From patchwork Thu Jun 18 04:26:11 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 191047 Delivered-To: patch@linaro.org Received: by 2002:a92:cf06:0:0:0:0:0 with SMTP id c6csp1078830ilo; Wed, 17 Jun 2020 22:05:23 -0700 (PDT) X-Google-Smtp-Source: ABdhPJxsnJ3BwhB0E2vM9kxqlSxLADh85qrRk3IjJNdSeJkX2gHWw1Tv4sIV1RgjGyRm+XJY5XUW X-Received: by 2002:a25:a0c7:: with SMTP id i7mr3869803ybm.420.1592456723513; Wed, 17 Jun 2020 22:05:23 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1592456723; cv=none; d=google.com; s=arc-20160816; b=JPwsC6kpXw81pQRgRtp09lKiqBuNJENzcQdr71aJdNE5anJUeA3r7WddfEN0iBq6+x kbgPK7ocGVqRCLqgmgIwUgyJ1hwQsrCK7lnHlDNuw1ah3RJiBbVpLS7jPyx7CHz3AvhH +adohxXr4wHSSETICBW2/nxDjJgheAquQMyIoNRyFytqUCY+l/FAqKijG0j+Pgo/8LlF FMVzRqg5a+muFhbEDSDTfBSTiQ/Q13FtIZ/DfJrPzpkR9TXSZKORW4nxMD/A1Zig0LYd bSXl13W2X5rMWoOnjoHad05q8CveCrFpW4O8zy1DKqaA4aS9JB1eT/7fr5SAhq1y9Rfg VJ5Q== 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:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=qM6gI0HRCGxnV0woPUZVfv/KowA3Ydeyk+kfoCgD6zU=; b=r/ujuyeFjDPabFLnYaiIPHlIaXvLutVkdn3sLoxo08olFL9HIg3HcwqdvVF9hZsyuB 8mSZrwhE+tVeppnoxHdxq/hWstIBT8y11zUyFvdgGKb89tcu7LUSGMJTgvwzvOHFEmKh lPlsK6/V8gSLpgAiByZGfMcpJ56ADDVQmHFbrknaGgH/K3dmfFFfGgyf+gU5hE+CyGDf gA8ivP290on/j4dREUl8N2kPeaSCUszb9syerAFMxx73VsJwm1LI2eYgmMxCq0twnm8t Wzm8v2WVvhKHUH9kUOVi3LUjcGp56ea6tQ7raq1xsDh1f4Lf5Bqfftxej1YghoW5GJHn X9Nw== ARC-Authentication-Results: i=1; mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=MvZWALc+; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 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. [209.51.188.17]) by mx.google.com with ESMTPS id m188si1394655ybf.99.2020.06.17.22.05.23 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Wed, 17 Jun 2020 22:05:23 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=MvZWALc+; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 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]:35392 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jlmjq-0006cV-VN for patch@linaro.org; Thu, 18 Jun 2020 01:05:23 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:33406) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jlmCz-0003dN-DV for qemu-devel@nongnu.org; Thu, 18 Jun 2020 00:31:25 -0400 Received: from mail-pf1-x441.google.com ([2607:f8b0:4864:20::441]:43749) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1jlmCx-0003Le-3t for qemu-devel@nongnu.org; Thu, 18 Jun 2020 00:31:25 -0400 Received: by mail-pf1-x441.google.com with SMTP id 23so2178972pfw.10 for ; Wed, 17 Jun 2020 21:31:22 -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 :mime-version:content-transfer-encoding; bh=qM6gI0HRCGxnV0woPUZVfv/KowA3Ydeyk+kfoCgD6zU=; b=MvZWALc+Baj6XlHS/qEy48NUj4l/blwIRPU2WlulYtWbGDf2gvEOOCTiaSMl4jFrBn BqlCL6tBf76HOZgdbpq+QRsJ1wG4AkqSx5li8jUYaIicldvLMiq1neFATI8I5mHV/kOe DNCJD1KKPhorcE9VP/GyZ1UqGxMJce0b2H7vTHqPULwXhnutClthKfZ0jCX9Nd6sbyI+ uMIs91LRU6KZ6H48CYbU+jHSjWvGk2PUWN0DIV5PsvA+rEImhw/crZdPOnXrlS4TfgcK nrj6ownHw38A7UfhLGzH7sUBKIhREkJ+WnwpdPBS+XMZJ/wqIyvA6ouJVVhylFBz3kNN 5AWA== 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:mime-version:content-transfer-encoding; bh=qM6gI0HRCGxnV0woPUZVfv/KowA3Ydeyk+kfoCgD6zU=; b=DozghirmMI/qo20/MdD9vt2U7REQxgJ/njvRTPRVrhlvsOECwYeMWcrYEbNvozJTB5 PnX51uUzOrDz3JQ/XL9xyzcU2HrAGuXLv5VgX0u0txFCUsK4jz/lAtfT2gt0p3XU+TMJ hseRGtVwq1/aSUtqWlYRut9FLFrOg+pPmGsITO0c2L4OwbhAYMGjuzJA+TnRsqZp/vON iozAYr4b/xDIHpwqcbkN9erFXrkzwe+rhtKjdeVMgzKFpkRSBVMePs79fQy3PRCun4fH vc4a5qti0RMkIrKooOz7deHRbmUe+M6BY1N2CeIxjkw0MuqquTDnIaZo6Xs9L1prHLJJ Hf5w== X-Gm-Message-State: AOAM530waHf5fRDGgJc2FeV9U4/vQkGUrF7l5BcbYp2rkBIVfIxrlswT HKCu25pjCESmmdsnbDzvjqgFatSX+/w= X-Received: by 2002:a63:1b20:: with SMTP id b32mr1818752pgb.39.1592454680982; Wed, 17 Jun 2020 21:31:20 -0700 (PDT) Received: from localhost.localdomain (174-21-143-238.tukw.qwest.net. [174.21.143.238]) by smtp.gmail.com with ESMTPSA id o1sm974337pjf.17.2020.06.17.21.31.19 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 17 Jun 2020 21:31:20 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PATCH v2 067/100] target/arm: Pass separate addend to {U, S}DOT helpers Date: Wed, 17 Jun 2020 21:26:11 -0700 Message-Id: <20200618042644.1685561-68-richard.henderson@linaro.org> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20200618042644.1685561-1-richard.henderson@linaro.org> References: <20200618042644.1685561-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::441; envelope-from=richard.henderson@linaro.org; helo=mail-pf1-x441.google.com X-detected-operating-system: by eggs.gnu.org: No matching host in p0f cache. That's all we know. X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=_AUTOLEARN X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: qemu-arm@nongnu.org, steplong@quicinc.com Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" For SVE, we potentially have a 4th argument coming from the movprfx instruction. Currently we do not optimize movprfx, so the problem is not visible. Signed-off-by: Richard Henderson --- target/arm/helper.h | 20 +++--- target/arm/sve.decode | 7 +- target/arm/translate-a64.c | 15 ++++- target/arm/translate-neon.inc.c | 10 +-- target/arm/translate-sve.c | 13 ++-- target/arm/vec_helper.c | 112 ++++++++++++++++++-------------- 6 files changed, 105 insertions(+), 72 deletions(-) -- 2.25.1 diff --git a/target/arm/helper.h b/target/arm/helper.h index 7a29194052..dd32a11b9d 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -574,15 +574,19 @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 0688dae450..5815ba9b1c 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -756,12 +756,13 @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s # SVE integer dot product (unpredicated) -DOT_zzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 ra=%reg_movprfx +DOT_zzzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \ + ra=%reg_movprfx # SVE integer dot product (indexed) -DOT_zzx 01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \ +DOT_zzxw 01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \ sz=0 ra=%reg_movprfx -DOT_zzx 01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \ +DOT_zzxw 01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \ sz=1 ra=%reg_movprfx # SVE floating-point complex add (predicated) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 4f5c433b47..7366553f8d 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -605,6 +605,17 @@ static void gen_gvec_op3_fpst(DisasContext *s, bool is_q, int rd, int rn, tcg_temp_free_ptr(fpst); } +/* Expand a 4-operand operation using an out-of-line helper. */ +static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn, + int rm, int ra, int data, gen_helper_gvec_4 *fn) +{ + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + is_q ? 