From patchwork Fri Jan 26 04:57:41 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 125892 Delivered-To: patch@linaro.org Received: by 10.46.84.92 with SMTP id y28csp72768ljd; Thu, 25 Jan 2018 21:01:22 -0800 (PST) X-Google-Smtp-Source: AH8x226eW5oEhlrbBFfQSqjmWuCV4tBgi3tw5DTW9+9a+5iSrC4NeQz/+yEHxvK44xjlB04wF+JK X-Received: by 10.13.248.195 with SMTP id i186mr10521661ywf.239.1516942882635; Thu, 25 Jan 2018 21:01:22 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1516942882; cv=none; d=google.com; s=arc-20160816; b=EPfKHL1pMu6gYFMJgwERtj9cvDXA63uWf4cUu+AenZCefjY6l0UEtZXkmLr5XVDSHW V03Z/yyfJOwHNf+LCDWCX46T81c3k+x5ifaTAOFHvfaUuu+L8MJYaLLrEXZKcrXlU/qE puveT53qQdYD46QPxMz+bt/gdCKOKYC4WRN/YQseoqlqxPi5AwEwrQ7neb4+P6uFQ7mb k8hEjXEJhnWaifB7mEib92fB3FKN88U2ZZXVJU1cEbicLysssZ9ImWQzLcpJAxrwKF19 5kZgfweS1P4WnRZWT6geGpXrMbO0EzX83UCKL/7EkUiXIV1lunqRVJzp8z07bztCory5 HwtA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:cc:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:subject:references:in-reply-to :message-id:date:to:from:dkim-signature:arc-authentication-results; bh=xtOI1nUDKtGGcgYrathFK7ztryVGvh92iIOXjnJYbN0=; b=k4PEHtHiHmsPId38cYk8z56gCcbkt/41Quon2CxF5tW4aEETb3HP5nzAHn0+R9Eh4t qI/MVrjjZK00coT525K8hGUMPAKPfAd3csWL89vdruU2LZT2ttf7iuHEvMKHYzKX0cvl NNhz9aDGAGNWV47Exp8Q7eGG0ti8iEkPmu3RHsl0OaNNZQpfjaa96AwDVkqeKbKpLwe7 nrjI++laXoTlILLTRrLToInKulpMbZg3cwoh4GlyQydSYa1ufE2WQB5fA1cuSt6K+u/A EYlwAI/PkQ3pWJ5lRtQUqPLWFymE13KRo+f/FKZSdQ6HnbpFNSBBeDvJGgp/Hj6j1q1A kzRg== ARC-Authentication-Results: i=1; mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=PE1IUgIl; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) smtp.mailfrom=qemu-devel-bounces+patch=linaro.org@nongnu.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [2001:4830:134:3::11]) by mx.google.com with ESMTPS id 81si3482314ybg.605.2018.01.25.21.01.22 for (version=TLS1 cipher=AES128-SHA bits=128/128); Thu, 25 Jan 2018 21:01:22 -0800 (PST) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) client-ip=2001:4830:134:3::11; Authentication-Results: mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=PE1IUgIl; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) smtp.mailfrom=qemu-devel-bounces+patch=linaro.org@nongnu.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1]:58878 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eew8f-0001ud-SX for patch@linaro.org; Fri, 26 Jan 2018 00:01:21 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:50464) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eew5x-0008UR-61 for qemu-devel@nongnu.org; Thu, 25 Jan 2018 23:58:37 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1eew5s-0004AR-6j for qemu-devel@nongnu.org; Thu, 25 Jan 2018 23:58:33 -0500 Received: from mail-pg0-x236.google.com ([2607:f8b0:400e:c05::236]:34806) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1eew5r-00049K-SV for qemu-devel@nongnu.org; Thu, 25 Jan 2018 23:58:28 -0500 Received: by mail-pg0-x236.google.com with SMTP id r19so6545292pgn.1 for ; Thu, 25 Jan 2018 20:58:27 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=xtOI1nUDKtGGcgYrathFK7ztryVGvh92iIOXjnJYbN0=; b=PE1IUgIlLdaz2DWfUJvjlFvTfrJZoTkVVI4ZKOJ+sLZ9DRr8pRo35/oNluGOmBWZE+ d/6tb5Lq0V9b0XEgBgm7B9TXxytcXkNpDUF2j5Ry5DcJ5wNDGkHu6E7sg9w9jLfB7UCx pliPy3z9FMJqjpJtqk2416KcRVN/B7x+ewBWc= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=xtOI1nUDKtGGcgYrathFK7ztryVGvh92iIOXjnJYbN0=; b=iwOEZ1GhtlUz8ymgq02+Jr/OAgovP5nS2LNxGxHwFyTxV2fbQ/VDHC60AyWIUHDyG8 I3fafPSp5MTqXXG/VW9XTEsUVKxcLEeeTkXksZ2iRSLiw/bTmzUUNu0UbbKy8HkwQfku gQKTYeK68kLUNWfXMwrvIVoHP4DOPZHXb1j2bqgY+jhtn5UrPUncCECOFv/7Wl1LArx4 VXs1yxfw1cPqNMTTeyckUjc/Rlw/DLb5H/gu297Qxxi8jQDu+dZK5lD8BkHR4Gktl0N7 nCsMsAEWapuzzTi4UvSJH2J42WAnMsYKkYvfLWFSdv7LvWmVipR4lhAfufYA0Tnos+AJ 0xCg== X-Gm-Message-State: AKwxytdwuUWt/K9Q3EtzAKIJr62faY7/szEdCRSz3/h+e2b/+/hWlxSf Xr6KLzDPU0m+fSF07E/wrjRxVLFOhac= X-Received: by 10.99.115.82 with SMTP id d18mr14706797pgn.312.1516942705227; Thu, 25 Jan 2018 20:58:25 -0800 (PST) Received: from cloudburst.twiddle.net (174-21-6-47.tukw.qwest.net. [174.21.6.47]) by smtp.gmail.com with ESMTPSA id q67sm20460313pfi.164.2018.01.25.20.58.23 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Thu, 25 Jan 2018 20:58:24 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Date: Thu, 25 Jan 2018 20:57:41 -0800 Message-Id: <20180126045742.5487-20-richard.henderson@linaro.org> X-Mailer: git-send-email 2.14.3 In-Reply-To: <20180126045742.5487-1-richard.henderson@linaro.org> References: <20180126045742.5487-1-richard.henderson@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:400e:c05::236 Subject: [Qemu-devel] [PATCH v11 19/20] tcg/i386: Add vector operations X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: peter.maydell@linaro.org Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" The x86 vector instruction set is extremely irregular. With newer editions, Intel has filled in some of the blanks. However, we don't get many 64-bit operations until SSE4.2, introduced in 2009. The subsequent edition was for AVX1, introduced in 2011, which added three-operand addressing, and adjusts how all instructions should be encoded. Given the relatively narrow 2 year window between possible to support and desirable to support, and to vastly simplify code maintainence, I am only planning to support AVX1 and later cpus. Signed-off-by: Richard Henderson --- tcg/i386/tcg-target.h | 41 +- tcg/i386/tcg-target.opc.h | 13 + tcg/i386/tcg-target.inc.c | 987 +++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 987 insertions(+), 54 deletions(-) create mode 100644 tcg/i386/tcg-target.opc.h -- 2.14.3 diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index b89dababf4..9fdf37f23c 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -30,10 +30,10 @@ #ifdef __x86_64__ # define TCG_TARGET_REG_BITS 64 -# define