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 for-8.0 v3 05/45] tcg/arm: Use register pair allocation for qemu_{ld, st}_i64
Date: Fri, 11 Nov 2022 17:40:21 +1000	[thread overview]
Message-ID: <20221111074101.2069454-6-richard.henderson@linaro.org> (raw)
In-Reply-To: <20221111074101.2069454-1-richard.henderson@linaro.org>

Although we still can't use ldrd and strd for all operations,
increase the chances by getting the register allocation correct.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/arm/tcg-target-con-set.h |  7 ++++---
 tcg/arm/tcg-target-con-str.h |  2 ++
 tcg/arm/tcg-target.c.inc     | 28 ++++++++++++++++++----------
 3 files changed, 24 insertions(+), 13 deletions(-)

diff --git a/tcg/arm/tcg-target-con-set.h b/tcg/arm/tcg-target-con-set.h
index 3685e1786a..b8849b2478 100644
--- a/tcg/arm/tcg-target-con-set.h
+++ b/tcg/arm/tcg-target-con-set.h
@@ -15,8 +15,9 @@ C_O0_I2(r, rIN)
 C_O0_I2(s, s)
 C_O0_I2(w, r)
 C_O0_I3(s, s, s)
+C_O0_I3(S, p, s)
 C_O0_I4(r, r, rI, rI)
-C_O0_I4(s, s, s, s)
+C_O0_I4(S, p, s, s)
 C_O1_I1(r, l)
 C_O1_I1(r, r)
 C_O1_I1(w, r)
@@ -38,8 +39,8 @@ C_O1_I2(w, w, wZ)
 C_O1_I3(w, w, w, w)
 C_O1_I4(r, r, r, rI, rI)
 C_O1_I4(r, r, rIN, rIK, 0)
-C_O2_I1(r, r, l)
-C_O2_I2(r, r, l, l)
+C_O2_I1(e, p, l)
+C_O2_I2(e, p, l, l)
 C_O2_I2(r, r, r, r)
 C_O2_I4(r, r, r, r, rIN, rIK)
 C_O2_I4(r, r, rI, rI, rIN, rIK)
diff --git a/tcg/arm/tcg-target-con-str.h b/tcg/arm/tcg-target-con-str.h
index 8f501149e1..24b4b59feb 100644
--- a/tcg/arm/tcg-target-con-str.h
+++ b/tcg/arm/tcg-target-con-str.h
@@ -8,9 +8,11 @@
  * Define constraint letters for register sets:
  * REGS(letter, register_mask)
  */
+REGS('e', ALL_GENERAL_REGS & 0x5555) /* even regs */
 REGS('r', ALL_GENERAL_REGS)
 REGS('l', ALL_QLOAD_REGS)
 REGS('s', ALL_QSTORE_REGS)
+REGS('S', ALL_QSTORE_REGS & 0x5555)  /* even qstore */
 REGS('w', ALL_VECTOR_REGS)
 
