From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([209.51.188.92]:40218) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1hHkWj-00005s-39 for qemu-devel@nongnu.org; Sat, 20 Apr 2019 03:35:10 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hHkWi-00084i-1l for qemu-devel@nongnu.org; Sat, 20 Apr 2019 03:35:09 -0400 Received: from mail-pf1-x444.google.com ([2607:f8b0:4864:20::444]:34091) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1hHkWh-00083F-Rt for qemu-devel@nongnu.org; Sat, 20 Apr 2019 03:35:07 -0400 Received: by mail-pf1-x444.google.com with SMTP id b3so3480564pfd.1 for ; Sat, 20 Apr 2019 00:35:07 -0700 (PDT) From: Richard Henderson Date: Fri, 19 Apr 2019 21:34:17 -1000 Message-Id: <20190420073442.7488-14-richard.henderson@linaro.org> In-Reply-To: <20190420073442.7488-1-richard.henderson@linaro.org> References: <20190420073442.7488-1-richard.henderson@linaro.org> Subject: [Qemu-devel] [PATCH 13/38] tcg/i386: Support vector variable shift opcodes List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: david@redhat.com Signed-off-by: Richard Henderson --- tcg/i386/tcg-target.h | 2 +- tcg/i386/tcg-target.inc.c | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 1 deletion(-) diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index 241bf19413..b240633455 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -184,7 +184,7 @@ extern bool have_avx2; #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_shv_vec have_avx2 #define TCG_TARGET_HAS_cmp_vec 1 #define TCG_TARGET_HAS_mul_vec 1 #define TCG_TARGET_HAS_sat_vec 1 diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c index 4c42a2430d..04e609c7b2 100644 --- a/tcg/i386/tcg-target.inc.c +++ b/tcg/i386/tcg-target.inc.c @@ -467,6 +467,11 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type, #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_VPSLLVD (0x47 | P_EXT38 | P_DATA16) +#define OPC_VPSLLVQ (0x47 | P_EXT38 | P_DATA16 | P_REXW) +#define OPC_VPSRAVD (0x46 | P_EXT38 | P_DATA16) +#define OPC_VPSRLVD (0x45 | P_EXT38 | P_DATA16) +#define OPC_VPSRLVQ (0x45 | P_EXT38 | P_DATA16 | P_REXW) #define OPC_VZEROUPPER (0x77 | P_EXT) #define OPC_XCHG_ax_r32 (0x90) @@ -2705,6 +2710,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, static int const umax_insn[4] = { OPC_PMAXUB, OPC_PMAXUW, OPC_PMAXUD, OPC_UD2 }; + static int const shlv_insn[4] = { + /* TODO: AVX512 adds support for MO_16. */ + OPC_UD2, OPC_UD2, OPC_VPSLLVD, OPC_VPSLLVQ + }; + static int const shrv_insn[4] = { + /* TODO: AVX512 adds support for MO_16. */ + OPC_UD2, OPC_UD2, OPC_VPSRLVD, OPC_VPSRLVQ + }; + static int const sarv_insn[4] = { + /* TODO: AVX512 adds support for MO_16, MO_64. */ + OPC_UD2, OPC_UD2, OPC_VPSRAVD, OPC_UD2 + }; TCGType type = vecl + TCG_TYPE_V64; int insn, sub; @@ -2757,6 +2774,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, case INDEX_op_umax_vec: insn = umax_insn[vece]; goto gen_simd; + case INDEX_op_shlv_vec: + insn = shlv_insn[vece]; + goto gen_simd; + case INDEX_op_shrv_vec: + insn = shrv_insn[vece]; + goto gen_simd; + case INDEX_op_sarv_vec: + insn = sarv_insn[vece]; + goto gen_simd; case INDEX_op_x86_punpckl_vec: insn = punpckl_insn[vece]; goto gen_simd; @@ -3134,6 +3160,9 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op) case INDEX_op_umin_vec: case INDEX_op_smax_vec: case INDEX_op_umax_vec: + case INDEX_op_shlv_vec: + case