TCG_TARGET_NB_REGS 16 +# define TCG_TARGET_NB_REGS 32 #else # define TCG_TARGET_REG_BITS 32 -# define TCG_TARGET_NB_REGS 8 +# define TCG_TARGET_NB_REGS 24 #endif typedef enum { @@ -56,6 +56,26 @@ typedef enum { TCG_REG_R13, TCG_REG_R14, TCG_REG_R15, + + TCG_REG_XMM0, + TCG_REG_XMM1, + TCG_REG_XMM2, + TCG_REG_XMM3, + TCG_REG_XMM4, + TCG_REG_XMM5, + TCG_REG_XMM6, + TCG_REG_XMM7, + + /* 64-bit registers; likewise always define. */ + TCG_REG_XMM8, + TCG_REG_XMM9, + TCG_REG_XMM10, + TCG_REG_XMM11, + TCG_REG_XMM12, + TCG_REG_XMM13, + TCG_REG_XMM14, + TCG_REG_XMM15, + TCG_REG_RAX = TCG_REG_EAX, TCG_REG_RCX = TCG_REG_ECX, TCG_REG_RDX = TCG_REG_EDX, @@ -77,6 +97,8 @@ typedef enum { extern bool have_bmi1; extern bool have_popcnt; +extern bool have_avx1; +extern bool have_avx2; /* optional instructions */ #define TCG_TARGET_HAS_div2_i32 1 @@ -146,6 +168,21 @@ extern bool have_popcnt; #define TCG_TARGET_HAS_mulsh_i64 0 #endif +/* We do not support older SSE systems, only beginning with AVX1. */ +#define TCG_TARGET_HAS_v64 have_avx1 +#define TCG_TARGET_HAS_v128 have_avx1 +#define TCG_TARGET_HAS_v256 have_avx2 + +#define TCG_TARGET_HAS_andc_vec 1 +#define TCG_TARGET_HAS_orc_vec 0 +#define TCG_TARGET_HAS_not_vec 0 +#define TCG_TARGET_HAS_neg_vec 0 +#define TCG_TARGET_HAS_shi_vec 1 +#define TCG_TARGET_HAS_shs_vec 0 +#define TCG_TARGET_HAS_shv_vec 0 +#define TCG_TARGET_HAS_cmp_vec 1 +#define TCG_TARGET_HAS_mul_vec 1 + #define TCG_TARGET_deposit_i32_valid(ofs, len) \ (((ofs) == 0 && (len) == 8) || ((ofs) == 8 && (len) == 8) || \ ((ofs) == 0 && (len) == 16)) diff --git a/tcg/i386/tcg-target.opc.h b/tcg/i386/tcg-target.opc.h new file mode 100644 index 0000000000..e5fa88ba25 --- /dev/null +++ b/tcg/i386/tcg-target.opc.h @@ -0,0 +1,13 @@ +/* Target-specific opcodes for host vector expansion. These will be + emitted by tcg_expand_vec_op. For those familiar with GCC internals, + consider these to be UNSPEC with names. */ + +DEF(x86_shufps_vec, 1, 2, 1, IMPLVEC) +DEF(x86_vpblendvb_vec, 1, 3, 0, IMPLVEC) +DEF(x86_blend_vec, 1, 2, 1, IMPLVEC) +DEF(x86_packss_vec, 1, 2, 0, IMPLVEC) +DEF(x86_packus_vec, 1, 2, 0, IMPLVEC) +DEF(x86_psrldq_vec, 1, 1, 1, IMPLVEC) +DEF(x86_vperm2i128_vec, 1, 2, 1, IMPLVEC) +DEF(x86_punpckl_vec, 1, 2, 0, IMPLVEC) +DEF(x86_punpckh_vec, 1, 2, 0, IMPLVEC) diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c index 63d27f10e7..fc05909d1d 100644 --- a/tcg/i386/tcg-target.inc.c +++ b/tcg/i386/tcg-target.inc.c @@ -28,9 +28,14 @@ static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { #if TCG_TARGET_REG_BITS == 64 "%rax", "%rcx", "%rdx", "%rbx", "%rsp", "%rbp", "%rsi", "%rdi", - "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", #else "%eax", "%ecx", "%edx", "%ebx", "%esp", "%ebp", "%esi", "%edi", +#endif + "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", + "%xmm0", "%xmm1", "%xmm2", "%xmm3", "%xmm4", "%xmm5", "%xmm6", "%xmm7", +#if TCG_TARGET_REG_BITS == 64 + "%xmm8", "%xmm9", "%xmm10", "%xmm11", + "%xmm12", "%xmm13", "%xmm14", "%xmm15", #endif }; #endif @@ -60,6 +65,28 @@ static const int tcg_target_reg_alloc_order[] = { TCG_REG_ECX, TCG_REG_EDX, TCG_REG_EAX, +#endif + TCG_REG_XMM0, + TCG_REG_XMM1, + TCG_REG_XMM2, + TCG_REG_XMM3, + TCG_REG_XMM4, + TCG_REG_XMM5, +#ifndef _WIN64 + /* The Win64 ABI has xmm6-xmm15 as caller-saves, and we do not save + any of them. Therefore only allow xmm0-xmm5 to be allocated. */ + TCG_REG_XMM6, + TCG_REG_XMM7, +#if TCG_TARGET_REG_BITS == 64 + TCG_REG_XMM8, + TCG_REG_XMM9, + TCG_REG_XMM10, + TCG_REG_XMM11, + TCG_REG_XMM12, + TCG_REG_XMM13, + TCG_REG_XMM14, + TCG_REG_XMM15, +#endif #endif }; @@ -94,7 +121,7 @@ static const int tcg_target_call_oarg_regs[] = { #define TCG_CT_CONST_I32 0x400 #define TCG_CT_CONST_WSZ 0x800 -/* Registers used with L constraint, which are the first argument +/* Registers used with L constraint, which are the first argument registers on x86_64, and two random call clobbered registers on i386. */ #if TCG_TARGET_REG_BITS == 64 @@ -125,6 +152,8 @@ static bool have_cmov; it there. Therefore we always define the variable. */ bool have_bmi1; bool have_popcnt; +bool have_avx1; +bool have_avx2; #ifdef CONFIG_CPUID_H static bool have_movbe; @@ -148,6 +177,8 @@ static void patch_reloc(tcg_insn_unit *code_ptr, int type, if (value != (int32_t)value) { tcg_abort(); } + /* FALLTHRU */ + case R_386_32: tcg_patch32(code_ptr, value); break; case R_386_PC8: @@ -162,6 +193,14 @@ static void patch_reloc(tcg_insn_unit *code_ptr, int type, } } +#if TCG_TARGET_REG_BITS == 64 +#define ALL_GENERAL_REGS 0x0000ffffu +#define ALL_VECTOR_REGS 0xffff0000u +#else +#define ALL_GENERAL_REGS 0x000000ffu +#define ALL_VECTOR_REGS 0x00ff0000u +#endif + /* parse target specific constraints */ static const char *target_parse_constraint(TCGArgConstraint *ct, const char *ct_str, TCGType type) @@ -192,21 +231,29 @@ static const char *target_parse_constraint(TCGArgConstraint *ct, tcg_regset_set_reg(ct->u.regs, TCG_REG_EDI); break; case 'q': + /* A register that can be used as a byte operand. */ ct->ct |= TCG_CT_REG; ct->u.regs = TCG_TARGET_REG_BITS == 64 ? 0xffff : 0xf; break; case 'Q': + /* A register with an addressable second byte (e.g. %ah). */ ct->ct |= TCG_CT_REG; ct->u.regs = 0xf; break; case 'r': + /* A general register. */ ct->ct |= TCG_CT_REG; - ct->u.regs = TCG_TARGET_REG_BITS == 64 ? 