 /*
diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc
index 2c6c353eea..aa3a888fed 100644
--- a/tcg/arm/tcg-target.c.inc
+++ b/tcg/arm/tcg-target.c.inc
@@ -1686,9 +1686,11 @@ static void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc,
         tcg_out_ld32_r(s, COND_AL, datalo, addrlo, addend);
         break;
     case MO_UQ:
+        /* We used pair allocation for datalo, so already should be aligned. */
+        tcg_debug_assert((datalo & 1) == 0);
+        tcg_debug_assert(datahi == datalo + 1);
         /* LDRD requires alignment; double-check that. */
-        if (get_alignment_bits(opc) >= MO_64
-            && (datalo & 1) == 0 && datahi == datalo + 1) {
+        if (get_alignment_bits(opc) >= MO_64) {
             /*
              * Rm (the second address op) must not overlap Rt or Rt + 1.
              * Since datalo is aligned, we can simplify the test via alignment.
@@ -1742,9 +1744,11 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, TCGReg datalo,
         tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0);
         break;
     case MO_UQ:
+        /* We used pair allocation for datalo, so already should be aligned. */
+        tcg_debug_assert((datalo & 1) == 0);
+        tcg_debug_assert(datahi == datalo + 1);
         /* LDRD requires alignment; double-check that. */
-        if (get_alignment_bits(opc) >= MO_64
-            && (datalo & 1) == 0 && datahi == datalo + 1) {
+        if (get_alignment_bits(opc) >= MO_64) {
             tcg_out_ldrd_8(s, COND_AL, datalo, addrlo, 0);
         } else if (datalo == addrlo) {
             tcg_out_ld32_12(s, COND_AL, datahi, addrlo, 4);
@@ -1826,9 +1830,11 @@ static void tcg_out_qemu_st_index(TCGContext *s, ARMCond cond, MemOp opc,
         tcg_out_st32_r(s, cond, datalo, addrlo, addend);
         break;
     case MO_64:
+        /* We used pair allocation for datalo, so already should be aligned. */
+        tcg_debug_assert((datalo & 1) == 0);
+        tcg_debug_assert(datahi == datalo + 1);
         /* STRD requires alignment; double-check that. */
-        if (get_alignment_bits(opc) >= MO_64
-            && (datalo & 1) == 0 && datahi == datalo + 1) {
+        if (get_alignment_bits(opc) >= MO_64) {
             tcg_out_strd_r(s, cond, datalo, addrlo, addend);
         } else if (scratch_addend) {
             tcg_out_st32_rwb(s, cond, datalo, addend, addrlo);
@@ -1863,9 +1869,11 @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg datalo,
         tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
         break;
     case MO_64:
+        /* We used pair allocation for datalo, so already should be aligned. */
+        tcg_debug_assert((datalo & 1) == 0);
+        tcg_debug_assert(datahi == datalo + 1);
         /* STRD requires alignment; double-check that. */
-        if (get_alignment_bits(opc) >= MO_64
-            && (datalo & 1) == 0 && datahi == datalo + 1) {
+        if (get_alignment_bits(opc) >= MO_64) {
             tcg_out_strd_8(s, COND_AL, datalo, addrlo, 0);
         } else {
             tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
@@ -2333,11 +2341,11 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_qemu_ld_i32:
         return TARGET_LONG_BITS == 32 ? C_O1_I1(r, l) : C_O1_I2(r, l, l);
     case INDEX_op_qemu_ld_i64:
-        return TARGET_LONG_BITS == 32 ? C_O2_I1(r, r, l) : C_O2_I2(r, r, l, l);
+        return TARGET_LONG_BITS == 32 ? C_O2_I1(e, p, l) : C_O2_I2(e, p, l, l);
     case INDEX_op_qemu_st_i32:
         return TARGET_LONG_BITS == 32 ? C_O0_I2(s, s) : C_O0_I3(s, s, s);
     case INDEX_op_qemu_st_i64:
-        return TARGET_LONG_BITS == 32 ? C_O0_I3(s, s, s) : C_O0_I4(s, s, s, s);
+        return TARGET_LONG_BITS == 32 ? C_O0_I3(S, p, s) : C_O0_I4(S, p, s, s);
 
