All the mail mirrored from lore.kernel.org
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: "Philippe Mathieu-Daudé" <f4bug@amsat.org>
Subject: [PATCH v7 22/27] tcg/tci: Implement add2, sub2
Date: Tue,  1 Jun 2021 08:01:01 -0700	[thread overview]
Message-ID: <20210601150106.12761-23-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210601150106.12761-1-richard.henderson@linaro.org>

We already had the 32-bit versions for a 32-bit host; expand this
to 64-bit hosts as well.  The 64-bit opcodes are new.

Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/tci/tcg-target.h     |  8 ++++----
 tcg/tci.c                | 40 ++++++++++++++++++++++++++--------------
 tcg/tci/tcg-target.c.inc | 15 ++++++++-------
 3 files changed, 38 insertions(+), 25 deletions(-)

diff --git a/tcg/tci/tcg-target.h b/tcg/tci/tcg-target.h
index 71a44bbfb0..515b3c7a56 100644
--- a/tcg/tci/tcg-target.h
+++ b/tcg/tci/tcg-target.h
@@ -121,11 +121,11 @@
 #define TCG_TARGET_HAS_rot_i64          1
 #define TCG_TARGET_HAS_movcond_i64      1
 #define TCG_TARGET_HAS_muls2_i64        1
-#define TCG_TARGET_HAS_add2_i32         0
-#define TCG_TARGET_HAS_sub2_i32         0
+#define TCG_TARGET_HAS_add2_i32         1
+#define TCG_TARGET_HAS_sub2_i32         1
 #define TCG_TARGET_HAS_mulu2_i32        1
-#define TCG_TARGET_HAS_add2_i64         0
-#define TCG_TARGET_HAS_sub2_i64         0
+#define TCG_TARGET_HAS_add2_i64         1
+#define TCG_TARGET_HAS_sub2_i64         1
 #define TCG_TARGET_HAS_mulu2_i64        1
 #define TCG_TARGET_HAS_muluh_i64        0
 #define TCG_TARGET_HAS_mulsh_i64        0
diff --git a/tcg/tci.c b/tcg/tci.c
index 811af1e618..eb9b1ab463 100644
--- a/tcg/tci.c
+++ b/tcg/tci.c
@@ -191,7 +191,6 @@ static void tci_args_rrrrrc(uint32_t insn, TCGReg *r0, TCGReg *r1,
     *c5 = extract32(insn, 28, 4);
 }
 
-#if TCG_TARGET_REG_BITS == 32
 static void tci_args_rrrrrr(uint32_t insn, TCGReg *r0, TCGReg *r1,
                             TCGReg *r2, TCGReg *r3, TCGReg *r4, TCGReg *r5)
 {
@@ -202,7 +201,6 @@ static void tci_args_rrrrrr(uint32_t insn, TCGReg *r0, TCGReg *r1,
     *r4 = extract32(insn, 24, 4);
     *r5 = extract32(insn, 28, 4);
 }
-#endif
 
 static bool tci_compare32(uint32_t u0, uint32_t u1, TCGCond condition)
 {
@@ -353,17 +351,14 @@ uintptr_t QEMU_DISABLE_CFI tcg_qemu_tb_exec(CPUArchState *env,
     for (;;) {
         uint32_t insn;
         TCGOpcode opc;
-        TCGReg r0, r1, r2, r3, r4;
+        TCGReg r0, r1, r2, r3, r4, r5;
         tcg_target_ulong t1;
         TCGCond condition;
         target_ulong taddr;
         uint8_t pos, len;
         uint32_t tmp32;
         uint64_t tmp64;
-#if TCG_TARGET_REG_BITS == 32
-        TCGReg r5;
         uint64_t T1, T2;
-#endif
         TCGMemOpIdx oi;
         int32_t ofs;
         void *ptr;
@@ -654,20 +649,22 @@ uintptr_t QEMU_DISABLE_CFI tcg_qemu_tb_exec(CPUArchState *env,
                 tb_ptr = ptr;
             }
             break;
-#if TCG_TARGET_REG_BITS == 32
+#if TCG_TARGET_REG_BITS == 32 || TCG_TARGET_HAS_add2_i32
         case INDEX_op_add2_i32:
             tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
             T1 = tci_uint64(regs[r3], regs[r2]);
             T2 = tci_uint64(regs[r5], regs[r4]);
             tci_write_reg64(regs, r1, r0, T1 + T2);
             break;
+#endif
+#if TCG_TARGET_REG_BITS == 32 || TCG_TARGET_HAS_sub2_i32
         case INDEX_op_sub2_i32:
             tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
             T1 = tci_uint64(regs[r3], regs[r2]);
             T2 = tci_uint64(regs[r5], regs[r4]);
             tci_write_reg64(regs, r1, r0, T1 - T2);
             break;
-#endif /* TCG_TARGET_REG_BITS == 32 */
+#endif
 #if TCG_TARGET_HAS_mulu2_i32
         case INDEX_op_mulu2_i32:
             tci_args_rrrr(insn, &r0, &r1, &r2, &r3);
@@ -797,6 +794,24 @@ uintptr_t QEMU_DISABLE_CFI tcg_qemu_tb_exec(CPUArchState *env,
             muls64(&regs[r0], &regs[r1], regs[r2], regs[r3]);
             break;
 #endif
+#if TCG_TARGET_HAS_add2_i64
+        case INDEX_op_add2_i64:
+            tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
+            T1 = regs[r2] + regs[r4];
+            T2 = regs[r3] + regs[r5] + (T1 < regs[r2]);
+            regs[r0] = T1;
+            regs[r1] = T2;
+            break;
+#endif
+#if TCG_TARGET_HAS_add2_i64
+        case INDEX_op_sub2_i64:
+            tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
+            T1 = regs[r2] - regs[r4];
+            T2 = regs[r3] - regs[r5] - (regs[r2] < regs[r4]);
+            regs[r0] = T1;
+            regs[r1] = T2;
+            break;
+#endif
 