0xffff : 0xff; + ct->u.regs |= ALL_GENERAL_REGS; break; case 'W': /* With TZCNT/LZCNT, we can have operand-size as an input. */ ct->ct |= TCG_CT_CONST_WSZ; break; + case 'x': + /* A vector register. */ + ct->ct |= TCG_CT_REG; + ct->u.regs |= ALL_VECTOR_REGS; + break; /* qemu_ld/st address constraint */ case 'L': @@ -277,14 +324,17 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type, # define P_REXB_RM 0 # define P_GS 0 #endif -#define P_SIMDF3 0x10000 /* 0xf3 opcode prefix */ -#define P_SIMDF2 0x20000 /* 0xf2 opcode prefix */ +#define P_EXT3A 0x10000 /* 0x0f 0x3a opcode prefix */ +#define P_SIMDF3 0x20000 /* 0xf3 opcode prefix */ +#define P_SIMDF2 0x40000 /* 0xf2 opcode prefix */ +#define P_VEXL 0x80000 /* Set VEX.L = 1 */ #define OPC_ARITH_EvIz (0x81) #define OPC_ARITH_EvIb (0x83) #define OPC_ARITH_GvEv (0x03) /* ... plus (ARITH_FOO << 3) */ #define OPC_ANDN (0xf2 | P_EXT38) #define OPC_ADD_GvEv (OPC_ARITH_GvEv | (ARITH_ADD << 3)) +#define OPC_BLENDPS (0x0c | P_EXT3A | P_DATA16) #define OPC_BSF (0xbc | P_EXT) #define OPC_BSR (0xbd | P_EXT) #define OPC_BSWAP (0xc8 | P_EXT) @@ -310,11 +360,68 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type, #define OPC_MOVL_Iv (0xb8) #define OPC_MOVBE_GyMy (0xf0 | P_EXT38) #define OPC_MOVBE_MyGy (0xf1 | P_EXT38) +#define OPC_MOVD_VyEy (0x6e | P_EXT | P_DATA16) +#define OPC_MOVD_EyVy (0x7e | P_EXT | P_DATA16) +#define OPC_MOVDDUP (0x12 | P_EXT | P_SIMDF2) +#define OPC_MOVDQA_VxWx (0x6f | P_EXT | P_DATA16) +#define OPC_MOVDQA_WxVx (0x7f | P_EXT | P_DATA16) +#define OPC_MOVDQU_VxWx (0x6f | P_EXT | P_SIMDF3) +#define OPC_MOVDQU_WxVx (0x7f | P_EXT | P_SIMDF3) +#define OPC_MOVQ_VqWq (0x7e | P_EXT | P_SIMDF3) +#define OPC_MOVQ_WqVq (0xd6 | P_EXT | P_DATA16) #define OPC_MOVSBL (0xbe | P_EXT) #define OPC_MOVSWL (0xbf | P_EXT) #define OPC_MOVSLQ (0x63 | P_REXW) #define OPC_MOVZBL (0xb6 | P_EXT) #define OPC_MOVZWL (0xb7 | P_EXT) +#define OPC_PACKSSDW (0x6b | P_EXT | P_DATA16) +#define OPC_PACKSSWB (0x63 | P_EXT | P_DATA16) +#define OPC_PACKUSDW (0x2b | P_EXT38 | P_DATA16) +#define OPC_PACKUSWB (0x67 | P_EXT | P_DATA16) +#define OPC_PADDB (0xfc | P_EXT | P_DATA16) +#define OPC_PADDW (0xfd | P_EXT | P_DATA16) +#define OPC_PADDD (0xfe | P_EXT | P_DATA16) +#define OPC_PADDQ (0xd4 | P_EXT | P_DATA16) +#define OPC_PAND (0xdb | P_EXT | P_DATA16) +#define OPC_PANDN (0xdf | P_EXT | P_DATA16) +#define OPC_PBLENDW (0x0e | P_EXT3A | P_DATA16) +#define OPC_PCMPEQB (0x74 | P_EXT | P_DATA16) +#define OPC_PCMPEQW (0x75 | P_EXT | P_DATA16) +#define OPC_PCMPEQD (0x76 | P_EXT | P_DATA16) +#define OPC_PCMPEQQ (0x29 | P_EXT38 | P_DATA16) +#define OPC_PCMPGTB (0x64 | P_EXT | P_DATA16) +#define OPC_PCMPGTW (0x65 | P_EXT | P_DATA16) +#define OPC_PCMPGTD (0x66 | P_EXT | P_DATA16) +#define OPC_PCMPGTQ (0x37 | P_EXT38 | P_DATA16) +#define OPC_PMOVSXBW (0x20 | P_EXT38 | P_DATA16) +#define OPC_PMOVSXWD (0x23 | P_EXT38 | P_DATA16) +#define OPC_PMOVSXDQ (0x25 | P_EXT38 | P_DATA16) +#define OPC_PMOVZXBW (0x30 | P_EXT38 | P_DATA16) +#define OPC_PMOVZXWD (0x33 | P_EXT38 | P_DATA16) +#define OPC_PMOVZXDQ (0x35 | P_EXT38 | P_DATA16) +#define OPC_PMULLW (0xd5 | P_EXT | P_DATA16) +#define OPC_PMULLD (0x40 | P_EXT38 | P_DATA16) +#define OPC_POR (0xeb | P_EXT | P_DATA16) +#define OPC_PSHUFB (0x00 | P_EXT38 | P_DATA16) +#define OPC_PSHUFD (0x70 | P_EXT | P_DATA16) +#define OPC_PSHUFLW (0x70 | P_EXT | P_SIMDF2) +#define OPC_PSHUFHW (0x70 | P_EXT | P_SIMDF3) +#define OPC_PSHIFTW_Ib (0x71 | P_EXT | P_DATA16) /* /2 /6 /4 */ +#define OPC_PSHIFTD_Ib (0x72 | P_EXT | P_DATA16) /* /2 /6 /4 */ +#define OPC_PSHIFTQ_Ib (0x73 | P_EXT | P_DATA16) /* /2 /6 /4 */ +#define OPC_PSUBB (0xf8 | P_EXT | P_DATA16) +#define OPC_PSUBW (0xf9 | P_EXT | P_DATA16) +#define OPC_PSUBD (0xfa | P_EXT | P_DATA16) +#define OPC_PSUBQ (0xfb | P_EXT | P_DATA16) +#define OPC_PUNPCKLBW (0x60 | P_EXT | P_DATA16) +#define OPC_PUNPCKLWD (0x61 | P_EXT | P_DATA16) +#define OPC_PUNPCKLDQ (0x62 | P_EXT | P_DATA16) +#define OPC_PUNPCKLQDQ (0x6c | P_EXT | P_DATA16) +#define OPC_PUNPCKHBW (0x68 | P_EXT | P_DATA16) +#define OPC_PUNPCKHWD (0x69 | P_EXT | P_DATA16) +#define OPC_PUNPCKHDQ (0x6a | P_EXT | P_DATA16) +#define OPC_PUNPCKHQDQ (0x6d | P_EXT | P_DATA16) +#define OPC_PXOR (0xef | P_EXT | P_DATA16) #define OPC_POP_r32 (0x58) #define OPC_POPCNT (0xb8 | P_EXT | P_SIMDF3) #define OPC_PUSH_r32 (0x50) @@ -326,14 +433,26 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type, #define OPC_SHIFT_Ib (0xc1) #define OPC_SHIFT_cl (0xd3) #define OPC_SARX (0xf7 | P_EXT38 | P_SIMDF3) +#define OPC_SHUFPS (0xc6 | P_EXT) #define OPC_SHLX (0xf7 | P_EXT38 | P_DATA16) #define OPC_SHRX (0xf7 | P_EXT38 | P_SIMDF2) #define OPC_TESTL (0x85) #define OPC_TZCNT (0xbc | P_EXT | P_SIMDF3) +#define OPC_UD2 (0x0b | P_EXT) +#define OPC_VPBLENDD (0x02 | P_EXT3A | P_DATA16) +#define OPC_VPBLENDVB (0x4c | P_EXT3A | P_DATA16) +#define OPC_VPBROADCASTB (0x78 | P_EXT38 | P_DATA16) +#define OPC_VPBROADCASTW (0x79 | P_EXT38 | P_DATA16) +#define OPC_VPBROADCASTD (0x58 | P_EXT38 | P_DATA16) +#define OPC_VPBROADCASTQ (0x59 | P_EXT38 | P_DATA16) +#define OPC_VPERMQ (0x00 | P_EXT3A | P_DATA16 | P_REXW) +#define OPC_VPERM2I128 (0x46 | P_EXT3A | P_DATA16 | P_VEXL) +#define OPC_VZEROUPPER (0x77 | P_EXT) #define OPC_XCHG_ax_r32 (0x90) #define OPC_GRP3_Ev (0xf7) #define OPC_GRP5 (0xff) +#define OPC_GRP14 (0x73 | P_EXT | P_DATA16) /* Group 1 opcode extensions for 0x80-0x83. These are also used as modifiers for OPC_ARITH. */ @@ -439,10 +558,12 @@ static void tcg_out_opc(TCGContext *s, int opc, int r, int rm, int x) tcg_out8(s, (uint8_t)(rex | 0x40)); } - if (opc & (P_EXT | P_EXT38)) { + if (opc & (P_EXT | P_EXT38 | P_EXT3A)) { tcg_out8(s, 0x0f); if (opc & P_EXT38) { tcg_out8(s, 0x38); + } else if (opc & P_EXT3A) { + tcg_out8(s, 0x3a); } } @@ -459,10 +580,12 @@ static void tcg_out_opc(TCGContext *s, int opc) } else if (opc & P_SIMDF2) { tcg_out8(s, 0xf2); } - if (opc & (P_EXT | P_EXT38)) { + if (opc & (P_EXT | P_EXT38 | P_EXT3A)) { tcg_out8(s, 0x0f); if (opc & P_EXT38) { tcg_out8(s, 0x38); + } else if (opc & P_EXT3A) { + tcg_out8(s, 0x3a); } } tcg_out8(s, opc); @@ -479,34 +602,42 @@ static void tcg_out_modrm(TCGContext *s, int opc, int r, int rm) tcg_out8(s, 0xc0 | (LOWREGMASK(r) << 3) | LOWREGMASK(rm)); } -static void tcg_out_vex_modrm(TCGContext *s, int opc, int r, int v, int rm) +static void tcg_out_vex_opc(TCGContext *s, int opc, int r, int v, + int rm, int index) { int tmp; - if ((opc & (P_REXW | P_EXT | P_EXT38)) || (rm & 8)) { + /* Use the two byte form if possible, which cannot encode + VEX.W, VEX.B, VEX.X, or an m-mmmm field other than P_EXT. */ + if ((opc & (P_EXT | P_EXT38 | P_EXT3A | P_REXW)) == P_EXT + && ((rm | index) & 8) == 0) { + /* Two byte VEX prefix. */ + tcg_out8(s, 0xc5); + + tmp = (r & 8 ? 