     case INDEX_op_st_vec:
         return C_O0_I2(w, r);
-- 
2.34.1



  parent reply	other threads:[~2022-11-11  8:11 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-11  7:40 [PATCH for-8.0 v3 00/45] tcg: Support for Int128 with helpers Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 01/45] meson: Move CONFIG_TCG_INTERPRETER to config_host Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 02/45] tcg: Tidy tcg_reg_alloc_op Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 03/45] tcg: Introduce paired register allocation Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 04/45] tcg/s390x: Use register pair allocation for div and mulu2 Richard Henderson
2022-11-11  7:40 ` Richard Henderson [this message]
2022-11-11  7:40 ` [PATCH for-8.0 v3 06/45] tcg: Remove TCG_TARGET_STACK_GROWSUP Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 07/45] accel/tcg: Set cflags_next_tb in cpu_common_initfn Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 08/45] target/sparc: Avoid TCGV_{LOW,HIGH} Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 09/45] tcg: Move TCG_{LOW,HIGH} to tcg-internal.h Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 10/45] tcg: Add temp_subindex to TCGTemp Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 11/45] tcg: Simplify calls to temp_sync vs mem_coherent Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 12/45] tcg: Allocate TCGTemp pairs in host memory order Richard Henderson
2022-11-22 11:25   ` Philippe Mathieu-Daudé
2022-11-11  7:40 ` [PATCH for-8.0 v3 13/45] tcg: Move TCG_TYPE_COUNT outside enum Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 14/45] tcg: Introduce tcg_type_size Richard Henderson
2022-11-22 11:30   ` Philippe Mathieu-Daudé
2022-11-22 16:54     ` Richard Henderson
2022-11-22 18:14       ` Philippe Mathieu-Daudé
2022-11-22 18:15         ` Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 15/45] tcg: Introduce TCGCallReturnKind and TCGCallArgumentKind Richard Henderson
2022-11-22 11:33   ` Philippe Mathieu-Daudé
2022-11-11  7:40 ` [PATCH for-8.0 v3 16/45] tcg: Replace TCG_TARGET_CALL_ALIGN_ARGS with TCG_TARGET_CALL_ARG_I64 Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 17/45] tcg: Replace TCG_TARGET_EXTEND_ARGS with TCG_TARGET_CALL_ARG_I32 Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 18/45] tcg: Use TCG_CALL_ARG_EVEN for TCI special case Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 19/45] accel/tcg/plugin: Don't search for the function pointer index Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 20/45] accel/tcg/plugin: Avoid duplicate copy in copy_call Richard Henderson
2022-11-22 15:21   ` Philippe Mathieu-Daudé
2022-11-11  7:40 ` [PATCH for-8.0 v3 21/45] accel/tcg/plugin: Use copy_op in append_{udata, mem}_cb Richard Henderson
2022-11-22 15:22   ` Philippe Mathieu-Daudé
2022-11-11  7:40 ` [PATCH for-8.0 v3 22/45] tci: MAX_OPC_PARAM_IARGS is no longer used Richard Henderson
2022-11-22 15:25   ` Philippe Mathieu-Daudé
2022-11-11  7:40 ` [PATCH for-8.0 v3 23/45] tcg: Vary the allocation size for TCGOp Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 24/45] tcg: Use output_pref wrapper function Richard Henderson
2022-11-22 15:28   ` Philippe Mathieu-Daudé
2022-11-11  7:40 ` [PATCH for-8.0 v3 25/45] tcg: Reorg function calls Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 26/45] tcg: Move ffi_cif pointer into TCGHelperInfo Richard Henderson
2022-11-22 18:08   ` [PATCH 0/3] tcg: Move ffi_cif pointer into TCGHelperInfo (splitted) Philippe Mathieu-Daudé
2022-11-22 18:08     ` [PATCH 1/3] tcg: Convert typecode_to_ffi from array to function Philippe Mathieu-Daudé
2022-11-22 18:08     ` [PATCH 2/3] tcg: Factor init_ffi_layouts() out of tcg_context_init() Philippe Mathieu-Daudé
2022-11-22 18:08     ` [PATCH 3/3] tcg: Move ffi_cif pointer into TCGHelperInfo Philippe Mathieu-Daudé
2022-11-23 16:22       ` Philippe Mathieu-Daudé
2022-11-11  7:40 ` [PATCH for-8.0 v3 27/45] tcg/aarch64: Merge tcg_out_callr into tcg_out_call Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 28/45] tcg: Add TCGHelperInfo argument to tcg_out_call Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 29/45] tcg: Define TCG_TYPE_I128 and related helper macros Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 30/45] tcg: Handle dh_typecode_i128 with TCG_CALL_{RET, ARG}_NORMAL Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 31/45] tcg: Allocate objects contiguously in temp_allocate_frame Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 32/45] tcg: Introduce tcg_out_addi_ptr Richard Henderson
2022-11-22  9:45   ` Daniel Henrique Barboza
2022-11-11  7:40 ` [PATCH for-8.0 v3 33/45] tcg: Add TCG_CALL_{RET,ARG}_BY_REF Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 34/45] tcg: Introduce tcg_target_call_oarg_reg Richard Henderson
2022-11-22  9:41   ` Daniel Henrique Barboza
2022-11-11  7:40 ` [PATCH for-8.0 v3 35/45] tcg: Add TCG_CALL_RET_BY_VEC Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 36/45] include/qemu/int128: Use Int128 structure for TCI Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 37/45] tcg/i386: Add TCG_TARGET_CALL_{RET, ARG}_I128 Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 38/45] tcg/tci: Fix big-endian return register ordering Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 39/45] tcg/tci: Add TCG_TARGET_CALL_{RET,ARG}_I128 Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 40/45] tcg: " Richard Henderson
2022-11-22  9:47   ` Daniel Henrique Barboza
2022-11-11  7:40 ` [PATCH for-8.0 v3 41/45] tcg: Add temp allocation for TCGv_i128 Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 42/45] tcg: Add basic data movement " Richard Henderson
2022-11-11  7:40 ` [PATCH for-8.0 v3 43/45] tcg: Add guest load/store primitives " Richard Henderson
2022-11-11  7:41 ` [PATCH for-8.0 v3 44/45] tcg: Add tcg_gen_{non}atomic_cmpxchg_i128 Richard Henderson
2022-11-11  7:41 ` [PATCH for-8.0 v3 45/45] tcg: Split out tcg_gen_nonatomic_cmpxchg_i{32, 64} 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=20221111074101.2069454-6-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).