qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: luis.pires@eldorado.org.br, alex.bennee@linaro.org
Subject: [PATCH v3 44/48] tcg/optimize: Optimize sign extensions
Date: Thu, 21 Oct 2021 14:05:35 -0700	[thread overview]
Message-ID: <20211021210539.825582-45-richard.henderson@linaro.org> (raw)
In-Reply-To: <20211021210539.825582-1-richard.henderson@linaro.org>

Certain targets, like riscv, produce signed 32-bit results.
This can lead to lots of redundant extensions as values are
manipulated.

Begin by tracking only the obvious sign-extensions, and
converting them to simple copies when possible.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/optimize.c | 129 ++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 105 insertions(+), 24 deletions(-)

diff --git a/tcg/optimize.c b/tcg/optimize.c
index 89117dd420..cf3c9d6b12 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -43,6 +43,7 @@ typedef struct TempOptInfo {
     TCGTemp *next_copy;
     uint64_t val;
     uint64_t z_mask;  /* mask bit is 0 if and only if value bit is 0 */
+    uint64_t s_mask;  /* a left-aligned mask of clrsb(value) bits. */
 } TempOptInfo;
 
 typedef struct OptContext {
@@ -53,9 +54,37 @@ typedef struct OptContext {
     /* In flight values from optimization. */
     uint64_t a_mask;  /* mask bit is 0 iff value identical to first input */
     uint64_t z_mask;  /* mask bit is 0 iff value bit is 0 */
+    uint64_t s_mask;  /* mask of clrsb(value) bits */
     TCGType type;
 } OptContext;
 
+/* Calculate the smask for a specific value. */
+static uint64_t smask_from_value(uint64_t value)
+{
+    int rep = clrsb64(value);
+    return ~(~0ull >> rep);
+}
+
+/*
+ * Calculate the smask for a given set of known-zeros.
+ * If there are lots of zeros on the left, we can consider the remainder
+ * an unsigned field, and thus the corresponding signed field is one bit
+ * larger.
+ */
+static uint64_t smask_from_zmask(uint64_t zmask)
+{
+    /*
+     * Only the 0 bits are significant for zmask, thus the msb itself
+     * must be zero, else we have no sign information.
+     */
+    int rep = clz64(zmask);
+    if (rep == 0) {
+        return 0;
+    }
+    rep -= 1;
+    return ~(~0ull >> rep);
+}
+
 static inline TempOptInfo *ts_info(TCGTemp *ts)
 {
     return ts->state_ptr;
@@ -94,6 +123,7 @@ static void reset_ts(TCGTemp *ts)
     ti->prev_copy = ts;
     ti->is_const = false;
     ti->z_mask = -1;
+    ti->s_mask = 0;
 }
 
 static void reset_temp(TCGArg arg)
@@ -124,9 +154,11 @@ static void init_ts_info(OptContext *ctx, TCGTemp *ts)
         ti->is_const = true;
         ti->val = ts->val;
         ti->z_mask = ts->val;
+        ti->s_mask = smask_from_value(ts->val);
     } else {
         ti->is_const = false;
         ti->z_mask = -1;
+        ti->s_mask = 0;
     }
 }
 
@@ -220,6 +252,7 @@ static bool tcg_opt_gen_mov(OptContext *ctx, TCGOp *op, TCGArg dst, TCGArg src)
     op->args[1] = src;
 
     di->z_mask = si->z_mask;
+    di->s_mask = si->s_mask;
 
     if (src_ts->type == dst_ts->type) {
         TempOptInfo *ni = ts_info(si->next_copy);
@@ -645,13 +678,15 @@ static void finish_folding(OptContext *ctx, TCGOp *op)
 
     nb_oargs = def->nb_oargs;
     for (i = 0; i < nb_oargs; i++) {
-        reset_temp(op->args[i]);
+        TCGTemp *ts = arg_temp(op->args[i]);
+        reset_ts(ts);
         /*
-         * Save the corresponding known-zero bits mask for the
+         * Save the corresponding known-zero/sign bits mask for the
          * first output argument (only one supported so far).
          */
         if (i == 0) {
-            arg_info(op->args[i])->z_mask = ctx->z_mask;
+            ts_info(ts)->z_mask = ctx->z_mask;
+            ts_info(ts)->s_mask = ctx->s_mask;
         }
     }
 }
@@ -701,6 +736,7 @@ static bool fold_masks(OptContext *ctx, TCGOp *op)
 {
     uint64_t a_mask = ctx->a_mask;
     uint64_t z_mask = ctx->z_mask;
+    uint64_t s_mask = ctx->s_mask;
 