             /* Shift/rotate operations (64 bit). */
 
@@ -1113,10 +1128,7 @@ int print_insn_tci(bfd_vma addr, disassemble_info *info)
     const char *op_name;
     uint32_t insn;
     TCGOpcode op;
-    TCGReg r0, r1, r2, r3, r4;
-#if TCG_TARGET_REG_BITS == 32
-    TCGReg r5;
-#endif
+    TCGReg r0, r1, r2, r3, r4, r5;
     tcg_target_ulong i1;
     int32_t s2;
     TCGCond c;
@@ -1314,15 +1326,15 @@ int print_insn_tci(bfd_vma addr, disassemble_info *info)
                            str_r(r2), str_r(r3));
         break;
 
-#if TCG_TARGET_REG_BITS == 32
     case INDEX_op_add2_i32:
+    case INDEX_op_add2_i64:
     case INDEX_op_sub2_i32:
+    case INDEX_op_sub2_i64:
         tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
         info->fprintf_func(info->stream, "%-12s  %s, %s, %s, %s, %s, %s",
                            op_name, str_r(r0), str_r(r1), str_r(r2),
                            str_r(r3), str_r(r4), str_r(r5));
         break;
-#endif
 
     case INDEX_op_qemu_ld_i64:
     case INDEX_op_qemu_st_i64:
diff --git a/tcg/tci/tcg-target.c.inc b/tcg/tci/tcg-target.c.inc
index e617c46366..bb04c326e8 100644
--- a/tcg/tci/tcg-target.c.inc
+++ b/tcg/tci/tcg-target.c.inc
@@ -134,11 +134,13 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_brcond_i64:
         return C_O0_I2(r, r);
 
-#if TCG_TARGET_REG_BITS == 32
-    /* TODO: Support R, R, R, R, RI, RI? Will it be faster? */
     case INDEX_op_add2_i32:
+    case INDEX_op_add2_i64:
     case INDEX_op_sub2_i32:
+    case INDEX_op_sub2_i64:
         return C_O2_I4(r, r, r, r, r, r);
+
+#if TCG_TARGET_REG_BITS == 32
     case INDEX_op_brcond2_i32:
         return C_O0_I4(r, r, r, r);
 #endif
@@ -467,7 +469,6 @@ static void tcg_out_op_rrrrrc(TCGContext *s, TCGOpcode op,
     tcg_out32(s, insn);
 }
 
-#if TCG_TARGET_REG_BITS == 32
 static void tcg_out_op_rrrrrr(TCGContext *s, TCGOpcode op,
                               TCGReg r0, TCGReg r1, TCGReg r2,
                               TCGReg r3, TCGReg r4, TCGReg r5)
@@ -483,7 +484,6 @@ static void tcg_out_op_rrrrrr(TCGContext *s, TCGOpcode op,
     insn = deposit32(insn, 28, 4, r5);
     tcg_out32(s, insn);
 }
-#endif
 
 static void tcg_out_ldst(TCGContext *s, TCGOpcode op, TCGReg val,
                          TCGReg base, intptr_t offset)
@@ -717,12 +717,13 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tcg_out_op_rr(s, opc, args[0], args[1]);
         break;
 
-#if TCG_TARGET_REG_BITS == 32
-    case INDEX_op_add2_i32:
-    case INDEX_op_sub2_i32:
+    CASE_32_64(add2)
+    CASE_32_64(sub2)
         tcg_out_op_rrrrrr(s, opc, args[0], args[1], args[2],
                           args[3], args[4], args[5]);
         break;
+
+#if TCG_TARGET_REG_BITS == 32
     case INDEX_op_brcond2_i32:
         tcg_out_op_rrrrrc(s, INDEX_op_setcond2_i32, TCG_REG_TMP,
                           args[0], args[1], args[2], args[3], args[4]);
-- 
2.25.1



