From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: Richard Henderson <richard.henderson@linaro.org>
Subject: [PULL 09/46] target/i386: avoid trunc and ext for MULX and RORX
Date: Sun, 31 Dec 2023 09:44:25 +0100 [thread overview]
Message-ID: <20231231084502.235366-10-pbonzini@redhat.com> (raw)
In-Reply-To: <20231231084502.235366-1-pbonzini@redhat.com>
Use _tl operations for 32-bit operands on 32-bit targets, and only go
through trunc and extu ops for 64-bit targets. While the trunc/ext
ops should be pretty much free after optimization, the optimizer also
does not like having the same temporary used in multiple EBBs.
Therefore it is nicer to not use tmpN* unless necessary.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
target/i386/tcg/emit.c.inc | 37 +++++++++++++++++++++++++------------
1 file changed, 25 insertions(+), 12 deletions(-)
diff --git a/target/i386/tcg/emit.c.inc b/target/i386/tcg/emit.c.inc
index 98c4c9569ef..f5e44117eab 100644
--- a/target/i386/tcg/emit.c.inc
+++ b/target/i386/tcg/emit.c.inc
@@ -1348,7 +1348,8 @@ static void gen_MULX(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
/* low part of result in VEX.vvvv, high in MODRM */
switch (ot) {
- default:
+ case MO_32:
+#ifdef TARGET_X86_64
tcg_gen_trunc_tl_i32(s->tmp2_i32, s->T0);
tcg_gen_trunc_tl_i32(s->tmp3_i32, s->T1);
tcg_gen_mulu2_i32(s->tmp2_i32, s->tmp3_i32,
@@ -1356,13 +1357,15 @@ static void gen_MULX(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
tcg_gen_extu_i32_tl(cpu_regs[s->vex_v], s->tmp2_i32);
tcg_gen_extu_i32_tl(s->T0, s->tmp3_i32);
break;
-#ifdef TARGET_X86_64
- case MO_64:
- tcg_gen_mulu2_i64(cpu_regs[s->vex_v], s->T0, s->T0, s->T1);
- break;
-#endif
- }
+ case MO_64:
+#endif
+ tcg_gen_mulu2_tl(cpu_regs[s->vex_v], s->T0, s->T0, s->T1);
+ break;
+
+ default:
+ g_assert_not_reached();
+ }
}
static void gen_PALIGNR(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
@@ -1765,14 +1768,24 @@ static void gen_PSLLDQ_i(DisasContext *s, CPUX86State *env, X86DecodedInsn *deco
static void gen_RORX(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
{
MemOp ot = decode->op[0].ot;
- int b = decode->immediate;
+ int mask = ot == MO_64 ? 63 : 31;
+ int b = decode->immediate & mask;
- if (ot == MO_64) {
- tcg_gen_rotri_tl(s->T0, s->T0, b & 63);
- } else {
+ switch (ot) {
+ case MO_32:
+#ifdef TARGET_X86_64
tcg_gen_trunc_tl_i32(s->tmp2_i32, s->T0);
- tcg_gen_rotri_i32(s->tmp2_i32, s->tmp2_i32, b & 31);
+ tcg_gen_rotri_i32(s->tmp2_i32, s->tmp2_i32, b);
tcg_gen_extu_i32_tl(s->T0, s->tmp2_i32);
+ break;
+
+ case MO_64:
+#endif
+ tcg_gen_rotri_tl(s->T0, s->T0, b);
+ break;
+
+ default:
+ g_assert_not_reached();
}
}
--
2.43.0
next prev parent reply other threads:[~2023-12-31 8:48 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-31 8:44 [PULL 00/46] (mostly) target/i386 and meson changes for 2023-12-31 Paolo Bonzini
2023-12-31 8:44 ` [PULL 01/46] configure: use a native non-cross compiler for linux-user Paolo Bonzini
2023-12-31 8:44 ` [PULL 02/46] target/i386: optimize computation of JL and JLE from flags Paolo Bonzini
2023-12-31 8:44 ` [PULL 03/46] target/i386: speedup JO/SETO after MUL or IMUL Paolo Bonzini
2023-12-31 8:44 ` [PULL 04/46] target/i386: remove unnecessary arguments from raise_interrupt Paolo Bonzini
2023-12-31 8:44 ` [PULL 05/46] target/i386: remove unnecessary truncations Paolo Bonzini
2023-12-31 8:44 ` [PULL 06/46] target/i386: clean up cpu_cc_compute_all Paolo Bonzini
2023-12-31 8:44 ` [PULL 07/46] target/i386: document more deviations from the manual Paolo Bonzini
2023-12-31 8:44 ` [PULL 08/46] target/i386: reimplement check for validity of LOCK prefix Paolo Bonzini
2023-12-31 8:44 ` Paolo Bonzini [this message]