0 : 0x80); /* VEX.R */ + } else { /* Three byte VEX prefix. */ tcg_out8(s, 0xc4); /* VEX.m-mmmm */ - if (opc & P_EXT38) { + if (opc & P_EXT3A) { + tmp = 3; + } else if (opc & P_EXT38) { tmp = 2; } else if (opc & P_EXT) { tmp = 1; } else { - tcg_abort(); + g_assert_not_reached(); } - tmp |= 0x40; /* VEX.X */ - tmp |= (r & 8 ? 0 : 0x80); /* VEX.R */ - tmp |= (rm & 8 ? 0 : 0x20); /* VEX.B */ + tmp |= (r & 8 ? 0 : 0x80); /* VEX.R */ + tmp |= (index & 8 ? 0 : 0x40); /* VEX.X */ + tmp |= (rm & 8 ? 0 : 0x20); /* VEX.B */ tcg_out8(s, tmp); - tmp = (opc & P_REXW ? 0x80 : 0); /* VEX.W */ - } else { - /* Two byte VEX prefix. */ - tcg_out8(s, 0xc5); - - tmp = (r & 8 ? 0 : 0x80); /* VEX.R */ + tmp = (opc & P_REXW ? 0x80 : 0); /* VEX.W */ } + + tmp |= (opc & P_VEXL ? 0x04 : 0); /* VEX.L */ /* VEX.pp */ if (opc & P_DATA16) { tmp |= 1; /* 0x66 */ @@ -518,6 +649,11 @@ static void tcg_out_vex_modrm(TCGContext *s, int opc, int r, int v, int rm) tmp |= (~v & 15) << 3; /* VEX.vvvv */ tcg_out8(s, tmp); tcg_out8(s, opc); +} + +static void tcg_out_vex_modrm(TCGContext *s, int opc, int r, int v, int rm) +{ + tcg_out_vex_opc(s, opc, r, v, rm, 0); tcg_out8(s, 0xc0 | (LOWREGMASK(r) << 3) | LOWREGMASK(rm)); } @@ -526,8 +662,8 @@ static void tcg_out_vex_modrm(TCGContext *s, int opc, int r, int v, int rm) mode for absolute addresses, ~RM is the size of the immediate operand that will follow the instruction. */ -static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, - int index, int shift, intptr_t offset) +static void tcg_out_sib_offset(TCGContext *s, int r, int rm, int index, + int shift, intptr_t offset) { int mod, len; @@ -538,7 +674,6 @@ static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, intptr_t pc = (intptr_t)s->code_ptr + 5 + ~rm; intptr_t disp = offset - pc; if (disp == (int32_t)disp) { - tcg_out_opc(s, opc, r, 0, 0); tcg_out8(s, (LOWREGMASK(r) << 3) | 5); tcg_out32(s, disp); return; @@ -548,7 +683,6 @@ static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, use of the MODRM+SIB encoding and is therefore larger than rip-relative addressing. */ if (offset == (int32_t)offset) { - tcg_out_opc(s, opc, r, 0, 0); tcg_out8(s, (LOWREGMASK(r) << 3) | 4); tcg_out8(s, (4 << 3) | 5); tcg_out32(s, offset); @@ -556,10 +690,9 @@ static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, } /* ??? The memory isn't directly addressable. */ - tcg_abort(); + g_assert_not_reached(); } else { /* Absolute address. */ - tcg_out_opc(s, opc, r, 0, 0); tcg_out8(s, (r << 3) | 5); tcg_out32(s, offset); return; @@ -582,7 +715,6 @@ static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, that would be used for %esp is the escape to the two byte form. */ if (index < 0 && LOWREGMASK(rm) != TCG_REG_ESP) { /* Single byte MODRM format. */ - tcg_out_opc(s, opc, r, rm, 0); tcg_out8(s, mod | (LOWREGMASK(r) << 3) | LOWREGMASK(rm)); } else { /* Two byte MODRM+SIB format. */ @@ -596,7 +728,6 @@ static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, tcg_debug_assert(index != TCG_REG_ESP); } - tcg_out_opc(s, opc, r, rm, index); tcg_out8(s, mod | (LOWREGMASK(r) << 3) | 4); tcg_out8(s, (shift << 6) | (LOWREGMASK(index) << 3) | LOWREGMASK(rm)); } @@ -608,6 +739,21 @@ static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, } } +static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm, + int index, int shift, intptr_t offset) +{ + tcg_out_opc(s, opc, r, rm < 0 ? 0 : rm, index < 0 ? 0 : index); + tcg_out_sib_offset(s, r, rm, index, shift, offset); +} + +static void tcg_out_vex_modrm_sib_offset(TCGContext *s, int opc, int r, int v, + int rm, int index, int shift, + intptr_t offset) +{ + tcg_out_vex_opc(s, opc, r, v, rm < 0 ? 0 : rm, index < 0 ? 0 : index); + tcg_out_sib_offset(s, r, rm, index, shift, offset); +} + /* A simplification of the above with no index or shift. */ static inline void tcg_out_modrm_offset(TCGContext *s, int opc, int r, int rm, intptr_t offset) @@ -615,6 +761,30 @@ static inline void tcg_out_modrm_offset(TCGContext *s, int opc, int r, tcg_out_modrm_sib_offset(s, opc, r, rm, -1, 0, offset); } +static inline void tcg_out_vex_modrm_offset(TCGContext *s, int opc, int r, + int v, int rm, intptr_t offset) +{ + tcg_out_vex_modrm_sib_offset(s, opc, r, v, rm, -1, 0, offset); +} + +/* Output an opcode with an expected reference to the constant pool. */ +static inline void tcg_out_modrm_pool(TCGContext *s, int opc, int r) +{ + tcg_out_opc(s, opc, r, 0, 0); + /* Absolute for 32-bit, pc-relative for 64-bit. */ + tcg_out8(s, LOWREGMASK(r) << 3 | 5); + tcg_out32(s, 0); +} + +/* Output an opcode with an expected reference to the constant pool. */ +static inline void tcg_out_vex_modrm_pool(TCGContext *s, int opc, int r) +{ + tcg_out_vex_opc(s, opc, r, 0, 0, 0); + /* Absolute for 32-bit, pc-relative for 64-bit. */ + tcg_out8(s, LOWREGMASK(r) << 3 | 5); + tcg_out32(s, 0); +} + /* Generate dest op= src. Uses the same ARITH_* codes as tgen_arithi. */ static inline void tgen_arithr(TCGContext *s, int subop, int dest, int src) { @@ -625,12 +795,116 @@ static inline void tgen_arithr(TCGContext *s, int subop, int dest, int src) tcg_out_modrm(s, OPC_ARITH_GvEv + (subop << 3) + ext, dest, src); } -static inline void tcg_out_mov(TCGContext *s, TCGType type, - TCGReg ret, TCGReg arg) +static void tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg) { - if (arg != ret) { - int opc = OPC_MOVL_GvEv + (type == TCG_TYPE_I64 ? P_REXW : 0); - tcg_out_modrm(s, opc, ret, arg); + int rexw = 0; + + if (arg == ret) { + return; + } + switch (type) { + case TCG_TYPE_I64: + rexw = P_REXW; + /* fallthru */ + case TCG_TYPE_I32: + if (ret < 16) { + if (arg < 16) { + tcg_out_modrm(s, OPC_MOVL_GvEv + rexw, ret, arg); + } else { + tcg_out_vex_modrm(s, OPC_MOVD_EyVy + rexw, arg, 0, ret); + } + } else { + if (arg < 16) { + tcg_out_vex_modrm(s, OPC_MOVD_VyEy + rexw, ret, 0, arg); + } else { + tcg_out_vex_modrm(s, OPC_MOVQ_VqWq, ret, 0, arg); + } + } + break; + + case TCG_TYPE_V64: + tcg_debug_assert(ret >= 16 && arg >= 16); + tcg_out_vex_modrm(s, OPC_MOVQ_VqWq, ret, 0, arg); + break; + case TCG_TYPE_V128: + tcg_debug_assert(ret >= 16 && arg >= 16); + tcg_out_vex_modrm(s, OPC_MOVDQA_VxWx, ret, 0, arg); + break; + case TCG_TYPE_V256: + tcg_debug_assert(ret >= 16 && arg >= 16); + tcg_out_vex_modrm(s, OPC_MOVDQA_VxWx | P_VEXL, ret, 0, arg); + break; + + default: + g_assert_not_reached(); + } +} + +static void tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece, + TCGReg r, TCGReg a) +{ + if (have_avx2) { + static const int dup_insn[4] = { + OPC_VPBROADCASTB, OPC_VPBROADCASTW, + OPC_VPBROADCASTD, OPC_VPBROADCASTQ, + }; + int vex_l = (type == TCG_TYPE_V256 ? P_VEXL : 0); + tcg_out_vex_modrm(s, dup_insn[vece] + vex_l, r, 0, a); + } else { + switch (vece) { + case MO_8: + /* ??? With zero in a register, use PSHUFB. */ + tcg_out_vex_modrm(s, OPC_PUNPCKLBW, r, 0, a); + a = r; + /* FALLTHRU */ + case MO_16: + tcg_out_vex_modrm(s, OPC_PUNPCKLWD, r, 0, a); + a = r; + /* FALLTHRU */ + case MO_32: + tcg_out_vex_modrm(s, OPC_PSHUFD, r, 0, a); + /* imm8 operand: all output lanes selected from input lane 0. */ + tcg_out8(s, 0); + break; + case MO_64: + tcg_out_vex_modrm(s, OPC_PUNPCKLQDQ, r, 0, a); + break; + default: + g_assert_not_reached(); + } + } +} + +static void tcg_out_dupi_vec(TCGContext *s, TCGType type, + TCGReg ret, tcg_target_long arg) +{ + int vex_l = (type == TCG_TYPE_V256 ? P_VEXL : 0); + + if (arg == 0) { + tcg_out_vex_modrm(s, OPC_PXOR, ret, ret, ret); + return; + } + if (arg == -1) { + tcg_out_vex_modrm(s, OPC_PCMPEQB + vex_l, ret, ret, ret); + return; + } + + if (TCG_TARGET_REG_BITS == 64) { + if (type == TCG_TYPE_V64) { + tcg_out_vex_modrm_pool(s, OPC_MOVQ_VqWq, ret); + } else if (have_avx2) { + tcg_out_vex_modrm_pool(s, OPC_VPBROADCASTQ + vex_l, ret); + } else { + tcg_out_vex_modrm_pool(s, OPC_MOVDDUP, ret); + } + new_pool_label(s, arg, R_386_PC32, s->code_ptr - 4, -4); + } else if (have_avx2) { + tcg_out_vex_modrm_pool(s, OPC_VPBROADCASTD + vex_l, ret); + new_pool_label(s, arg, R_386_32, s->code_ptr - 4, 0); + } else { + tcg_out_vex_modrm_pool(s, OPC_MOVD_VyEy, ret); + new_pool_label(s, arg, R_386_32, s->code_ptr - 4, 0); + tcg_out_dup_vec(s, type, MO_32, ret, ret); } } @@ -639,6 +913,25 @@ static void tcg_out_movi(TCGContext *s, TCGType type, { tcg_target_long diff; + switch (type) { + case TCG_TYPE_I32: +#if TCG_TARGET_REG_BITS == 64 + case TCG_TYPE_I64: +#endif + if (ret < 16) { + break; + } + /* fallthru */ + case TCG_TYPE_V64: + case TCG_TYPE_V128: + case TCG_TYPE_V256: + tcg_debug_assert(ret >= 16); + tcg_out_dupi_vec(s, type, ret, arg); + return; + default: + g_assert_not_reached(); + } + if (arg == 0) { tgen_arithr(s, ARITH_XOR, ret, ret); return; @@ -702,18 +995,74 @@ static inline void tcg_out_pop(TCGContext *s, int reg) tcg_out_opc(s, OPC_POP_r32 + LOWREGMASK(reg), 0, reg, 0); } -static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret, - TCGReg arg1, intptr_t arg2) +static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret, + TCGReg arg1, intptr_t arg2) { - int opc = OPC_MOVL_GvEv + (type == TCG_TYPE_I64 ? P_REXW : 0); - tcg_out_modrm_offset(s, opc, ret, arg1, arg2); + switch (type) { + case TCG_TYPE_I32: + if (ret < 16) { + tcg_out_modrm_offset(s, OPC_MOVL_GvEv, ret, arg1, arg2); + } else { + tcg_out_vex_modrm_offset(s, OPC_MOVD_VyEy, ret, 0, arg1, arg2); + } + break; + case TCG_TYPE_I64: + if (ret < 16) { + tcg_out_modrm_offset(s, OPC_MOVL_GvEv | P_REXW, ret, arg1, arg2); + break; + } + /* FALLTHRU */ + case TCG_TYPE_V64: + tcg_debug_assert(ret >= 16); + tcg_out_vex_modrm_offset(s, OPC_MOVQ_VqWq, ret, 0, arg1, arg2); + break; + case TCG_TYPE_V128: + tcg_debug_assert(ret >= 16); + tcg_out_vex_modrm_offset(s, OPC_MOVDQU_VxWx, ret, 0, arg1, arg2); + break; + case TCG_TYPE_V256: + tcg_debug_assert(ret >= 16); + tcg_out_vex_modrm_offset(s, OPC_MOVDQU_VxWx | P_VEXL, + ret, 0, arg1, arg2); + break; + default: + g_assert_not_reached(); + } } -static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, - TCGReg arg1, intptr_t arg2) +static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, + TCGReg arg1, intptr_t arg2) { - int opc = OPC_MOVL_EvGv + (type == TCG_TYPE_I64 ? P_REXW : 0); - tcg_out_modrm_offset(s, opc, arg, arg1, arg2); + switch (type) { + case TCG_TYPE_I32: + if (arg < 16) { + tcg_out_modrm_offset(s, OPC_MOVL_EvGv, arg, arg1, arg2); + } else { + tcg_out_vex_modrm_offset(s, OPC_MOVD_EyVy, arg, 0, arg1, arg2); + } + break; + case TCG_TYPE_I64: + if (arg < 16) { + tcg_out_modrm_offset(s, OPC_MOVL_EvGv | P_REXW, arg, arg1, arg2); + break; + } + /* FALLTHRU */ + case TCG_TYPE_V64: + tcg_debug_assert(arg >= 16); + tcg_out_vex_modrm_offset(s, OPC_MOVQ_WqVq, arg, 0, arg1, arg2); + break; + case TCG_TYPE_V128: + tcg_debug_assert(arg >= 16); + tcg_out_vex_modrm_offset(s, OPC_MOVDQU_WxVx, arg, 0, arg1, arg2); + break; + case TCG_TYPE_V256: + tcg_debug_assert(arg >= 16); + tcg_out_vex_modrm_offset(s, OPC_MOVDQU_WxVx | P_VEXL, + arg, 0, arg1, arg2); + break; + default: + g_assert_not_reached(); + } } static bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val, @@ -725,6 +1074,8 @@ static bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val, return false; } rexw = P_REXW; + } else