16 : 8, vec_full_reg_size(s), data, fn); +} + /* Set ZF and NF based on a 64 bit result. This is alas fiddlier * than the 32 bit equivalent. */ @@ -11710,7 +11721,7 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) return; case 0x2: /* SDOT / UDOT */ - gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b); return; @@ -12972,7 +12983,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) switch (16 * u + opcode) { case 0x0e: /* SDOT */ case 0x1e: /* UDOT */ - gen_gvec_op3_ool(s, is_q, rd, rn, rm, index, + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b); return; diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index a5aa56bbde..d4556dfb4e 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -131,7 +131,7 @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) static bool trans_VDOT(DisasContext *s, arg_VDOT *a) { int opr_sz; - gen_helper_gvec_3 *fn_gvec; + gen_helper_gvec_4 *fn_gvec; if (!dc_isar_feature(aa32_dp, s)) { return false; @@ -153,9 +153,10 @@ static bool trans_VDOT(DisasContext *s, arg_VDOT *a) opr_sz = (1 + a->q) * 8; fn_gvec = a->u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; - tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), + tcg_gen_gvec_4_ool(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), + vfp_reg_offset(1, a->vd), opr_sz, opr_sz, 0, fn_gvec); return true; } @@ -233,7 +234,7 @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) { - gen_helper_gvec_3 *fn_gvec; + gen_helper_gvec_4 *fn_gvec; int opr_sz; TCGv_ptr fpst; @@ -258,9 +259,10 @@ static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) fn_gvec = a->u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; opr_sz = (1 + a->q) * 8; fpst = get_fpstatus_ptr(1); - tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), + tcg_gen_gvec_4_ool(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->rm), + vfp_reg_offset(1, a->vd), opr_sz, opr_sz, a->index, fn_gvec); tcg_temp_free_ptr(fpst); return true; diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 45ee91d3fe..835ccc0cee 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -3804,28 +3804,29 @@ DO_ZZI(UMIN, umin) #undef DO_ZZI -static bool trans_DOT_zzz(DisasContext *s, arg_DOT_zzz *a) +static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a) { - static gen_helper_gvec_3 * const fns[2][2] = { + static gen_helper_gvec_4 * const fns[2][2] = { { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } }; if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, 0); + gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0); } return true; } -static bool trans_DOT_zzx(DisasContext *s, arg_DOT_zzx *a) +static bool trans_DOT_zzxw(DisasContext *s, arg_DOT_zzxw *a) { - static gen_helper_gvec_3 * const fns[2][2] = { + static gen_helper_gvec_4 * const fns[2][2] = { { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h }, { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h } }; if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->index); + gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, + a->ra, a->index); } return true; } diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index 3b38cdafb0..5a8de167f3 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -327,71 +327,76 @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm, * All elements are treated equally, no matter where they are. */ -void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint32_t *d = vd; + int32_t *d = vd, *a = va; int8_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 4; ++i) { - d[i] += n[i * 4 + 0] * m[i * 4 + 0] - + n[i * 4 + 1] * m[i * 4 + 1] - + n[i * 4 + 2] * m[i * 4 + 2] - + n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = (a[i] + + n[i * 4 + 0] * m[i * 4 + 0] + + n[i * 4 + 1] * m[i * 4 + 1] + + n[i * 4 + 2] * m[i * 4 + 2] + + n[i * 4 + 3] * m[i * 4 + 3]); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint32_t *d = vd; + uint32_t *d = vd, *a = va; uint8_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 4; ++i) { - d[i] += n[i * 4 + 0] * m[i * 4 + 