_x(OptContext *ctx, TCGOp *op)
 
 static bool fold_add(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_x(ctx, op, 0)) {
         return true;
     }
@@ -890,6 +896,9 @@ static bool fold_addsub2(OptContext *ctx, TCGOp *op, bool add)
 
 static bool fold_add2(OptContext *ctx, TCGOp *op)
 {
+    swap_commutative(op->args[0], &op->args[2], &op->args[4]);
+    swap_commutative(op->args[1], &op->args[3], &op->args[5]);
+
     return fold_addsub2(ctx, op, true);
 }
 
@@ -897,7 +906,7 @@ static bool fold_and(OptContext *ctx, TCGOp *op)
 {
     uint64_t z1, z2;
 
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_i(ctx, op, 0) ||
         fold_xi_to_x(ctx, op, -1) ||
         fold_xx_to_x(ctx, op)) {
@@ -949,8 +958,13 @@ static bool fold_andc(OptContext *ctx, TCGOp *op)
 static bool fold_brcond(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[2];
-    int i = do_constant_folding_cond(ctx->type, op->args[0], op->args[1], cond);
+    int i;
 
+    if (swap_commutative(-1, &op->args[0], &op->args[1])) {
+        op->args[2] = cond = tcg_swap_cond(cond);
+    }
+
+    i = do_constant_folding_cond(ctx->type, op->args[0], op->args[1], cond);
     if (i == 0) {
         tcg_op_remove(ctx->tcg, op);
         return true;
@@ -965,10 +979,14 @@ static bool fold_brcond(OptContext *ctx, TCGOp *op)
 static bool fold_brcond2(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[4];
-    int i = do_constant_folding_cond2(&op->args[0], &op->args[2], cond);
     TCGArg label = op->args[5];
-    int inv = 0;
+    int i, inv = 0;
 
+    if (swap_commutative2(&op->args[0], &op->args[2])) {
+        op->args[4] = cond = tcg_swap_cond(cond);
+    }
+
+    i = do_constant_folding_cond2(&op->args[0], &op->args[2], cond);
     if (i == 0) {
         goto do_brcond_false;
     } else if (i > 0) {
@@ -1215,7 +1233,7 @@ static bool fold_dup2(OptContext *ctx, TCGOp *op)
 
 static bool fold_eqv(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_x(ctx, op, -1) ||
         fold_xi_to_not(ctx, op, 0)) {
         return true;
@@ -1378,8 +1396,20 @@ static bool fold_movcond(OptContext *ctx, TCGOp *op)
 {
     TCGOpcode opc = op->opc;
     TCGCond cond = op->args[5];
-    int i = do_constant_folding_cond(opc, op->args[1], op->args[2], cond);
+    int i;
 
+    if (swap_commutative(-1, &op->args[1], &op->args[2])) {
+        op->args[5] = cond = tcg_swap_cond(cond);
+    }
+    /*
+     * Canonicalize the "false" input reg to match the destination reg so
+     * that the tcg backend can implement a "move if true" operation.
+     */
+    if (swap_commutative(op->args[0], &op->args[4], &op->args[3])) {
+        op->args[5] = cond = tcg_invert_cond(cond);
+    }
+
+    i = do_constant_folding_cond(opc, op->args[1], op->args[2], cond);
     if (i >= 0) {
         return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[4 - i]);
     }
@@ -1407,7 +1437,7 @@ static bool fold_movcond(OptContext *ctx, TCGOp *op)
 
 static bool fold_multiply(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_i(ctx, op, 0)) {
         return true;
     }
@@ -1416,6 +1446,8 @@ static bool fold_multiply(OptContext *ctx, TCGOp *op)
 
