From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: peter.maydell@linaro.org
Subject: [PULL 09/31] tcg/s390x: Do not expand cmp_vec early
Date: Sun, 22 Sep 2024 14:00:50 +0200 [thread overview]
Message-ID: <20240922120112.5067-10-richard.henderson@linaro.org> (raw)
In-Reply-To: <20240922120112.5067-1-richard.henderson@linaro.org>
Move expansion to opcode generation.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
tcg/s390x/tcg-target.c.inc | 139 +++++++++++++++++--------------------
1 file changed, 65 insertions(+), 74 deletions(-)
diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc
index ad587325fc..23935fd0f0 100644
--- a/tcg/s390x/tcg-target.c.inc
+++ b/tcg/s390x/tcg-target.c.inc
@@ -2841,6 +2841,67 @@ static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
tcg_out_insn(s, VRX, VLREP, dst, TCG_TMP0, TCG_REG_NONE, 0, MO_64);
}
+static bool tcg_out_cmp_vec_noinv(TCGContext *s, unsigned vece, TCGReg a0,
+ TCGReg a1, TCGReg a2, TCGCond cond)
+{
+ bool need_swap = false, need_inv = false;
+
+ switch (cond) {
+ case TCG_COND_EQ:
+ case TCG_COND_GT:
+ case TCG_COND_GTU:
+ break;
+ case TCG_COND_NE:
+ case TCG_COND_LE:
+ case TCG_COND_LEU:
+ need_inv = true;
+ break;
+ case TCG_COND_LT:
+ case TCG_COND_LTU:
+ need_swap = true;
+ break;
+ case TCG_COND_GE:
+ case TCG_COND_GEU:
+ need_swap = need_inv = true;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ if (need_inv) {
+ cond = tcg_invert_cond(cond);
+ }
+ if (need_swap) {
+ TCGReg swap = a1;
+ a1 = a2;
+ a2 = swap;
+ cond = tcg_swap_cond(cond);
+ }
+
+ switch (cond) {
+ case TCG_COND_EQ:
+ tcg_out_insn(s, VRRc, VCEQ, a0, a1, a2, vece);
+ break;
+ case TCG_COND_GT:
+ tcg_out_insn(s, VRRc, VCH, a0, a1, a2, vece);
+ break;
+ case TCG_COND_GTU:
+ tcg_out_insn(s, VRRc, VCHL, a0, a1, a2, vece);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ return need_inv;
+}
+
+static void tcg_out_cmp_vec(TCGContext *s, unsigned vece, TCGReg a0,
+ TCGReg a1, TCGReg a2, TCGCond cond)
+{
+ if (tcg_out_cmp_vec_noinv(s, vece, a0, a1, a2, cond)) {
+ tcg_out_insn(s, VRRc, VNO, a0, a0, a0, 0);
+ }
+}
+
static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
unsigned vecl, unsigned vece,
const TCGArg args[TCG_MAX_OP_ARGS],
@@ -2959,19 +3020,7 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
break;
case INDEX_op_cmp_vec:
- switch ((TCGCond)args[3]) {
- case TCG_COND_EQ:
- tcg_out_insn(s, VRRc, VCEQ, a0, a1, a2, vece);
- break;
- case TCG_COND_GT:
- tcg_out_insn(s, VRRc, VCH, a0, a1, a2, vece);
- break;
- case TCG_COND_GTU:
- tcg_out_insn(s, VRRc, VCHL, a0, a1, a2, vece);
- break;
- default:
- g_assert_not_reached();
- }
+ tcg_out_cmp_vec(s, vece, a0, a1, a2, args[3]);
break;
case INDEX_op_s390_vuph_vec:
@@ -3024,8 +3073,8 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
case INDEX_op_umax_vec:
case INDEX_op_umin_vec:
case INDEX_op_xor_vec:
- return 1;
case INDEX_op_cmp_vec:
+ return 1;
case INDEX_op_cmpsel_vec:
case INDEX_op_rotrv_vec:
return -1;
@@ -3039,68 +3088,14 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
}
}
-static bool expand_vec_cmp_noinv(TCGType type, unsigned vece, TCGv_vec v0,
- TCGv_vec v1, TCGv_vec v2, TCGCond cond)
-{
- bool need_swap = false, need_inv = false;
-
- switch (cond) {
- case TCG_COND_EQ:
- case TCG_COND_GT:
- case TCG_COND_GTU:
- break;
- case TCG_COND_NE:
- case TCG_COND_LE:
- case TCG_COND_LEU:
- need_inv = true;
- break;
- case TCG_COND_LT:
- case TCG_COND_LTU:
- need_swap = true;
- break;
- case TCG_COND_GE:
- case TCG_COND_GEU:
- need_swap = need_inv = true;
- break;
- default:
- g_assert_not_reached();
- }
-
- if (need_inv) {
- cond = tcg_invert_cond(cond);
- }
- if (need_swap) {
- TCGv_vec t1;
- t1 = v1, v1 = v2, v2 = t1;
- cond = tcg_swap_cond(cond);
- }
-
- vec_gen_4(INDEX_op_cmp_vec, type, vece, tcgv_vec_arg(v0),
- tcgv_vec_arg(v1), tcgv_vec_arg(v2), cond);
-
- return need_inv;
-}
-
-static void expand_vec_cmp(TCGType type, unsigned vece, TCGv_vec v0,
- TCGv_vec v1, TCGv_vec v2, TCGCond cond)
-{
- if (expand_vec_cmp_noinv(type, vece, v0, v1, v2, cond)) {
- tcg_gen_not_vec(vece, v0, v0);
- }
-}
-