if (type != TCG_TYPE_I32) { + return false; } tcg_out_modrm_offset(s, OPC_MOVL_EvIz | rexw, 0, base, ofs); tcg_out32(s, val); @@ -2259,8 +2610,10 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_mov_i32: /* Always emitted via tcg_out_mov. */ case INDEX_op_mov_i64: + case INDEX_op_mov_vec: case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi. */ case INDEX_op_movi_i64: + case INDEX_op_dupi_vec: case INDEX_op_call: /* Always emitted via tcg_out_call. */ default: tcg_abort(); @@ -2269,6 +2622,181 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, #undef OP_32_64 } +static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, + unsigned vecl, unsigned vece, + const TCGArg *args, const int *const_args) +{ + static int const add_insn[4] = { + OPC_PADDB, OPC_PADDW, OPC_PADDD, OPC_PADDQ + }; + static int const sub_insn[4] = { + OPC_PSUBB, OPC_PSUBW, OPC_PSUBD, OPC_PSUBQ + }; + static int const mul_insn[4] = { + OPC_UD2, OPC_PMULLW, OPC_PMULLD, OPC_UD2 + }; + static int const shift_imm_insn[4] = { + OPC_UD2, OPC_PSHIFTW_Ib, OPC_PSHIFTD_Ib, OPC_PSHIFTQ_Ib + }; + static int const cmpeq_insn[4] = { + OPC_PCMPEQB, OPC_PCMPEQW, OPC_PCMPEQD, OPC_PCMPEQQ + }; + static int const cmpgt_insn[4] = { + OPC_PCMPGTB, OPC_PCMPGTW, OPC_PCMPGTD, OPC_PCMPGTQ + }; + static int const punpckl_insn[4] = { + OPC_PUNPCKLBW, OPC_PUNPCKLWD, OPC_PUNPCKLDQ, OPC_PUNPCKLQDQ + }; + static int const punpckh_insn[4] = { + OPC_PUNPCKHBW, OPC_PUNPCKHWD, OPC_PUNPCKHDQ, OPC_PUNPCKHQDQ + }; + static int const packss_insn[4] = { + OPC_PACKSSWB, OPC_PACKSSDW, OPC_UD2, OPC_UD2 + }; + static int const packus_insn[4] = { + OPC_PACKUSWB, OPC_PACKUSDW, OPC_UD2, OPC_UD2 + }; + + TCGType type = vecl + TCG_TYPE_V64; + int insn, sub; + TCGArg a0, a1, a2; + + a0 = args[0]; + a1 = args[1]; + a2 = args[2]; + + switch (opc) { + case INDEX_op_add_vec: + insn = add_insn[vece]; + goto gen_simd; + case INDEX_op_sub_vec: + insn = sub_insn[vece]; + goto gen_simd; + case INDEX_op_mul_vec: + insn = mul_insn[vece]; + goto gen_simd; + case INDEX_op_and_vec: + insn = OPC_PAND; + goto gen_simd; + case INDEX_op_or_vec: + insn = OPC_POR; + goto gen_simd; + case INDEX_op_xor_vec: + insn = OPC_PXOR; + goto gen_simd; + case INDEX_op_x86_punpckl_vec: + insn = punpckl_insn[vece]; + goto gen_simd; + case INDEX_op_x86_punpckh_vec: + insn = punpckh_insn[vece]; + goto gen_simd; + case INDEX_op_x86_packss_vec: + insn = packss_insn[vece]; + goto gen_simd; + case INDEX_op_x86_packus_vec: + insn = packus_insn[vece]; + goto gen_simd; + gen_simd: + tcg_debug_assert(insn != OPC_UD2); + if (type == TCG_TYPE_V256) { + insn |= P_VEXL; + } + tcg_out_vex_modrm(s, insn, a0, a1, a2); + break; + + case INDEX_op_cmp_vec: + sub = args[3]; + if (sub == TCG_COND_EQ) { + insn = cmpeq_insn[vece]; + } else if (sub == TCG_COND_GT) { + insn = cmpgt_insn[vece]; + } else { + g_assert_not_reached(); + } + goto gen_simd; + + case INDEX_op_andc_vec: + insn = OPC_PANDN; + if (type == TCG_TYPE_V256) { + insn |= P_VEXL; + } + tcg_out_vex_modrm(s, insn, a0, a2, a1); + break; + + case INDEX_op_shli_vec: + sub = 6; + goto gen_shift; + case INDEX_op_shri_vec: + sub = 2; + goto gen_shift; + case INDEX_op_sari_vec: + tcg_debug_assert(vece != MO_64); + sub = 4; + gen_shift: + tcg_debug_assert(vece != MO_8); + insn = shift_imm_insn[vece]; + if (type == TCG_TYPE_V256) { + insn |= P_VEXL; + } + tcg_out_vex_modrm(s, insn, sub, a0, a1); + tcg_out8(s, a2); + break; + + case INDEX_op_ld_vec: + tcg_out_ld(s, type, a0, a1, a2); + break; + case INDEX_op_st_vec: + tcg_out_st(s, type, a0, a1, a2); + break; + case INDEX_op_dup_vec: + tcg_out_dup_vec(s, type, vece, a0, a1); + break; + + case INDEX_op_x86_shufps_vec: + insn = OPC_SHUFPS; + sub = args[3]; + goto gen_simd_imm8; + case INDEX_op_x86_blend_vec: + if (vece == MO_16) { + insn = OPC_PBLENDW; + } else if (vece == MO_32) { + insn = (have_avx2 ? OPC_VPBLENDD : OPC_BLENDPS); + } else { + g_assert_not_reached(); + } + sub = args[3]; + goto gen_simd_imm8; + case INDEX_op_x86_vperm2i128_vec: + insn = OPC_VPERM2I128; + sub = args[3]; + goto gen_simd_imm8; + gen_simd_imm8: + if (type == TCG_TYPE_V256) { + insn |= P_VEXL; + } + tcg_out_vex_modrm(s, insn, a0, a1, a2); + tcg_out8(s, sub); + break; + + case INDEX_op_x86_vpblendvb_vec: + insn = OPC_VPBLENDVB; + if (type == TCG_TYPE_V256) { + insn |= P_VEXL; + } + tcg_out_vex_modrm(s, insn, a0, a1, a2); + tcg_out8(s, args[3] << 4); + break; + + case INDEX_op_x86_psrldq_vec: + tcg_out_vex_modrm(s, OPC_GRP14, 3, a0, a1); + tcg_out8(s, a2); + break; + + default: + g_assert_not_reached(); + } +} + static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op) { static const TCGTargetOpDef r = { .args_ct_str = { "r" } }; @@ -2292,6 +2820,11 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op) = { .args_ct_str = { "r", "r", "L", "L" } }; static const TCGTargetOpDef L_L_L_L = { .args_ct_str = { "L", "L", "L", "L" } }; + static const TCGTargetOpDef x_x = { .args_ct_str = { "x", "x" } }; + static const TCGTargetOpDef x_x_x = { .args_ct_str = { "x", "x", "x" } }; + static const TCGTargetOpDef x_x_x_x + = { .args_ct_str = { "x", "x", "x", "x" } }; + static const TCGTargetOpDef x_r = { .args_ct_str = { "x", "r" } }; switch (op) { case INDEX_op_goto_ptr: @@ -2493,12 +3026,342 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op) return &s2; } + case INDEX_op_ld_vec: + case INDEX_op_st_vec: + return &x_r; + + case INDEX_op_add_vec: + case INDEX_op_sub_vec: + case INDEX_op_mul_vec: + case INDEX_op_and_vec: + case INDEX_op_or_vec: + case INDEX_op_xor_vec: + case INDEX_op_andc_vec: + case INDEX_op_cmp_vec: + case INDEX_op_x86_shufps_vec: + case INDEX_op_x86_blend_vec: + case INDEX_op_x86_packss_vec: + case INDEX_op_x86_packus_vec: + case INDEX_op_x86_vperm2i128_vec: + case INDEX_op_x86_punpckl_vec: + case INDEX_op_x86_punpckh_vec: + return &x_x_x; + case INDEX_op_dup_vec: + case INDEX_op_shli_vec: + case INDEX_op_shri_vec: + case INDEX_op_sari_vec: + case INDEX_op_x86_psrldq_vec: + return &x_x; + case INDEX_op_x86_vpblendvb_vec: + return &x_x_x_x; + default: break; } return NULL; } +int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece) +{ + switch (opc) { + case INDEX_op_add_vec: + case INDEX_op_sub_vec: + case INDEX_op_and_vec: + case INDEX_op_or_vec: + case INDEX_op_xor_vec: + case INDEX_op_andc_vec: + return 1; + case INDEX_op_cmp_vec: + return -1; + + case INDEX_op_shli_vec: + case INDEX_op_shri_vec: + /* We must expand the operation for MO_8. */ + return vece == MO_8 ? -1 : 1; + + case INDEX_op_sari_vec: + /* We must expand the operation for MO_8. */ + if (vece == MO_8) { + return -1; + } + /* We can emulate this for MO_64, but it does not pay off + unless we're producing at least 4 values. */ + if (vece == MO_64) { + return type >= TCG_TYPE_V256 ? -1 : 0; + } + return 1; + + case INDEX_op_mul_vec: + if (vece == MO_8) { + /* We can expand the operation for MO_8. */ + return -1; + } + if (vece == MO_64) { + return 0; + } + return 1; + + default: + return 0; + } +} + +void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece, + TCGArg a0, ...) +{ + va_list va; + TCGArg a1, a2; + TCGv_vec v0, t1, t2, t3, t4; + + va_start(va, a0); + v0 = temp_tcgv_vec(arg_temp(a0)); + + switch (opc) { + case INDEX_op_shli_vec: + case INDEX_op_shri_vec: + tcg_debug_assert(vece == MO_8); + a1 = va_arg(va, TCGArg); + a2 = va_arg(va, TCGArg); + /* Unpack to W, shift, and repack. Tricky bits: + (1) Use punpck*bw x,x to produce DDCCBBAA, + i.e. duplicate in other half of the 16-bit lane. + (2) For right-shift, add 8 so that the high half of + the lane becomes zero. For left-shift, we must + shift up and down again. + (3) Step 2 leaves high half zero such that PACKUSWB + (pack with unsigned saturation) does not modify + the quantity. */ + t1 = tcg_temp_new_vec(type); + t2 = tcg_temp_new_vec(type); + vec_gen_3(INDEX_op_x86_punpckl_vec, type, MO_8, + tcgv_vec_arg(t1), a1, a1); + vec_gen_3(INDEX_op_x86_punpckh_vec, type, MO_8, + tcgv_vec_arg(t2), a1, a1); + if (opc == INDEX_op_shri_vec) { + vec_gen_3(INDEX_op_shri_vec, type, MO_16, + tcgv_vec_arg(t1), tcgv_vec_arg(t1), a2 + 8); + vec_gen_3(INDEX_op_shri_vec, type, MO_16, + tcgv_vec_arg(t2), tcgv_vec_arg(t2), a2 + 8); + } else { + vec_gen_3(INDEX_op_shli_vec, type, MO_16, + tcgv_vec_arg(t1), tcgv_vec_arg(t1), a2 + 8); + vec_gen_3(INDEX_op_shli_vec, type, MO_16, + tcgv_vec_arg(t2), tcgv_vec_arg(t2), a2 + 8); + vec_gen_3(INDEX_op_shri_vec, type, MO_16, + tcgv_vec_arg(t1), tcgv_vec_arg(t1), 8); + vec_gen_3(INDEX_op_shri_vec, type, MO_16, + tcgv_vec_arg(t2), tcgv_vec_arg(t2), 8); + } + vec_gen_3(INDEX_op_x86_packus_vec, type, MO_8, + a0, tcgv_vec_arg(t1), tcgv_vec_arg(t2)); + tcg_temp_free_vec(t1); + tcg_temp_free_vec(t2); + break; + + case INDEX_op_sari_vec: + a1 = va_arg(va, TCGArg); + a2 = va_arg(va, TCGArg); + if (vece == MO_8) { + /* Unpack to W, shift, and repack, as above. */ + t1 = tcg_temp_new_vec(type); + t2 = tcg_temp_new_vec(type); + vec_gen_3(INDEX_op_x86_punpckl_vec, type, MO_8, + tcgv_vec_arg(t1), a1, a1); + vec_gen_3(INDEX_op_x86_punpckh_vec, type, MO_8, + tcgv_vec_arg(t2), a1, a1); + vec_gen_3(INDEX_op_sari_vec, type, MO_16, + tcgv_vec_arg(t1), tcgv_vec_arg(t1), a2 + 8); + vec_gen_3(INDEX_op_sari_vec, type, MO_16, + tcgv_vec_arg(t2), tcgv_vec_arg(t2), a2 + 8); + vec_gen_3(INDEX_op_x86_packss_vec, type, MO_8, + a0, tcgv_vec_arg(t1), tcgv_vec_arg(t2)); + tcg_temp_free_vec(t1); + tcg_temp_free_vec(t2); + break; + } + tcg_debug_assert(vece == MO_64); + /* MO_64: If the shift is <= 32, we can emulate the sign extend by + performing an arithmetic 32-bit shift and overwriting the high + half of the result (note that the ISA says shift of 32 is valid). */ + if (a2 <= 32) { + t1 = tcg_temp_new_vec(type); + vec_gen_3(INDEX_op_sari_vec, type, MO_32, tcgv_vec_arg(t1), a1, a2); + vec_gen_3(INDEX_op_shri_vec, type, MO_64, a0, a1, a2); + vec_gen_4(INDEX_op_x86_blend_vec, type, MO_32, + a0, a0, tcgv_vec_arg(t1), 0xaa); + tcg_temp_free_vec(t1); + break; + } + /* Otherwise we will need to use a compare vs 0 to produce the + sign-extend, shift and merge. */ + t1 = tcg_temp_new_vec(type); + t2 = tcg_const_zeros_vec(type); + vec_gen_4(INDEX_op_cmp_vec, type, MO_64, + tcgv_vec_arg(t1), tcgv_vec_arg(t2), a1, TCG_COND_GT); + tcg_temp_free_vec(t2); + vec_gen_3(INDEX_op_shri_vec, type, MO_64, a0, a1, a2); + vec_gen_3(INDEX_op_shli_vec, type, MO_64, + tcgv_vec_arg(t1), tcgv_vec_arg(t1), 64 - a2); + vec_gen_3(INDEX_op_or_vec, type, MO_64, a0, a0, tcgv_vec_arg(t1)); + tcg_temp_free_vec(t1); + break; + + case INDEX_op_mul_vec: + tcg_debug_assert(vece == MO_8); + a1 = va_arg(va, TCGArg); + a2 = va_arg(va, TCGArg); + switch (type) { + case TCG_TYPE_V64: + t1 = tcg_temp_new_vec(TCG_TYPE_V128); + t2 = tcg_temp_new_vec(TCG_TYPE_V128); + tcg_gen_dup16i_vec(t2, 0); + vec_gen_3(INDEX_op_x86_punpckl_vec, TCG_TYPE_V128, MO_8, + tcgv_vec_arg(t1), a1, tcgv_vec_arg(t2)); + vec_gen_3(INDEX_op_x86_punpckl_vec, TCG_TYPE_V128, MO_8, + tcgv_vec_arg(t2), tcgv_vec_arg(t2), a2); + tcg_gen_mul_vec(MO_16, t1, t1, t2); + tcg_gen_shri_vec(MO_16, t1, t1, 8); + vec_gen_3(INDEX_op_x86_packus_vec, TCG_TYPE_V128, MO_8, + a0, tcgv_vec_arg(t1), tcgv_vec_arg(t1)); + tcg_temp_free_vec(t1); + tcg_temp_free_vec(t2); + break; + + case TCG_TYPE_V128: + t1 = tcg_temp_new_vec(TCG_TYPE_V128); + t2 = tcg_temp_new_vec(TCG_TYPE_V128); + t3 = tcg_temp_new_vec(TCG_TYPE_V128); + t4 = tcg_temp_new_vec(TCG_TYPE_V128); + tcg_gen_dup16i_vec(t4, 