     /*
      * 32-bit ops generate 32-bit results, which for the purpose of
@@ -712,7 +748,9 @@ static bool fold_masks(OptContext *ctx, TCGOp *op)
     if (ctx->type == TCG_TYPE_I32) {
         a_mask = (int32_t)a_mask;
         z_mask = (int32_t)z_mask;
+        s_mask |= MAKE_64BIT_MASK(32, 32);
         ctx->z_mask = z_mask;
+        ctx->s_mask = s_mask;
     }
 
     if (z_mask == 0) {
@@ -1058,7 +1096,7 @@ static bool fold_brcond2(OptContext *ctx, TCGOp *op)
 
 static bool fold_bswap(OptContext *ctx, TCGOp *op)
 {
-    uint64_t z_mask, sign;
+    uint64_t z_mask, s_mask, sign;
 
     if (arg_is_const(op->args[1])) {
         uint64_t t = arg_info(op->args[1])->val;
@@ -1068,6 +1106,7 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op)
     }
 
     z_mask = arg_info(op->args[1])->z_mask;
+
     switch (op->opc) {
     case INDEX_op_bswap16_i32:
     case INDEX_op_bswap16_i64:
@@ -1086,6 +1125,7 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op)
     default:
         g_assert_not_reached();
     }
+    s_mask = smask_from_zmask(z_mask);
 
     switch (op->args[2] & (TCG_BSWAP_OZ | TCG_BSWAP_OS)) {
     case TCG_BSWAP_OZ:
@@ -1094,14 +1134,17 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op)
         /* If the sign bit may be 1, force all the bits above to 1. */
         if (z_mask & sign) {
             z_mask |= sign;
+            s_mask = sign << 1;
         }
         break;
     default:
         /* The high bits are undefined: force all bits above the sign to 1. */
         z_mask |= sign << 1;
+        s_mask = 0;
         break;
     }
     ctx->z_mask = z_mask;
+    ctx->s_mask = s_mask;
 
     return fold_masks(ctx, op);
 }
@@ -1240,21 +1283,24 @@ static bool fold_eqv(OptContext *ctx, TCGOp *op)
 static bool fold_extract(OptContext *ctx, TCGOp *op)
 {
     uint64_t z_mask_old, z_mask;
+    int pos = op->args[2];
+    int len = op->args[3];
 
     if (arg_is_const(op->args[1])) {
         uint64_t t;
 
         t = arg_info(op->args[1])->val;
-        t = extract64(t, op->args[2], op->args[3]);
+        t = extract64(t, pos, len);
         return tcg_opt_gen_movi(ctx, op, op->args[0], t);
     }
 
     z_mask_old = arg_info(op->args[1])->z_mask;
-    z_mask = sextract64(z_mask_old, op->args[2], op->args[3]);
-    if (op->args[2] == 0) {
+    z_mask = extract64(z_mask_old, pos, len);
+    if (pos == 0) {
         ctx->a_mask = z_mask_old ^ z_mask;
     }
     ctx->z_mask = z_mask;
+    ctx->s_mask = smask_from_zmask(z_mask);
 
     return fold_masks(ctx, op);
 }
@@ -1280,14 +1326,16 @@ static bool fold_extract2(OptContext *ctx, TCGOp *op)
 
 static bool fold_exts(OptContext *ctx, TCGOp *op)
 {
-    uint64_t z_mask_old, z_mask, sign;
+    uint64_t s_mask_old, s_mask, z_mask, sign;
     bool type_change = false;
 
     if (fold_const1(ctx, op)) {
         return true;
     }
 
-    z_mask_old = z_mask = arg_info(op->args[1])->z_mask;
+    z_mask = arg_info(op->args[1])->z_mask;
+    s_mask = arg_info(op->args[1])->s_mask;
+    s_mask_old = s_mask;
 
     switch (op->opc) {
     CASE_OP_32_64(ext8s):
@@ -1311,10 +1359,14 @@ static bool fold_exts(OptContext *ctx, TCGOp *op)
 
     if (z_mask & sign) {
         z_mask |= sign;
-    } else if (!type_change) {
-        ctx->a_mask = z_mask_old ^ z_mask;
     }
+    s_mask |= sign << 1;
+
     ctx->z_mask = z_mask;
+    ctx->s_mask = s_mask;
+    if (!type_change) {
+        ctx->a_mask = s_mask & ~s_mask_old;
+    }
 
     return fold_masks(ctx, op);
 }
@@ -1353,6 +1405,7 @@ static bool fold_extu(OptContext *ctx, TCGOp *op)
     }
 
     ctx->z_mask = z_mask;
+    ctx->s_mask = smask_from_zmask(z_mask);
     if (!type_change) {
         ctx->a_mask = z_mask_old ^ z_mask;
     }
@@ -1573,8 +1626,12 @@ static bool fold_qemu_ld(OptContext *ctx, TCGOp *op)
     MemOp mop = get_memop(oi);
     int width = 8 << (mop & MO_SIZE);
 
