From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: thuth@redhat.com, iii@linux.ibm.com
Subject: [PATCH v3 01/13] tcg/s390x: Use register pair allocation for div and mulu2
Date: Thu, 1 Dec 2022 22:51:48 -0800 [thread overview]
Message-ID: <20221202065200.224537-2-richard.henderson@linaro.org> (raw)
In-Reply-To: <20221202065200.224537-1-richard.henderson@linaro.org>
Previously we hard-coded R2 and R3.
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
next prev parent reply other threads:[~2022-12-02 6:52 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-02 6:51 [PATCH v3 00/13] tcg/s390x: misc patches Richard Henderson
2022-12-02 6:51 ` Richard Henderson [this message]
2022-12-06 15:49 ` [PATCH v3 01/13] tcg/s390x: Use register pair allocation for div and mulu2 Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 02/13] tcg/s390x: Remove TCG_REG_TB Richard Henderson
2022-12-06 19:29 ` Ilya Leoshkevich
2022-12-06 22:22 ` Richard Henderson
2022-12-07 0:42 ` Richard Henderson
2022-12-08 14:04 ` Ilya Leoshkevich
2022-12-07 7:45 ` Thomas Huth
2022-12-07 14:55 ` Richard Henderson
2022-12-07 20:40 ` Ilya Leoshkevich
2022-12-07 21:20 ` Christian Borntraeger
2022-12-07 22:09 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 03/13] tcg/s390x: Use LARL+AGHI for odd addresses Richard Henderson
2022-12-06 19:42 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 04/13] tcg/s390x: Distinguish RRF-a and RRF-c formats Richard Henderson
2022-12-06 19:45 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 05/13] tcg/s390x: Distinguish RIE formats Richard Henderson
2022-12-06 19:47 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 06/13] tcg/s390x: Support MIE2 multiply single instructions Richard Henderson
2022-12-06 20:02 ` Ilya Leoshkevich
2022-12-06 20:20 ` Richard Henderson
2022-12-02 6:51 ` [PATCH v3 07/13] tcg/s390x: Support MIE2 MGRK instruction Richard Henderson
2022-12-06 20:02 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 08/13] tcg/s390x: Support MIE3 logical operations Richard Henderson
2022-12-06 20:08 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 09/13] tcg/s390x: Create tgen_cmp2 to simplify movcond Richard Henderson
2022-12-06 20:14 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 10/13] tcg/s390x: Generalize movcond implementation Richard Henderson
2022-12-06 20:39 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 11/13] tcg/s390x: Support SELGR instruction in movcond Richard Henderson
2022-12-06 20:41 ` Ilya Leoshkevich
2022-12-02 6:51 ` [PATCH v3 12/13] tcg/s390x: Use tgen_movcond_int in tgen_clz Richard Henderson
2022-12-06 20:49 ` Ilya Leoshkevich
2022-12-02 6:52 ` [PATCH v3 13/13] tcg/s390x: Implement ctpop operation Richard Henderson
2022-12-06 21:10 ` Ilya Leoshkevich
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=20221202065200.224537-2-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=iii@linux.ibm.com \
--cc=qemu-devel@nongnu.org \
--cc=thuth@redhat.com \
/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).