static void expand_vec_cmpsel(TCGType type, unsigned vece, TCGv_vec v0,
TCGv_vec c1, TCGv_vec c2,
TCGv_vec v3, TCGv_vec v4, TCGCond cond)
{
TCGv_vec t = tcg_temp_new_vec(type);
- if (expand_vec_cmp_noinv(type, vece, t, c1, c2, cond)) {
- /* Invert the sense of the compare by swapping arguments. */
- tcg_gen_bitsel_vec(vece, v0, t, v4, v3);
- } else {
- tcg_gen_bitsel_vec(vece, v0, t, v3, v4);
- }
+ tcg_gen_cmp_vec(cond, vece, t, c1, c2);
+ tcg_gen_bitsel_vec(vece, v0, t, v3, v4);
tcg_temp_free_vec(t);
}
@@ -3153,10 +3148,6 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
v2 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
switch (opc) {
- case INDEX_op_cmp_vec:
- expand_vec_cmp(type, vece, v0, v1, v2, va_arg(va, TCGArg));
- break;
-
case INDEX_op_cmpsel_vec:
v3 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
v4 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
--
2.43.0
next prev parent reply other threads:[~2024-09-22 12:02 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-22 12:00 [PULL 00/31] tcg + linux-user patch queue Richard Henderson
2024-09-22 12:00 ` [PULL 01/31] tcg: Return TCGOp from tcg_gen_op[1-6] Richard Henderson
2024-09-22 12:00 ` [PULL 02/31] tcg: Propagate new TCGOp to add_as_label_use Richard Henderson
2024-09-22 12:00 ` [PULL 03/31] tcg: Fix iteration step in 32-bit gvec operation Richard Henderson
2024-09-22 12:00 ` [PULL 04/31] tcg: Export vec_gen_6 Richard Henderson
2024-09-22 12:00 ` [PULL 05/31] tcg/i386: Split out tcg_out_vex_modrm_type Richard Henderson
2024-09-22 12:00 ` [PULL 06/31] tcg/i386: Do not expand cmp_vec early Richard Henderson
2024-09-22 12:00 ` [PULL 07/31] tcg/i386: Do not expand cmpsel_vec early Richard Henderson
2024-09-22 12:00 ` [PULL 08/31] tcg/ppc: Do not expand cmp_vec early Richard Henderson
2024-09-22 12:00 ` Richard Henderson [this message]
2024-09-22 12:00 ` [PULL 10/31] tcg/optimize: Fold movcond with true and false values identical Richard Henderson
2024-09-22 12:00 ` [PULL 11/31] tcg/optimize: Optimize cmp_vec and cmpsel_vec Richard Henderson
2024-09-22 12:00 ` [PULL 12/31] tcg/optimize: Optimize bitsel_vec Richard Henderson
2024-09-22 12:00 ` [PULL 13/31] tcg/i386: Optimize cmpsel with constant 0 operand 3 Richard Henderson
2024-09-22 12:00 ` [PULL 14/31] tcg/i386: Implement cmp_vec with avx512 insns Richard Henderson
2024-09-22 12:00 ` [PULL 15/31] tcg/i386: Add predicate parameters to tcg_out_evex_opc Richard Henderson
2024-09-22 12:00 ` [PULL 16/31] tcg/i386: Implement cmpsel_vec with avx512 insns Richard Henderson
2024-09-22 12:00 ` [PULL 17/31] tcg/i386: Implement vector TST{EQ,NE} for avx512 Richard Henderson
2024-09-22 12:00 ` [PULL 18/31] tcg/ppc: Implement cmpsel_vec Richard Henderson
2024-09-22 12:01 ` [PULL 19/31] tcg/ppc: Optimize cmpsel with constant 0/-1 arguments Richard Henderson
2024-09-22 12:01 ` [PULL 20/31] tcg/s390x: Implement cmpsel_vec Richard Henderson
2024-09-22 12:01 ` [PULL 21/31] tcg/s390x: Optimize cmpsel with constant 0/-1 arguments Richard Henderson
2024-09-22 12:01 ` [PULL 22/31] target/ppc: Fix lxvx/stxvx facility check Richard Henderson
2024-09-22 12:01 ` [PULL 23/31] linux-user: update syscall_nr.h to Linux v6.10 Richard Henderson
2024-09-22 12:01 ` [PULL 24/31] linux-user, mips: update syscall-args-o32.c.inc " Richard Henderson
2024-09-22 12:01 ` [PULL 25/31] linux-user: update syscall.tbl " Richard Henderson
2024-09-22 12:01 ` [PULL 26/31] linux-user,aarch64: move to syscalltbl file Richard Henderson
2024-09-22 12:01 ` [PULL 27/31] linux-user,openrisc: " Richard Henderson
2024-09-22 12:01 ` [PULL 28/31] linux-user,riscv: " Richard Henderson
2024-09-22 12:01 ` [PULL 29/31] linux-user,hexagon: " Richard Henderson
2024-09-22 12:01 ` [PULL 30/31] linux-user,loongarch: " Richard Henderson
2024-09-22 12:01 ` [PULL 31/31] linux-user: update syscall.tbl to Linux v6.11 Richard Henderson
2024-09-27 15:18 ` [PULL 00/31] tcg + linux-user 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=20240922120112.5067-10-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=peter.maydell@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).