-    if (!(mop & MO_SIGN) && width < 64) {
-        ctx->z_mask = MAKE_64BIT_MASK(0, width);
+    if (width < 64) {
+        ctx->s_mask = MAKE_64BIT_MASK(width, 64 - width);
+        if (!(mop & MO_SIGN)) {
+            ctx->z_mask = MAKE_64BIT_MASK(0, width);
+            ctx->s_mask <<= 1;
+        }
     }
 
     /* Opcodes that touch guest memory stop the mb optimization.  */
@@ -1684,23 +1741,31 @@ static bool fold_setcond2(OptContext *ctx, TCGOp *op)
 
 static bool fold_sextract(OptContext *ctx, TCGOp *op)
 {
-    int64_t z_mask_old, z_mask;
+    uint64_t z_mask, s_mask, s_mask_old;
+    int pos = op->args[2];
+    int len = op->args[3];
 
     if (arg_is_const(op->args[1])) {
         uint64_t t;
 
         t = arg_info(op->args[1])->val;
-        t = sextract64(t, op->args[2], op->args[3]);
+        t = sextract64(t, pos, len);
         return tcg_opt_gen_movi(ctx, op, op->args[0], t);
     }
 
-    z_mask_old = arg_info(op->args[1])->z_mask;
-    z_mask = sextract64(z_mask_old, op->args[2], op->args[3]);
-    if (op->args[2] == 0 && z_mask >= 0) {
-        ctx->a_mask = z_mask_old ^ z_mask;
-    }
+    z_mask = arg_info(op->args[1])->z_mask;
+    z_mask = sextract64(z_mask, pos, len);
     ctx->z_mask = z_mask;
 
+    s_mask_old = arg_info(op->args[1])->s_mask;
+    s_mask = sextract64(s_mask_old, pos, len);
+    s_mask |= MAKE_64BIT_MASK(len, 64 - len);
+    ctx->s_mask = s_mask;
+
+    if (pos == 0) {
+        ctx->a_mask = s_mask & ~s_mask_old;
+    }
+
     return fold_masks(ctx, op);
 }
 
@@ -1777,14 +1842,26 @@ static bool fold_tcg_ld(OptContext *ctx, TCGOp *op)
 {
     /* We can't do any folding with a load, but we can record bits. */
     switch (op->opc) {
+    CASE_OP_32_64(ld8s):
+        ctx->s_mask = MAKE_64BIT_MASK(8, 56);
+        break;
     CASE_OP_32_64(ld8u):
-        ctx->z_mask = 0xff;
+        ctx->z_mask = MAKE_64BIT_MASK(0, 8);
+        ctx->s_mask = MAKE_64BIT_MASK(9, 55);
+        break;
+    CASE_OP_32_64(ld16s):
+        ctx->s_mask = MAKE_64BIT_MASK(16, 48);
         break;
     CASE_OP_32_64(ld16u):
-        ctx->z_mask = 0xffff;
+        ctx->z_mask = MAKE_64BIT_MASK(0, 16);
+        ctx->s_mask = MAKE_64BIT_MASK(17, 47);
+        break;
+    case INDEX_op_ld32s_i64:
+        ctx->s_mask = MAKE_64BIT_MASK(32, 32);
         break;
     case INDEX_op_ld32u_i64:
-        ctx->z_mask = 0xffffffffu;
+        ctx->z_mask = MAKE_64BIT_MASK(0, 32);
+        ctx->s_mask = MAKE_64BIT_MASK(33, 31);
         break;
     default:
         g_assert_not_reached();
@@ -1847,9 +1924,10 @@ void tcg_optimize(TCGContext *s)
             ctx.type = TCG_TYPE_I32;
         }
 
-        /* Assume all bits affected, and no bits known zero. */
+        /* Assume all bits affected, no bits known zero, no sign reps. */
         ctx.a_mask = -1;
         ctx.z_mask = -1;
+        ctx.s_mask = 0;
 
