From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Subject: [PATCH 17/20] tcg/i386: Implement avx512 min/max/abs
Date: Sat, 18 Dec 2021 11:42:47 -0800 [thread overview]
Message-ID: <20211218194250.247633-18-richard.henderson@linaro.org> (raw)
In-Reply-To: <20211218194250.247633-1-richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
tcg/i386/tcg-target.c.inc | 18 +++++++++++-------
1 file changed, 11 insertions(+), 7 deletions(-)
diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc
index 447aab7438..22eaa53cb1 100644
--- a/tcg/i386/tcg-target.c.inc
+++ b/tcg/i386/tcg-target.c.inc
@@ -312,6 +312,7 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct)
#define OPC_PABSB (0x1c | P_EXT38 | P_DATA16)
#define OPC_PABSW (0x1d | P_EXT38 | P_DATA16)
#define OPC_PABSD (0x1e | P_EXT38 | P_DATA16)
+#define OPC_VPABSQ (0x1f | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
#define OPC_PACKSSDW (0x6b | P_EXT | P_DATA16)
#define OPC_PACKSSWB (0x63 | P_EXT | P_DATA16)
#define OPC_PACKUSDW (0x2b | P_EXT38 | P_DATA16)
@@ -338,15 +339,19 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct)
#define OPC_PMAXSB (0x3c | P_EXT38 | P_DATA16)
#define OPC_PMAXSW (0xee | P_EXT | P_DATA16)
#define OPC_PMAXSD (0x3d | P_EXT38 | P_DATA16)
+#define OPC_VPMAXSQ (0x3d | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
#define OPC_PMAXUB (0xde | P_EXT | P_DATA16)
#define OPC_PMAXUW (0x3e | P_EXT38 | P_DATA16)
#define OPC_PMAXUD (0x3f | P_EXT38 | P_DATA16)
+#define OPC_VPMAXUQ (0x3f | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
#define OPC_PMINSB (0x38 | P_EXT38 | P_DATA16)
#define OPC_PMINSW (0xea | P_EXT | P_DATA16)
#define OPC_PMINSD (0x39 | P_EXT38 | P_DATA16)
+#define OPC_VPMINSQ (0x39 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
#define OPC_PMINUB (0xda | P_EXT | P_DATA16)
#define OPC_PMINUW (0x3a | P_EXT38 | P_DATA16)
#define OPC_PMINUD (0x3b | P_EXT38 | P_DATA16)
+#define OPC_VPMINUQ (0x3b | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
#define OPC_PMOVSXBW (0x20 | P_EXT38 | P_DATA16)
#define OPC_PMOVSXWD (0x23 | P_EXT38 | P_DATA16)
#define OPC_PMOVSXDQ (0x25 | P_EXT38 | P_DATA16)
@@ -2748,16 +2753,16 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
OPC_PACKUSWB, OPC_PACKUSDW, OPC_UD2, OPC_UD2
};
static int const smin_insn[4] = {
- OPC_PMINSB, OPC_PMINSW, OPC_PMINSD, OPC_UD2
+ OPC_PMINSB, OPC_PMINSW, OPC_PMINSD, OPC_VPMINSQ
};
static int const smax_insn[4] = {
- OPC_PMAXSB, OPC_PMAXSW, OPC_PMAXSD, OPC_UD2
+ OPC_PMAXSB, OPC_PMAXSW, OPC_PMAXSD, OPC_VPMAXSQ
};
static int const umin_insn[4] = {
- OPC_PMINUB, OPC_PMINUW, OPC_PMINUD, OPC_UD2
+ OPC_PMINUB, OPC_PMINUW, OPC_PMINUD, OPC_VPMINUQ
};
static int const umax_insn[4] = {
- OPC_PMAXUB, OPC_PMAXUW, OPC_PMAXUD, OPC_UD2
+ OPC_PMAXUB, OPC_PMAXUW, OPC_PMAXUD, OPC_VPMAXUQ
};
static int const rotlv_insn[4] = {
OPC_UD2, OPC_UD2, OPC_VPROLVD, OPC_VPROLVQ
@@ -2793,8 +2798,7 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
OPC_UD2, OPC_VPSHRDVW, OPC_VPSHRDVD, OPC_VPSHRDVQ
};
static int const abs_insn[4] = {
- /* TODO: AVX512 adds support for MO_64. */
- OPC_PABSB, OPC_PABSW, OPC_PABSD, OPC_UD2
+ OPC_PABSB, OPC_PABSW, OPC_PABSD, OPC_VPABSQ
};
TCGType type = vecl + TCG_TYPE_V64;
@@ -3377,7 +3381,7 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
case INDEX_op_umin_vec:
case INDEX_op_umax_vec:
case INDEX_op_abs_vec:
- return vece <= MO_32;
+ return vece <= MO_32 || have_avx512vl;
default:
return 0;
--
2.25.1