2023-12-31 8:44 ` [PULL 10/46] target/i386: rename zext0/zext2 and make them closer to the manual Paolo Bonzini
2023-12-31 8:44 ` [PULL 11/46] target/i386: add X86_SPECIALs for MOVSX and MOVZX Paolo Bonzini
2023-12-31 8:44 ` [PULL 12/46] target/i386: do not decode string source/destination into decode->mem Paolo Bonzini
2023-12-31 8:44 ` [PULL 13/46] target/i386: do not clobber A0 in POP translation Paolo Bonzini
2023-12-31 8:44 ` [PULL 14/46] target/i386: do not clobber T0 on string operations Paolo Bonzini
2023-12-31 8:44 ` [PULL 15/46] target/i386: split eflags computation out of gen_compute_eflags Paolo Bonzini
2023-12-31 8:44 ` [PULL 16/46] target/i386: do not use s->tmp4 for push Paolo Bonzini
2023-12-31 8:44 ` [PULL 17/46] target/i386: do not use s->tmp0 for jumps on ECX ==/!= 0 Paolo Bonzini
2023-12-31 8:44 ` [PULL 18/46] target/i386: prepare for implementation of STOS/SCAS in new decoder Paolo Bonzini
2023-12-31 8:44 ` [PULL 19/46] target/i386: move operand load and writeback out of gen_cmovcc1 Paolo Bonzini
2023-12-31 8:44 ` [PULL 20/46] target/i386: adjust decoding of J operand Paolo Bonzini
2023-12-31 8:44 ` [PULL 21/46] target/i386: introduce flags writeback mechanism Paolo Bonzini
2023-12-31 8:44 ` [PULL 22/46] target/i386: implement CMPccXADD Paolo Bonzini
2023-12-31 8:44 ` [PULL 23/46] target/i386: the sgx_epc_get_section stub is reachable Paolo Bonzini
2023-12-31 8:44 ` [PULL 24/46] esp: check for NULL result from scsi_device_find() Paolo Bonzini
2023-12-31 8:44 ` [PULL 25/46] meson: fix type of "relocatable" option Paolo Bonzini
2023-12-31 8:44 ` [PULL 26/46] meson: remove unused variable Paolo Bonzini
2023-12-31 8:44 ` [PULL 27/46] meson: use version_compare() to compare version Paolo Bonzini
2023-12-31 8:44 ` [PULL 28/46] Makefile: clean qemu-iotests output Paolo Bonzini
2023-12-31 8:44 ` [PULL 29/46] configure: remove unnecessary subshell Paolo Bonzini
2023-12-31 8:44 ` [PULL 30/46] configure: unify again the case arms in probe_target_compiler Paolo Bonzini
2023-12-31 8:44 ` [PULL 31/46] meson: add more sections to main meson.build Paolo Bonzini
2023-12-31 8:44 ` [PULL 32/46] meson: move program checks together Paolo Bonzini
2023-12-31 8:44 ` [PULL 33/46] meson: move option validation together Paolo Bonzini
2023-12-31 8:44 ` [PULL 34/46] meson: move accelerator dependency checks together Paolo Bonzini
2023-12-31 8:44 ` [PULL 35/46] meson: keep subprojects together Paolo Bonzini
2023-12-31 8:44 ` [PULL 36/46] meson: move CFI detection code with other compiler flags Paolo Bonzini
2023-12-31 8:44 ` [PULL 37/46] meson: move config-host.h definitions together Paolo Bonzini
2023-12-31 8:44 ` [PULL 38/46] meson: move subdirs to "Collect sources" section Paolo Bonzini
2023-12-31 8:44 ` [PULL 39/46] meson: always probe u2f and canokey if the option is enabled Paolo Bonzini
2023-12-31 8:44 ` [PULL 40/46] meson: remove OS definitions from config_targetos Paolo Bonzini
2023-12-31 8:44 ` [PULL 41/46] meson: remove CONFIG_POSIX and CONFIG_WIN32 " Paolo Bonzini
2023-12-31 8:44 ` [PULL 42/46] meson: remove config_targetos Paolo Bonzini
2023-12-31 8:44 ` [PULL 43/46] meson: remove CONFIG_ALL Paolo Bonzini
2023-12-31 8:45 ` [PULL 44/46] meson: rename config_all Paolo Bonzini
2023-12-31 8:45 ` [PULL 45/46] configure, meson: rename targetos to host_os Paolo Bonzini
2023-12-31 8:45 ` [PULL 46/46] meson.build: report graphics backends separately Paolo Bonzini
2024-01-05 12:53 ` [PULL 00/46] (mostly) target/i386 and meson changes for 2023-12-31 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=20231231084502.235366-10-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=richard.henderson@linaro.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).