0); + vec_gen_3(INDEX_op_x86_punpckl_vec, TCG_TYPE_V128, MO_8, + tcgv_vec_arg(t1), a1, tcgv_vec_arg(t4)); + vec_gen_3(INDEX_op_x86_punpckl_vec, TCG_TYPE_V128, MO_8, + tcgv_vec_arg(t2), tcgv_vec_arg(t4), a2); + vec_gen_3(INDEX_op_x86_punpckh_vec, TCG_TYPE_V128, MO_8, + tcgv_vec_arg(t3), a1, tcgv_vec_arg(t4)); + vec_gen_3(INDEX_op_x86_punpckh_vec, TCG_TYPE_V128, MO_8, + tcgv_vec_arg(t4), tcgv_vec_arg(t4), a2); + tcg_gen_mul_vec(MO_16, t1, t1, t2); + tcg_gen_mul_vec(MO_16, t3, t3, t4); + tcg_gen_shri_vec(MO_16, t1, t1, 8); + tcg_gen_shri_vec(MO_16, t3, t3, 8); + vec_gen_3(INDEX_op_x86_packus_vec, TCG_TYPE_V128, MO_8, + a0, tcgv_vec_arg(t1), tcgv_vec_arg(t3)); + tcg_temp_free_vec(t1); + tcg_temp_free_vec(t2); + tcg_temp_free_vec(t3); + tcg_temp_free_vec(t4); + break; + + case TCG_TYPE_V256: + t1 = tcg_temp_new_vec(TCG_TYPE_V256); + t2 = tcg_temp_new_vec(TCG_TYPE_V256); + t3 = tcg_temp_new_vec(TCG_TYPE_V256); + t4 = tcg_temp_new_vec(TCG_TYPE_V256); + tcg_gen_dup16i_vec(t4, 0); + /* a1: A[0-7] ... D[0-7]; a2: W[0-7] ... Z[0-7] + t1: extends of B[0-7], D[0-7] + t2: extends of X[0-7], Z[0-7] + t3: extends of A[0-7], C[0-7] + t4: extends of W[0-7], Y[0-7]. */ + vec_gen_3(INDEX_op_x86_punpckl_vec, TCG_TYPE_V256, MO_8, + tcgv_vec_arg(t1), a1, tcgv_vec_arg(t4)); + vec_gen_3(INDEX_op_x86_punpckl_vec, TCG_TYPE_V256, MO_8, + tcgv_vec_arg(t2), tcgv_vec_arg(t4), a2); + vec_gen_3(INDEX_op_x86_punpckh_vec, TCG_TYPE_V256, MO_8, + tcgv_vec_arg(t3), a1, tcgv_vec_arg(t4)); + vec_gen_3(INDEX_op_x86_punpckh_vec, TCG_TYPE_V256, MO_8, + tcgv_vec_arg(t4), tcgv_vec_arg(t4), a2); + /* t1: BX DZ; t2: AW CY. */ + tcg_gen_mul_vec(MO_16, t1, t1, t2); + tcg_gen_mul_vec(MO_16, t3, t3, t4); + tcg_gen_shri_vec(MO_16, t1, t1, 8); + tcg_gen_shri_vec(MO_16, t3, t3, 8); + /* a0: AW BX CY DZ. */ + vec_gen_3(INDEX_op_x86_packus_vec, TCG_TYPE_V256, MO_8, + a0, tcgv_vec_arg(t1), tcgv_vec_arg(t3)); + tcg_temp_free_vec(t1); + tcg_temp_free_vec(t2); + tcg_temp_free_vec(t3); + tcg_temp_free_vec(t4); + break; + + default: + g_assert_not_reached(); + } + break; + + case INDEX_op_cmp_vec: + { + enum { + NEED_SWAP = 1, + NEED_INV = 2, + NEED_BIAS = 4 + }; + static const uint8_t fixups[16] = { + [0 ... 15] = -1, + [TCG_COND_EQ] = 0, + [TCG_COND_NE] = NEED_INV, + [TCG_COND_GT] = 0, + [TCG_COND_LT] = NEED_SWAP, + [TCG_COND_LE] = NEED_INV, + [TCG_COND_GE] = NEED_SWAP | NEED_INV, + [TCG_COND_GTU] = NEED_BIAS, + [TCG_COND_LTU] = NEED_BIAS | NEED_SWAP, + [TCG_COND_LEU] = NEED_BIAS | NEED_INV, + [TCG_COND_GEU] = NEED_BIAS | NEED_SWAP | NEED_INV, + }; + + TCGCond cond; + uint8_t fixup; + + a1 = va_arg(va, TCGArg); + a2 = va_arg(va, TCGArg); + cond = va_arg(va, TCGArg); + fixup = fixups[cond & 15]; + tcg_debug_assert(fixup != 0xff); + + if (fixup & NEED_INV) { + cond = tcg_invert_cond(cond); + } + if (fixup & NEED_SWAP) { + TCGArg t; + t = a1, a1 = a2, a2 = t; + cond = tcg_swap_cond(cond); + } + + t1 = t2 = NULL; + if (fixup & NEED_BIAS) { + t1 = tcg_temp_new_vec(type); + t2 = tcg_temp_new_vec(type); + tcg_gen_dupi_vec(vece, t2, 1ull << ((8 << vece) - 1)); + tcg_gen_sub_vec(vece, t1, temp_tcgv_vec(arg_temp(a1)), t2); + tcg_gen_sub_vec(vece, t2, temp_tcgv_vec(arg_temp(a2)), t2); + a1 = tcgv_vec_arg(t1); + a2 = tcgv_vec_arg(t2); + cond = tcg_signed_cond(cond); + } + + tcg_debug_assert(cond == TCG_COND_EQ || cond == TCG_COND_GT); + vec_gen_4(INDEX_op_cmp_vec, type, vece, a0, a1, a2, cond); + + if (fixup & NEED_BIAS) { + tcg_temp_free_vec(t1); + tcg_temp_free_vec(t2); + } + if (fixup & NEED_INV) { + tcg_gen_not_vec(vece, v0, v0); + } + } + break; + + default: + break; + } + + va_end(va); +} + static const int tcg_target_callee_save_regs[] = { #if TCG_TARGET_REG_BITS == 64 TCG_REG_RBP, @@ -2577,6 +3440,9 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_addi(s, TCG_REG_CALL_STACK, stack_addend); + if (have_avx2) { + tcg_out_vex_opc(s, OPC_VZEROUPPER, 0, 0, 0, 0); + } for (i = ARRAY_SIZE(tcg_target_callee_save_regs) - 1; i >= 0; i--) { tcg_out_pop(s, tcg_target_callee_save_regs[i]); } @@ -2598,9 +3464,16 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count) static void tcg_target_init(TCGContext *s) { #ifdef CONFIG_CPUID_H - unsigned a, b, c, d; + unsigned a, b, c, d, b7 = 0; int max = __get_cpuid_max(0, 0); + if (max >= 7) { + /* BMI1 is available on AMD Piledriver and Intel Haswell CPUs. */ + __cpuid_count(7, 0, a, b7, c, d); + have_bmi1 = (b7 & bit_BMI) != 0; + have_bmi2 = (b7 & bit_BMI2) != 0; + } + if (max >= 1) { __cpuid(1, a, b, c, d); #ifndef have_cmov @@ -2609,17 +3482,22 @@ static void tcg_target_init(TCGContext *s) available, we'll use a small forward branch. */ have_cmov = (d & bit_CMOV) != 0; #endif + /* MOVBE is only available on Intel Atom and Haswell CPUs, so we need to probe for it. */ have_movbe = (c & bit_MOVBE) != 0; have_popcnt = (c & bit_POPCNT) != 0; - } - if (max >= 7) { - /* BMI1 is available on AMD Piledriver and Intel Haswell CPUs. */ - __cpuid_count(7, 0, a, b, c, d); - have_bmi1 = (b & bit_BMI) != 0; - have_bmi2 = (b & bit_BMI2) != 0; + /* There are a number of things we must check before we can be + sure of not hitting invalid opcode. */ + if (c & bit_OSXSAVE) { + unsigned xcrl, xcrh; + asm ("xgetbv" : "=a" (xcrl), "=d" (xcrh) : "c" (0)); + if ((xcrl & 6) == 6) { + have_avx1 = (c & bit_AVX) != 0; + have_avx2 = (b7 & bit_AVX2) != 0; + } + } } max = __get_cpuid_max(0x8000000, 0); @@ -2630,11 +3508,16 @@ static void tcg_target_init(TCGContext *s) } #endif /* CONFIG_CPUID_H */ + tcg_target_available_regs[TCG_TYPE_I32] = ALL_GENERAL_REGS; if (TCG_TARGET_REG_BITS == 64) { - tcg_target_available_regs[TCG_TYPE_I32] = 0xffff; - tcg_target_available_regs[TCG_TYPE_I64] = 0xffff; - } else { - tcg_target_available_regs[TCG_TYPE_I32] = 0xff; + tcg_target_available_regs[TCG_TYPE_I64] = ALL_GENERAL_REGS; + } + if (have_avx1) { + tcg_target_available_regs[TCG_TYPE_V64] = ALL_VECTOR_REGS; + tcg_target_available_regs[TCG_TYPE_V128] = ALL_VECTOR_REGS; + } + if (have_avx2) { + tcg_target_available_regs[TCG_TYPE_V256] = ALL_VECTOR_REGS; } tcg_target_call_clobber_regs = 0;