INDEX_op_shrv_vec: + case INDEX_op_sarv_vec: case INDEX_op_cmp_vec: case INDEX_op_x86_shufps_vec: case INDEX_op_x86_blend_vec: @@ -3191,6 +3220,12 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece) } return 1; + case INDEX_op_shlv_vec: + case INDEX_op_shrv_vec: + return have_avx2 && vece >= MO_32; + case INDEX_op_sarv_vec: + return have_avx2 && vece == MO_32; + case INDEX_op_mul_vec: if (vece == MO_8) { /* We can expand the operation for MO_8. */ -- 2.17.1 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-8.7 required=3.0 tests=DKIM_INVALID,DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id C4EC6C282DD for ; Sat, 20 Apr 2019 07:50:58 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 4554721479 for ; Sat, 20 Apr 2019 07:50:58 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=linaro.org header.i=@linaro.org header.b="ASW0F1Fb" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 4554721479 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=linaro.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([127.0.0.1]:38295 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1hHkm1-00058w-Bi for qemu-devel@archiver.kernel.org; Sat, 20 Apr 2019 03:50:57 -0400 Received: from eggs.gnu.org ([209.51.188.92]:40218) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1hHkWj-00005s-39 for qemu-devel@nongnu.org; Sat, 20 Apr 2019 03:35:10 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hHkWi-00084i-1l for qemu-devel@nongnu.org; Sat, 20 Apr 2019 03:35:09 -0400 Received: from mail-pf1-x444.google.com ([2607:f8b0:4864:20::444]:34091) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1hHkWh-00083F-Rt for qemu-devel@nongnu.org; Sat, 20 Apr 2019 03:35:07 -0400 Received: by mail-pf1-x444.google.com with SMTP id b3so3480564pfd.1 for ; Sat, 20 Apr 2019 00:35:07 -0700 (PDT) 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=F1de5So3vFDWwHAWVYAQ29uD+09yUtcwgv6kBjYxLtM=; b=ASW0F1FbKt3Bq1COddmbp3oVZcJN2FNaQNqVewjp9+KYNX4Vg4voLCqr1DJG8H2qzK rn//YW51aZyO6RUEzkgWx6p+I65oUrOIZIyaBtvztJV8Id3JzZdM6+S3SIOh1pIJtVai taXs6nS8RZ5JZRO/JRSPVbT97Lgc/yD9LGPWMHuUbblNXR8QrGDvU0KaOvWJZzbVcW5T yvUAgCcboGKxg2Khqh5Wz0GX1Pw353l1046eidxslnpyopaOiAqPCJdv3IjMzt3tS6Y2 OfGbDgUhDg/p0w2dGtfYKj8EZgXOC3xgrL/4fqerdmvQel9PIR+n5LTJx5kjeo4hz35h nQSQ== 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=F1de5So3vFDWwHAWVYAQ29uD+09yUtcwgv6kBjYxLtM=; b=c/cVH3JP+jCRAEhmK13E4G0uGcudZCFO3YA7jiKsXaHpHEybvcgp4HyLMFSFAo+Ubk 1XXLPivEeqwiKCTqupnaHLuOnJ0FxudCQd12fsyJsSrA0XZQEBDsV7LHCG9FlnIhYBoP bXLTFvcqdVOVWRn3wuRaoZZLlUY1/5nKMt7c5D7I4qsKGZyp9HzDShZhuSMD3KhtaINJ G9Cg1ONKxKoxZJecePDnNvbV9EcYtv127G1ehvosXaQ2aZs4a/mb+eSI83P/aTpGcIn2 C5TbnCaTN37O4a8XB/02tjla6lwkDERTKio+iXhPMIrXl4vCEJlGc2K6f61xAt8Npu2w xiPA== X-Gm-Message-State: APjAAAWcXUpVIpxfGdSyVIk/db/TdlN6Dgwj77cIheXDw5yAml2FqHtZ UAYmlCMMzoa2dRcziIdC0GicnSqSoqs= X-Google-Smtp-Source: APXvYqxEraO7aRcg5SPlK1jetffmZ2O0DPFwZiu9+M1EhDnWgvQnnaJ3e1VM0KBW9AwNHZCrHFbODg== X-Received: by 2002:a05:6a00:dc:: with SMTP id e28mr8433637pfj.186.1555745706468; Sat, 20 Apr 2019 00:35:06 -0700 (PDT) Received: from localhost.localdomain (rrcs-66-91-136-155.west.biz.rr.com. [66.91.136.155]) by smtp.gmail.com with ESMTPSA id z22sm7025492pgv.23.2019.04.20.00.35.05 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Sat, 20 Apr 2019 00:35:05 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Date: Fri, 19 Apr 2019 21:34:17 -1000 Message-Id: <20190420073442.7488-14-richard.henderson@linaro.