next prev parent reply other threads:[~2021-12-18 19:52 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-18 19:42 [PATCH 00/20] tcg: vector improvements Richard Henderson
2021-12-18 19:42 ` [PATCH 01/20] tcg/optimize: Fix folding of vector ops Richard Henderson
2021-12-19 11:37 ` Philippe Mathieu-Daudé
2021-12-18 19:42 ` [PATCH 02/20] tcg: Add opcodes for vector nand, nor, eqv Richard Henderson
2021-12-19 11:28 ` Philippe Mathieu-Daudé
2022-02-01 18:28 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 03/20] tcg/ppc: Implement vector NAND, NOR, EQV Richard Henderson
2021-12-19 0:15 ` Philippe Mathieu-Daudé
2022-02-01 18:29 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 04/20] tcg/s390x: " Richard Henderson
2021-12-19 0:17 ` Philippe Mathieu-Daudé
2022-02-01 18:29 ` Alex Bennée
2022-02-01 18:31 ` Alex Bennée
2024-01-03 13:21 ` Philippe Mathieu-Daudé
2024-01-03 21:58 ` Richard Henderson
2021-12-18 19:42 ` [PATCH 05/20] tcg/i386: Detect AVX512 Richard Henderson
2022-02-01 18:41 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 06/20] tcg/i386: Add tcg_out_evex_opc Richard Henderson
2022-02-01 19:20 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 07/20] tcg/i386: Use tcg_can_emit_vec_op in expand_vec_cmp_noinv Richard Henderson
2022-02-01 19:21 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 08/20] tcg/i386: Implement avx512 variable shifts Richard Henderson
2022-02-01 20:33 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 09/20] tcg/i386: Implement avx512 scalar shift Richard Henderson
2022-02-02 13:48 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 10/20] tcg/i386: Implement avx512 immediate sari shift Richard Henderson
2022-02-02 14:02 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 11/20] tcg/i386: Implement avx512 immediate rotate Richard Henderson
2022-02-02 14:05 ` Alex Bennée
2022-02-03 1:26 ` Richard Henderson
2021-12-18 19:42 ` [PATCH 12/20] tcg/i386: Implement avx512 variable rotate Richard Henderson
2022-02-02 14:14 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 13/20] tcg/i386: Support avx512vbmi2 vector shift-double instructions Richard Henderson
2022-02-02 14:28 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 14/20] tcg/i386: Expand vector word rotate as avx512vbmi2 shift-double Richard Henderson
2022-02-03 10:32 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 15/20] tcg/i386: Remove rotls_vec from tcg_target_op_def Richard Henderson
2022-02-03 10:34 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 16/20] tcg/i386: Expand scalar rotate with avx512 insns Richard Henderson
2022-02-03 10:38 ` Alex Bennée
2021-12-18 19:42 ` Richard Henderson [this message]
2022-02-03 10:44 ` [PATCH 17/20] tcg/i386: Implement avx512 min/max/abs Alex Bennée
2021-12-18 19:42 ` [PATCH 18/20] tcg/i386: Implement avx512 multiply Richard Henderson
2022-02-03 10:45 ` Alex Bennée
2021-12-18 19:42 ` [PATCH 19/20] tcg/i386: Implement more logical operations for avx512 Richard Henderson
2022-02-03 10:46 ` Alex Bennée
2022-02-03 21:54 ` Richard Henderson
2021-12-18 19:42 ` [PATCH 20/20] tcg/i386: Implement bitsel " Richard Henderson
2022-02-03 10:51 ` Alex Bennée
2022-01-29 9:28 ` [PATCH 00/20] tcg: vector improvements Richard Henderson
2022-02-03 10:25 ` Alex Bennée
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=20211218194250.247633-18-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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.