qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Subject: [PULL 01/27] tcg/s390x: Use register pair allocation for div and mulu2
Date: Fri,  6 Jan 2023 23:50:52 -0800	[thread overview]
Message-ID: <20230107075118.1814503-2-richard.henderson@linaro.org> (raw)
In-Reply-To: <20230107075118.1814503-1-richard.henderson@linaro.org>

Previously we hard-coded R2 and R3.

Reviewed-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/s390x/tcg-target-con-set.h |  4 ++--
 tcg/s390x/tcg-target-con-str.h |  8 +------
 tcg/s390x/tcg-target.c.inc     | 43 +++++++++++++++++++++++++---------
 3 files changed, 35 insertions(+), 20 deletions(-)

diff --git a/tcg/s390x/tcg-target-con-set.h b/tcg/s390x/tcg-target-con-set.h
index 426dd92e51..00ba727b70 100644
--- a/tcg/s390x/tcg-target-con-set.h
+++ b/tcg/s390x/tcg-target-con-set.h
@@ -29,8 +29,8 @@ C_O1_I2(v, v, v)
 C_O1_I3(v, v, v, v)
 C_O1_I4(r, r, ri, r, 0)
 C_O1_I4(r, r, ri, rI, 0)
-C_O2_I2(b, a, 0, r)
-C_O2_I3(b, a, 0, 1, r)
+C_O2_I2(o, m, 0, r)
+C_O2_I3(o, m, 0, 1, r)
 C_O2_I4(r, r, 0, 1, rA, r)
 C_O2_I4(r, r, 0, 1, ri, r)
 C_O2_I4(r, r, 0, 1, r, r)
diff --git a/tcg/s390x/tcg-target-con-str.h b/tcg/s390x/tcg-target-con-str.h
index 8bb0358ae5..76446aecae 100644
--- a/tcg/s390x/tcg-target-con-str.h
+++ b/tcg/s390x/tcg-target-con-str.h
@@ -11,13 +11,7 @@
 REGS('r', ALL_GENERAL_REGS)
 REGS('L', ALL_GENERAL_REGS & ~SOFTMMU_RESERVE_REGS)
 REGS('v', ALL_VECTOR_REGS)
-/*
- * A (single) even/odd pair for division.
- * TODO: Add something to the register allocator to allow
- * this kind of regno+1 pairing to be done more generally.
- */
-REGS('a', 1u << TCG_REG_R2)
-REGS('b', 1u << TCG_REG_R3)
+REGS('o', 0xaaaa) /* odd numbered general regs */
 
 /*
  * Define constraint letters for constants:
diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc
index b9ba7b605e..cb00bb6999 100644
--- a/tcg/s390x/tcg-target.c.inc
+++ b/tcg/s390x/tcg-target.c.inc
@@ -2264,10 +2264,18 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
 
     case INDEX_op_div2_i32:
-        tcg_out_insn(s, RR, DR, TCG_REG_R2, args[4]);
+        tcg_debug_assert(args[0] == args[2]);
+        tcg_debug_assert(args[1] == args[3]);
+        tcg_debug_assert((args[1] & 1) == 0);
+        tcg_debug_assert(args[0] == args[1] + 1);
+        tcg_out_insn(s, RR, DR, args[1], args[4]);
         break;
     case INDEX_op_divu2_i32:
-        tcg_out_insn(s, RRE, DLR, TCG_REG_R2, args[4]);
+        tcg_debug_assert(args[0] == args[2]);
+        tcg_debug_assert(args[1] == args[3]);
+        tcg_debug_assert((args[1] & 1) == 0);
+        tcg_debug_assert(args[0] == args[1] + 1);
+        tcg_out_insn(s, RRE, DLR, args[1], args[4]);
         break;
 
     case INDEX_op_shl_i32:
@@ -2521,17 +2529,30 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
 
     case INDEX_op_div2_i64:
-        /* ??? We get an unnecessary sign-extension of the dividend
-           into R3 with this definition, but as we do in fact always
-           produce both quotient and remainder using INDEX_op_div_i64
-           instead requires jumping through even more hoops.  */
-        tcg_out_insn(s, RRE, DSGR, TCG_REG_R2, args[4]);
+        /*
+         * ??? We get an unnecessary sign-extension of the dividend
+         * into op0 with this definition, but as we do in fact always
+         * produce both quotient and remainder using INDEX_op_div_i64
+         * instead requires jumping through even more hoops.
+         */
+        tcg_debug_assert(args[0] == args[2]);
+        tcg_debug_assert(args[1] == args[3]);
+        tcg_debug_assert((args[1] & 1) == 0);
+        tcg_debug_assert(args[0] == args[1] + 1);
+        tcg_out_insn(s, RRE, DSGR, args[1], args[4]);
         break;
     case INDEX_op_divu2_i64:
-        tcg_out_insn(s, RRE, DLGR, TCG_REG_R2, args[4]);
+        tcg_debug_assert(args[0] == args[2]);
+        tcg_debug_assert(args[1] == args[3]);
+        tcg_debug_assert((args[1] & 1) == 0);
+        tcg_debug_assert(args[0] == args[1] + 1);
+        tcg_out_insn(s, RRE, DLGR, args[1], args[4]);
         break;
     case INDEX_op_mulu2_i64:
-        tcg_out_insn(s, RRE, MLGR, TCG_REG_R2, args[3]);
+        tcg_debug_assert(args[0] == args[2]);
+        tcg_debug_assert((args[1] & 1) == 0);
+        tcg_debug_assert(args[0] == args[1] + 1);
+        tcg_out_insn(s, RRE, MLGR, args[1], args[3]);
         break;
 