  parent reply	other threads:[~2021-06-01 15:25 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-01 15:00 [PATCH v7 00/27] TCI fixes and cleanups Richard Henderson
2021-06-01 15:00 ` [PATCH v7 01/27] tcg: Combine dh_is_64bit and dh_is_signed to dh_typecode Richard Henderson
2021-06-01 15:00 ` [PATCH v7 02/27] tcg: Add tcg_call_flags Richard Henderson
2021-06-01 15:00 ` [PATCH v7 03/27] accel/tcg/plugin-gen: Drop inline markers Richard Henderson
2021-06-01 15:00 ` [PATCH v7 04/27] plugins: Drop tcg_flags from struct qemu_plugin_dyn_cb Richard Henderson
2021-06-02  9:22   ` Alex Bennée
2021-06-02 16:02     ` Richard Henderson
2021-06-01 15:00 ` [PATCH v7 05/27] accel/tcg: Add tcg call flags to plugins helpers Richard Henderson
2021-06-01 15:00 ` [PATCH v7 06/27] tcg: Store the TCGHelperInfo in the TCGOp for call Richard Henderson
2021-06-01 15:00 ` [PATCH v7 07/27] tcg: Add tcg_call_func Richard Henderson
2021-06-01 15:00 ` [PATCH v7 08/27] tcg: Build ffi data structures for helpers Richard Henderson
2021-06-01 15:00 ` [PATCH v7 09/27] tcg/tci: Improve tcg_target_call_clobber_regs Richard Henderson
2021-06-02 17:59   ` Philippe Mathieu-Daudé
2021-06-01 15:00 ` [PATCH v7 10/27] tcg/tci: Move call-return regs to end of tcg_target_reg_alloc_order Richard Henderson
2021-06-01 15:00 ` [PATCH v7 11/27] tcg/tci: Use ffi for calls Richard Henderson
2021-06-02 10:31   ` Alex Bennée
2021-06-01 15:00 ` [PATCH v7 12/27] tcg/tci: Reserve r13 for a temporary Richard Henderson
2021-06-19 15:50   ` Philippe Mathieu-Daudé
2021-06-01 15:00 ` [PATCH v7 13/27] tcg/tci: Emit setcond before brcond Richard Henderson
2021-06-19 15:50   ` Philippe Mathieu-Daudé
2021-06-01 15:00 ` [PATCH v7 14/27] tcg/tci: Remove tci_write_reg Richard Henderson
2021-06-01 15:00 ` [PATCH v7 15/27] tcg/tci: Change encoding to uint32_t units Richard Henderson
2021-06-12 10:21   ` Philippe Mathieu-Daudé
2021-06-12 15:40     ` Richard Henderson
2021-06-19 17:48   ` Philippe Mathieu-Daudé
2021-06-19 18:05     ` Richard Henderson
2021-06-01 15:00 ` [PATCH v7 16/27] tcg/tci: Implement goto_ptr Richard Henderson
2021-06-12  9:45   ` Philippe Mathieu-Daudé
2021-06-01 15:00 ` [PATCH v7 17/27] tcg/tci: Implement movcond Richard Henderson
2021-06-01 15:00 ` [PATCH v7 18/27] tcg/tci: Implement andc, orc, eqv, nand, nor Richard Henderson
2021-06-01 15:00 ` [PATCH v7 19/27] tcg/tci: Implement extract, sextract Richard Henderson
2021-06-01 15:00 ` [PATCH v7 20/27] tcg/tci: Implement clz, ctz, ctpop Richard Henderson
2021-06-01 15:01 ` [PATCH v7 21/27] tcg/tci: Implement mulu2, muls2 Richard Henderson
2021-06-01 15:01 ` Richard Henderson [this message]
2021-06-12  9:36   ` [PATCH v7 22/27] tcg/tci: Implement add2, sub2 Philippe Mathieu-Daudé
2021-06-01 15:01 ` [PATCH v7 23/27] tcg/tci: Split out tci_qemu_ld, tci_qemu_st Richard Henderson
2021-06-02 18:01   ` Philippe Mathieu-Daudé
2021-06-01 15:01 ` [PATCH v7 24/27] Revert "tcg/tci: Use exec/cpu_ldst.h interfaces" Richard Henderson
2021-06-12  9:24   ` Philippe Mathieu-Daudé
2021-06-01 15:01 ` [PATCH v7 25/27] tcg/tci: Remove the qemu_ld/st_type macros Richard Henderson
2021-06-02 18:03   ` Philippe Mathieu-Daudé
2021-06-01 15:01 ` [PATCH v7 26/27] tcg/tci: Use {set,clear}_helper_retaddr Richard Henderson
2021-06-12  9:24   ` Philippe Mathieu-Daudé
2021-06-01 15:01 ` [PATCH v7 27/27] tests/tcg: Increase timeout for TCI Richard Henderson
2021-06-02  9:26   ` Alex Bennée
2021-06-01 15:30 ` [PATCH v7 00/27] TCI fixes and cleanups no-reply
2021-06-19 17:42 ` Philippe Mathieu-Daudé

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=20210601150106.12761-23-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=f4bug@amsat.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.