         /*
          * Process each opcode.
@@ -1922,8 +2000,11 @@ void tcg_optimize(TCGContext *s)
         case INDEX_op_extrh_i64_i32:
             done = fold_extu(&ctx, op);
             break;
+        CASE_OP_32_64(ld8s):
         CASE_OP_32_64(ld8u):
+        CASE_OP_32_64(ld16s):
         CASE_OP_32_64(ld16u):
+        case INDEX_op_ld32s_i64:
         case INDEX_op_ld32u_i64:
             done = fold_tcg_ld(&ctx, op);
             break;
-- 
2.25.1



  parent reply	other threads:[~2021-10-21 21:43 UTC|newest]

Thread overview: 108+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-21 21:04 [PATCH v3 00/48] tcg: optimize redundant " Richard Henderson
2021-10-21 21:04 ` [PATCH v3 01/48] tcg/optimize: Rename "mask" to "z_mask" Richard Henderson
2021-10-21 21:04 ` [PATCH v3 02/48] tcg/optimize: Split out OptContext Richard Henderson
2021-10-22 14:53   ` Philippe Mathieu-Daudé
2021-10-21 21:04 ` [PATCH v3 03/48] tcg/optimize: Remove do_default label Richard Henderson
2021-10-22 15:12   ` Philippe Mathieu-Daudé
2021-10-21 21:04 ` [PATCH v3 04/48] tcg/optimize: Change tcg_opt_gen_{mov, movi} interface Richard Henderson
2021-10-21 21:04 ` [PATCH v3 05/48] tcg/optimize: Move prev_mb into OptContext Richard Henderson
2021-10-22 15:13   ` Philippe Mathieu-Daudé
2021-10-21 21:04 ` [PATCH v3 06/48] tcg/optimize: Split out init_arguments Richard Henderson
2021-10-21 21:04 ` [PATCH v3 07/48] tcg/optimize: Split out copy_propagate Richard Henderson
2021-10-21 21:04 ` [PATCH v3 08/48] tcg/optimize: Split out fold_call Richard Henderson
2021-10-21 21:05 ` [PATCH v3 09/48] tcg/optimize: Drop nb_oargs, nb_iargs locals Richard Henderson
2021-10-21 21:05 ` [PATCH v3 10/48] tcg/optimize: Change fail return for do_constant_folding_cond* Richard Henderson
2021-10-22 13:53   ` Philippe Mathieu-Daudé
2021-10-21 21:05 ` [PATCH v3 11/48] tcg/optimize: Return true from tcg_opt_gen_{mov, movi} Richard Henderson
2021-10-26 15:13   ` [PATCH v3 11/48] tcg/optimize: Return true from tcg_opt_gen_{mov,movi} Alex Bennée
2021-10-21 21:05 ` [PATCH v3 12/48] tcg/optimize: Split out finish_folding Richard Henderson
2021-10-26 15:16   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 13/48] tcg/optimize: Use a boolean to avoid a mass of continues Richard Henderson
2021-10-26 15:17   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 14/48] tcg/optimize: Split out fold_mb, fold_qemu_{ld,st} Richard Henderson
2021-10-22 13:56   ` Philippe Mathieu-Daudé
2021-10-21 21:05 ` [PATCH v3 15/48] tcg/optimize: Split out fold_const{1,2} Richard Henderson
2021-10-26 15:19   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 16/48] tcg/optimize: Split out fold_setcond2 Richard Henderson
2021-10-26 15:31   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 17/48] tcg/optimize: Split out fold_brcond2 Richard Henderson
2021-10-22 17:26   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 18/48] tcg/optimize: Split out fold_brcond Richard Henderson
2021-10-22 13:58   ` Philippe Mathieu-Daudé
2021-10-21 21:05 ` [PATCH v3 19/48] tcg/optimize: Split out fold_setcond Richard Henderson
2021-10-22 13:59   ` Philippe Mathieu-Daudé
2021-10-21 21:05 ` [PATCH v3 20/48] tcg/optimize: Split out fold_mulu2_i32 Richard Henderson
2021-10-22 14:00   ` Philippe Mathieu-Daudé
2021-10-22 17:32   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 21/48] tcg/optimize: Split out fold_addsub2_i32 Richard Henderson
2021-10-22 14:01   ` Philippe Mathieu-Daudé
2021-10-22 17:33   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 22/48] tcg/optimize: Split out fold_movcond Richard Henderson
2021-10-22 14:05   ` Philippe Mathieu-Daudé
2021-10-22 17:34   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 23/48] tcg/optimize: Split out fold_extract2 Richard Henderson
2021-10-22 14:07   ` Philippe Mathieu-Daudé
2021-10-22 17:34   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 24/48] tcg/optimize: Split out fold_extract, fold_sextract Richard Henderson
2021-10-22 14:08   ` Philippe Mathieu-Daudé
2021-10-22 17:34   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 25/48] tcg/optimize: Split out fold_deposit Richard Henderson
2021-10-22 14:09   ` Philippe Mathieu-Daudé