 static bool fold_multiply2(OptContext *ctx, TCGOp *op)
 {
+    swap_commutative(op->args[0], &op->args[2], &op->args[3]);
+
     if (arg_is_const(op->args[2]) && arg_is_const(op->args[3])) {
         uint64_t a = arg_info(op->args[2])->val;
         uint64_t b = arg_info(op->args[3])->val;
@@ -1459,7 +1491,7 @@ static bool fold_multiply2(OptContext *ctx, TCGOp *op)
 
 static bool fold_nand(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_not(ctx, op, -1)) {
         return true;
     }
@@ -1488,7 +1520,7 @@ static bool fold_neg(OptContext *ctx, TCGOp *op)
 
 static bool fold_nor(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_not(ctx, op, 0)) {
         return true;
     }
@@ -1508,7 +1540,7 @@ static bool fold_not(OptContext *ctx, TCGOp *op)
 
 static bool fold_or(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_x(ctx, op, 0) ||
         fold_xx_to_x(ctx, op)) {
         return true;
@@ -1554,8 +1586,13 @@ static bool fold_qemu_st(OptContext *ctx, TCGOp *op)
 static bool fold_setcond(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[3];
-    int i = do_constant_folding_cond(op->opc, op->args[1], op->args[2], cond);
+    int i;
 
+    if (swap_commutative(op->args[0], &op->args[1], &op->args[2])) {
+        op->args[3] = cond = tcg_swap_cond(cond);
+    }
+
+    i = do_constant_folding_cond(op->opc, op->args[1], op->args[2], cond);
     if (i >= 0) {
         return tcg_opt_gen_movi(ctx, op, op->args[0], i);
     }
@@ -1567,9 +1604,13 @@ static bool fold_setcond(OptContext *ctx, TCGOp *op)
 static bool fold_setcond2(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[5];
-    int i = do_constant_folding_cond2(&op->args[1], &op->args[3], cond);
-    int inv = 0;
+    int i, inv = 0;
 
+    if (swap_commutative2(&op->args[1], &op->args[3])) {
+        op->args[5] = cond = tcg_swap_cond(cond);
+    }
+
+    i = do_constant_folding_cond2(&op->args[1], &op->args[3], cond);
     if (i >= 0) {
         goto do_setcond_const;
     }
@@ -1747,7 +1788,7 @@ static bool fold_tcg_ld(OptContext *ctx, TCGOp *op)
 
 static bool fold_xor(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xx_to_i(ctx, op, 0) ||
         fold_xi_to_x(ctx, op, 0) ||
         fold_xi_to_not(ctx, op, -1)) {
@@ -1800,63 +1841,6 @@ void tcg_optimize(TCGContext *s)
             ctx.type = TCG_TYPE_I32;
         }
 
-        /* For commutative operations make constant second argument */
-        switch (opc) {
-        CASE_OP_32_64_VEC(add):
-        CASE_OP_32_64_VEC(mul):
-        CASE_OP_32_64_VEC(and):
-        CASE_OP_32_64_VEC(or):
-        CASE_OP_32_64_VEC(xor):
-        CASE_OP_32_64(eqv):
-        CASE_OP_32_64(nand):
-        CASE_OP_32_64(nor):
-        CASE_OP_32_64(muluh):
-        CASE_OP_32_64(mulsh):
-            swap_commutative(op->args[0], &op->args[1], &op->args[2]);
-            break;
-        CASE_OP_32_64(brcond):
-            if (swap_commutative(-1, &op->args[0], &op->args[1])) {
-                op->args[2] = tcg_swap_cond(op->args[2]);
-            }
-            break;
-        CASE_OP_32_64(setcond):
-            if (swap_commutative(op->args[0], &op->args[1], &op->args[2])) {
-                op->args[3] = tcg_swap_cond(op->args[3]);
-            }
-            break;
-        CASE_OP_32_64(movcond):
-            if (swap_commutative(-1, &op->args[1], &op->args[2])) {
-                op->args[5] = tcg_swap_cond(op->args[5]);
-            }
-            /* For movcond, we canonicalize the "false" input reg to match
-               the destination reg so that the tcg backend can implement
-               a "move if true" operation.  */
-            if (swap_commutative(op->args[0], &op->args[4], &op->args[3])) {
-                op->args[5] = tcg_invert_cond(op->args[5]);
-            }
-            break;
-        CASE_OP_32_64(add2):
-            swap_commutative(op->args[0], &op->args[2], &op->args[4]);
-            swap_commutative(op->args[1], &op->args[3], &op->args[5]);
-            break;
-        CASE_OP_32_64(mulu2):
-        CASE_OP_32_64(muls2):
-            swap_commutative(op->args[0], &op->args[2], &op->args[3]);
-            break;
-        case INDEX_op_brcond2_i32:
-            if (swap_commutative2(&op->args[0], &op->args[2])) {
-                op->args[4] = tcg_swap_cond(op->args[4]);
-            }
-            break;
-        case INDEX_op_setcond2_i32:
-            if (swap_commutative2(&op->args[1], &op->args[3])) {
-                op->args[5] = tcg_swap_cond(op->args[5]);
-            }
-            break;
-        default:
-            break;
-        }
-
         /* Assume all bits affected, and no bits known zero. */
         ctx.a_mask = -1;
         ctx.z_mask = -1;
-- 
2.25.1