     case INDEX_op_shl_i64:
@@ -3226,10 +3247,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_div2_i64:
     case INDEX_op_divu2_i32:
     case INDEX_op_divu2_i64:
-        return C_O2_I3(b, a, 0, 1, r);
+        return C_O2_I3(o, m, 0, 1, r);
 
     case INDEX_op_mulu2_i64:
-        return C_O2_I2(b, a, 0, r);
+        return C_O2_I2(o, m, 0, r);
 
     case INDEX_op_add2_i32:
     case INDEX_op_sub2_i32:
-- 
2.34.1



  reply	other threads:[~2023-01-07  7:52 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-07  7:50 [PULL 00/27] tcg/s390x patch queue Richard Henderson
2023-01-07  7:50 ` Richard Henderson [this message]
2023-01-07  7:50 ` [PULL 02/27] tcg/s390x: Remove TCG_REG_TB Richard Henderson
2023-01-07  7:50 ` [PULL 03/27] tcg/s390x: Always set TCG_TARGET_HAS_direct_jump Richard Henderson
2023-01-07  7:50 ` [PULL 04/27] tcg/s390x: Remove USE_LONG_BRANCHES Richard Henderson
2023-01-07  7:50 ` [PULL 05/27] tcg/s390x: Check for long-displacement facility at startup Richard Henderson
2023-01-07  7:50 ` [PULL 06/27] tcg/s390x: Check for extended-immediate " Richard Henderson
2023-01-07  7:50 ` [PULL 07/27] tcg/s390x: Check for general-instruction-extension " Richard Henderson
2023-01-07  7:50 ` [PULL 08/27] tcg/s390x: Check for load-on-condition " Richard Henderson
2023-01-07  7:51 ` [PULL 09/27] tcg/s390x: Remove FAST_BCR_SER facility check Richard Henderson
2023-01-07  7:51 ` [PULL 10/27] tcg/s390x: Remove DISTINCT_OPERANDS " Richard Henderson
2023-01-07  7:51 ` [PULL 11/27] tcg/s390x: Use LARL+AGHI for odd addresses Richard Henderson
2023-01-07  7:51 ` [PULL 12/27] tcg/s390x: Distinguish RRF-a and RRF-c formats Richard Henderson
2023-01-07  7:51 ` [PULL 13/27] tcg/s390x: Distinguish RIE formats Richard Henderson
2023-01-07  7:51 ` [PULL 14/27] tcg/s390x: Support MIE2 multiply single instructions Richard Henderson
2023-01-07  7:51 ` [PULL 15/27] tcg/s390x: Support MIE2 MGRK instruction Richard Henderson
2023-01-07  7:51 ` [PULL 16/27] tcg/s390x: Issue XILF directly for xor_i32 Richard Henderson
2023-01-07  7:51 ` [PULL 17/27] tcg/s390x: Tighten constraints for or_i64 and xor_i64 Richard Henderson
2023-01-07  7:51 ` [PULL 18/27] tcg/s390x: Tighten constraints for and_i64 Richard Henderson
2023-01-07  7:51 ` [PULL 19/27] tcg/s390x: Support MIE3 logical operations Richard Henderson
2023-01-07  7:51 ` [PULL 20/27] tcg/s390x: Create tgen_cmp2 to simplify movcond Richard Henderson
2023-01-07  7:51 ` [PULL 21/27] tcg/s390x: Generalize movcond implementation Richard Henderson
2023-01-07  7:51 ` [PULL 22/27] tcg/s390x: Support SELGR instruction in movcond Richard Henderson
2023-01-07  7:51 ` [PULL 23/27] tcg/s390x: Use tgen_movcond_int in tgen_clz Richard Henderson
2023-01-07  7:51 ` [PULL 24/27] tcg/s390x: Implement ctpop operation Richard Henderson
2023-01-07  7:51 ` [PULL 25/27] tcg/s390x: Tighten constraints for 64-bit compare Richard Henderson
2023-01-07  7:51 ` [PULL 26/27] tcg/s390x: Cleanup tcg_out_movi Richard Henderson
2023-01-07  7:51 ` [PULL 27/27] tcg/s390x: Avoid the constant pool in tcg_out_movi Richard Henderson
2023-01-08 14:27 ` [PULL 00/27] tcg/s390x patch queue Peter Maydell

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=20230107075118.1814503-2-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=iii@linux.ibm.com \
    --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).