2021-10-22 17:35   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 26/48] tcg/optimize: Split out fold_count_zeros Richard Henderson
2021-10-22 14:10   ` Philippe Mathieu-Daudé
2021-10-22 17:35   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 27/48] tcg/optimize: Split out fold_bswap Richard Henderson
2021-10-22 17:36   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 28/48] tcg/optimize: Split out fold_dup, fold_dup2 Richard Henderson
2021-10-22 14:12   ` Philippe Mathieu-Daudé
2021-10-22 17:36   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 29/48] tcg/optimize: Split out fold_mov Richard Henderson
2021-10-22 17:39   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 30/48] tcg/optimize: Split out fold_xx_to_i Richard Henderson
2021-10-22 21:04   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 31/48] tcg/optimize: Split out fold_xx_to_x Richard Henderson
2021-10-22 21:04   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 32/48] tcg/optimize: Split out fold_xi_to_i Richard Henderson
2021-10-22 21:17   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 33/48] tcg/optimize: Add type to OptContext Richard Henderson
2021-10-22 22:11   ` Luis Fernando Fujita Pires
2021-10-23 18:25     ` Richard Henderson
2021-10-21 21:05 ` [PATCH v3 34/48] tcg/optimize: Split out fold_to_not Richard Henderson
2021-10-25 14:17   ` Luis Fernando Fujita Pires
2021-10-25 17:31     ` Richard Henderson
2021-10-25 18:13       ` Luis Fernando Fujita Pires
2021-10-25 18:35         ` Richard Henderson
2021-10-21 21:05 ` [PATCH v3 35/48] tcg/optimize: Split out fold_sub_to_neg Richard Henderson
2021-10-25 14:17   ` Luis Fernando Fujita Pires
2021-10-21 21:05 ` [PATCH v3 36/48] tcg/optimize: Split out fold_xi_to_x Richard Henderson
2021-10-25 14:26   ` Luis Fernando Fujita Pires
2021-10-25 17:46     ` Richard Henderson
2021-10-21 21:05 ` [PATCH v3 37/48] tcg/optimize: Split out fold_ix_to_i Richard Henderson
2021-10-25 14:26   ` Luis Fernando Fujita Pires
2021-10-26 19:11   ` Philippe Mathieu-Daudé
2021-10-21 21:05 ` [PATCH v3 38/48] tcg/optimize: Split out fold_masks Richard Henderson
2021-10-26 15:32   ` Alex Bennée
2021-10-26 18:50     ` Richard Henderson
2021-10-21 21:05 ` [PATCH v3 39/48] tcg/optimize: Expand fold_mulu2_i32 to all 4-arg multiplies Richard Henderson
2021-10-22 14:16   ` Philippe Mathieu-Daudé
2021-10-21 21:05 ` [PATCH v3 40/48] tcg/optimize: Expand fold_addsub2_i32 to 64-bit ops Richard Henderson
2021-10-26 16:21   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 41/48] tcg/optimize: Sink commutative operand swapping into fold functions Richard Henderson
2021-10-26 16:27   ` Alex Bennée
2021-10-26 19:33     ` Richard Henderson
2021-10-27 13:22       ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 42/48] tcg/optimize: Add more simplifications for orc Richard Henderson
2021-10-26 16:22   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 43/48] tcg/optimize: Stop forcing z_mask to "garbage" for 32-bit values Richard Henderson
2021-10-26 16:35   ` Alex Bennée
2021-10-21 21:05 ` Richard Henderson [this message]
2021-10-26 16:34   ` [PATCH v3 44/48] tcg/optimize: Optimize sign extensions Alex Bennée
2021-10-21 21:05 ` [PATCH v3 45/48] tcg/optimize: Propagate sign info for logical operations Richard Henderson
2021-10-26 16:35   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 46/48] tcg/optimize: Propagate sign info for setcond Richard Henderson
2021-10-26 16:36   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 47/48] tcg/optimize: Propagate sign info for bit counting Richard Henderson
2021-10-26 16:36   ` Alex Bennée
2021-10-21 21:05 ` [PATCH v3 48/48] tcg/optimize: Propagate sign info for shifting Richard Henderson
2021-10-26 16:37   ` Alex Bennée

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=20211021210539.825582-45-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=alex.bennee@linaro.org \
    --cc=luis.pires@eldorado.org.br \
    --cc=qemu-devel@nongnu.org \
    --subject='Re: [PATCH v3 44/48] tcg/optimize: Optimize sign extensions' \
    /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

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).