  parent reply	other threads:[~2021-08-30  7:06 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-30  6:24 [PATCH 00/48] tcg: optimize redundant sign extensions Richard Henderson
2021-08-30  6:24 ` [PATCH 01/48] tcg/optimize: Rename "mask" to "z_mask" Richard Henderson
2021-08-30  9:15   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 02/48] tcg/optimize: Split out OptContext Richard Henderson
2021-08-30  6:24 ` [PATCH 03/48] tcg/optimize: Remove do_default label Richard Henderson
2021-08-30  6:24 ` [PATCH 04/48] tcg/optimize: Change tcg_opt_gen_{mov,movi} interface Richard Henderson
2021-08-30  6:24 ` [PATCH 05/48] tcg/optimize: Move prev_mb into OptContext Richard Henderson
2021-08-30  6:24 ` [PATCH 06/48] tcg/optimize: Split out init_arguments Richard Henderson
2021-08-30  9:17   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 07/48] tcg/optimize: Split out copy_propagate Richard Henderson
2021-08-30  9:18   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 08/48] tcg/optimize: Split out fold_call Richard Henderson
2021-08-30  6:24 ` [PATCH 09/48] tcg/optimize: Drop nb_oargs, nb_iargs locals Richard Henderson
2021-08-30  6:24 ` [PATCH 10/48] tcg/optimize: Change fail return for do_constant_folding_cond* Richard Henderson
2021-08-30  6:24 ` [PATCH 11/48] tcg/optimize: Return true from tcg_opt_gen_{mov,movi} Richard Henderson
2021-08-30  9:20   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 12/48] tcg/optimize: Split out finish_folding Richard Henderson
2021-08-30  6:24 ` [PATCH 13/48] tcg/optimize: Use a boolean to avoid a mass of continues Richard Henderson
2021-08-30  9:23   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 14/48] tcg/optimize: Split out fold_mb, fold_qemu_{ld,st} Richard Henderson
2021-08-30  6:24 ` [PATCH 15/48] tcg/optimize: Split out fold_const{1,2} Richard Henderson
2021-08-30  6:24 ` [PATCH 16/48] tcg/optimize: Split out fold_setcond2 Richard Henderson
2021-08-30  6:24 ` [PATCH 17/48] tcg/optimize: Split out fold_brcond2 Richard Henderson
2021-08-30  6:24 ` [PATCH 18/48] tcg/optimize: Split out fold_brcond Richard Henderson
2021-08-30  6:24 ` [PATCH 19/48] tcg/optimize: Split out fold_setcond Richard Henderson
2021-08-30  6:24 ` [PATCH 20/48] tcg/optimize: Split out fold_mulu2_i32 Richard Henderson
2021-08-30  6:24 ` [PATCH 21/48] tcg/optimize: Split out fold_addsub2_i32 Richard Henderson
2021-08-30  6:24 ` [PATCH 22/48] tcg/optimize: Split out fold_movcond Richard Henderson
2021-08-30  6:24 ` [PATCH 23/48] tcg/optimize: Split out fold_extract2 Richard Henderson
2021-08-30  6:24 ` [PATCH 24/48] tcg/optimize: Split out fold_extract, fold_sextract Richard Henderson
2021-08-30  6:24 ` [PATCH 25/48] tcg/optimize: Split out fold_deposit Richard Henderson