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190420073442.7488-1-richard.henderson@linaro.org> References: <20190420073442.7488-1-richard.henderson@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:4864:20::444 Subject: [Qemu-devel] [PATCH 13/38] tcg/i386: Support vector variable shift opcodes 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: david@redhat.com Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" Content-Type: text/plain; charset="UTF-8" Message-ID: <20190420073417.CJblDRDiDDtDY0_qJccVN5DMgQYvTs0iQtS-obLzc-w@z> Signed-off-by: Richard Henderson --- tcg/i386/tcg-target.h | 2 +- tcg/i386/tcg-target.inc.c | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 1 deletion(-) diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index 241bf19413..b240633455 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -184,7 +184,7 @@ extern bool have_avx2; #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_shv_vec have_avx2 #define TCG_TARGET_HAS_cmp_vec 1 #define TCG_TARGET_HAS_mul_vec 1 #define TCG_TARGET_HAS_sat_vec 1 diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c index 4c42a2430d..04e609c7b2 100644 --- a/tcg/i386/tcg-target.inc.c +++ b/tcg/i386/tcg-target.inc.c @@ -467,6 +467,11 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type, #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_VPSLLVD (0x47 | P_EXT38 | P_DATA16) +#define OPC_VPSLLVQ (0x47 | P_EXT38 | P_DATA16 | P_REXW) +#define OPC_VPSRAVD (0x46 | P_EXT38 | P_DATA16) +#define OPC_VPSRLVD (0x45 | P_EXT38 | P_DATA16) +#define OPC_VPSRLVQ (0x45 | P_EXT38 | P_DATA16 | P_REXW) #define OPC_VZEROUPPER (0x77 | P_EXT) #define OPC_XCHG_ax_r32 (0x90) @@ -2705,6 +2710,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, static int const umax_insn[4] = { OPC_PMAXUB, OPC_PMAXUW, OPC_PMAXUD, OPC_UD2 }; + static int const shlv_insn[4] = { + /* TODO: AVX512 adds support for MO_16. */ + OPC_UD2, OPC_UD2, OPC_VPSLLVD, OPC_VPSLLVQ + }; + static int const shrv_insn[4] = { + /* TODO: AVX512 adds support for MO_16. */ + OPC_UD2, OPC_UD2, OPC_VPSRLVD, OPC_VPSRLVQ + }; + static int const sarv_insn[4] = { + /* TODO: AVX512 adds support for MO_16, MO_64. */ + OPC_UD2, OPC_UD2, OPC_VPSRAVD, OPC_UD2 + }; TCGType type = vecl + TCG_TYPE_V64; int insn, sub; @@ -2757,6 +2774,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, case INDEX_op_umax_vec: insn = umax_insn[vece]; goto gen_simd; + case INDEX_op_shlv_vec: + insn = shlv_insn[vece]; + goto gen_simd; + case INDEX_op_shrv_vec: + insn = shrv_insn[vece]; + goto gen_simd; + case INDEX_op_sarv_vec: + insn = sarv_insn[vece]; + goto gen_simd; case INDEX_op_x86_punpckl_vec: insn = punpckl_insn[vece]; goto gen_simd; @@ -3134,6 +3160,9 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op) case INDEX_op_umin_vec: case INDEX_op_smax_vec: case INDEX_op_umax_vec: + case INDEX_op_shlv_vec: + case INDEX_op_shrv_vec: + case INDEX_op_sarv_vec: case INDEX_op_cmp_vec: case INDEX_op_x86_shufps_vec: case INDEX_op_x86_blend_vec: @@ -3191,6 +3220,12 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece) } return 1; + case INDEX_op_shlv_vec: + case INDEX_op_shrv_vec: + return have_avx2 && vece >= MO_32; + case INDEX_op_sarv_vec: + return have_avx2 && vece == MO_32; + case INDEX_op_mul_vec: if (vece == MO_8) { /* We can expand the operation for MO_8. */ -- 2.17.1