2021-08-30  6:24 ` [PATCH 26/48] tcg/optimize: Split out fold_count_zeros Richard Henderson
2021-08-30  6:24 ` [PATCH 27/48] tcg/optimize: Split out fold_bswap Richard Henderson
2021-08-30 21:17   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 28/48] tcg/optimize: Split out fold_dup, fold_dup2 Richard Henderson
2021-08-30  6:24 ` [PATCH 29/48] tcg/optimize: Split out fold_mov Richard Henderson
2021-08-30 21:57   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 30/48] tcg/optimize: Split out fold_xx_to_i Richard Henderson
2021-08-30 21:56   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 31/48] tcg/optimize: Split out fold_xx_to_x Richard Henderson
2021-08-30 21:55   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 32/48] tcg/optimize: Split out fold_xi_to_i Richard Henderson
2021-08-30 21:53   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 33/48] tcg/optimize: Add type to OptContext Richard Henderson
2021-08-30  6:24 ` [PATCH 34/48] tcg/optimize: Split out fold_to_not Richard Henderson
2021-08-30  6:24 ` [PATCH 35/48] tcg/optimize: Split out fold_sub_to_neg Richard Henderson
2021-08-30  6:24 ` [PATCH 36/48] tcg/optimize: Split out fold_xi_to_x Richard Henderson
2021-08-30  6:24 ` [PATCH 37/48] tcg/optimize: Split out fold_ix_to_i Richard Henderson
2021-08-30  6:24 ` [PATCH 38/48] tcg/optimize: Split out fold_masks Richard Henderson
2021-08-30  6:24 ` [PATCH 39/48] tcg/optimize: Expand fold_mulu2_i32 to all 4-arg multiplies Richard Henderson
2021-08-30  6:24 ` [PATCH 40/48] tcg/optimize: Expand fold_addsub2_i32 to 64-bit ops Richard Henderson
2021-08-30 21:47   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` Richard Henderson [this message]
2021-08-30  6:24 ` [PATCH 42/48] tcg/optimize: Add more simplifications for orc Richard Henderson
2021-08-30  6:24 ` [PATCH 43/48] tcg/optimize: Stop forcing z_mask to "garbage" for 32-bit values Richard Henderson
2021-08-30  6:24 ` [PATCH 44/48] tcg/optimize: Optimize sign extensions Richard Henderson
2021-08-30  6:24 ` [PATCH 45/48] tcg/optimize: Propagate sign info for logical operations Richard Henderson
2021-08-30 21:49   ` Philippe Mathieu-Daudé
2021-08-30  6:24 ` [PATCH 46/48] tcg/optimize: Propagate sign info for setcond Richard Henderson
2021-08-30  6:24 ` [PATCH 47/48] tcg/optimize: Propagate sign info for bit counting Richard Henderson
2021-08-30  6:24 ` [PATCH 48/48] tcg/optimize: Propagate sign info for shifting Richard Henderson
2021-08-30 22:00 ` [PATCH 00/48] tcg: optimize redundant sign extensions Philippe Mathieu-Daudé
2021-08-31  3:50   ` Richard Henderson

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=20210830062451.639572-42-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).