0] - + n[i * 4 + 1] * m[i * 4 + 1] - + n[i * 4 + 2] * m[i * 4 + 2] - + n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = (a[i] + + n[i * 4 + 0] * m[i * 4 + 0] + + n[i * 4 + 1] * m[i * 4 + 1] + + n[i * 4 + 2] * m[i * 4 + 2] + + n[i * 4 + 3] * m[i * 4 + 3]); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint64_t *d = vd; + int64_t *d = vd, *a = va; int16_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 8; ++i) { - d[i] += (int64_t)n[i * 4 + 0] * m[i * 4 + 0] - + (int64_t)n[i * 4 + 1] * m[i * 4 + 1] - + (int64_t)n[i * 4 + 2] * m[i * 4 + 2] - + (int64_t)n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = (a[i] + + (int64_t)n[i * 4 + 0] * m[i * 4 + 0] + + (int64_t)n[i * 4 + 1] * m[i * 4 + 1] + + (int64_t)n[i * 4 + 2] * m[i * 4 + 2] + + (int64_t)n[i * 4 + 3] * m[i * 4 + 3]); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint64_t *d = vd; + uint64_t *d = vd, *a = va; uint16_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 8; ++i) { - d[i] += (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] - + (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] - + (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] - + (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = (a[i] + + (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] + + (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] + + (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] + + (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; intptr_t index = simd_data(desc); - uint32_t *d = vd; + int32_t *d = vd, *a = va; int8_t *n = vn; int8_t *m_indexed = (int8_t *)vm + index * 4; @@ -407,10 +412,11 @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) int8_t m3 = m_indexed[i * 4 + 3]; do { - d[i] += n[i * 4 + 0] * m0 - + n[i * 4 + 1] * m1 - + n[i * 4 + 2] * m2 - + n[i * 4 + 3] * m3; + d[i] = (a[i] + + n[i * 4 + 0] * m0 + + n[i * 4 + 1] * m1 + + n[i * 4 + 2] * m2 + + n[i * 4 + 3] * m3); } while (++i < segend); segend = i + 4; } while (i < opr_sz_4); @@ -418,11 +424,12 @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; intptr_t index = simd_data(desc); - uint32_t *d = vd; + uint32_t *d = vd, *a = va; uint8_t *n = vn; uint8_t *m_indexed = (uint8_t *)vm + index * 4; @@ -438,10 +445,11 @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) uint8_t m3 = m_indexed[i * 4 + 3]; do { - d[i] += n[i * 4 + 0] * m0 - + n[i * 4 + 1] * m1 - + n[i * 4 + 2] * m2 - + n[i * 4 + 3] * m3; + d[i] = (a[i] + + n[i * 4 + 0] * m0 + + n[i * 4 + 1] * m1 + + n[i * 4 + 2] * m2 + + n[i * 4 + 3] * m3); } while (++i < segend); segend = i + 4; } while (i < opr_sz_4); @@ -449,11 +457,12 @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; intptr_t index = simd_data(desc); - uint64_t *d = vd; + int64_t *d = vd, *a = va; int16_t *n = vn; int16_t *m_indexed = (int16_t *)vm + index * 4; @@ -461,14 +470,17 @@ void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) * Process the entire segment all at once, writing back the results * only after we've consumed all of the inputs. */ - for (i = 0; i < opr_sz_8 ; i += 2) { - uint64_t d0, d1; + for (i = 0; i < opr_sz_8; i += 2) { + int64_t d0, d1; - d0 = n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0]; + d0 = a[i + 0]; + d0 += n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0]; d0 += n[i * 4 + 1] * (int64_t)m_indexed[i * 4 + 1]; d0 += n[i * 4 + 2] * (int64_t)m_indexed[i * 4 + 2]; d0 += n[i * 4 + 3] * (int64_t)m_indexed[i * 4 + 3]; - d1 = n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0]; + + d1 = a[i + 1]; + d1 += n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0]; d1 += n[i * 4 + 5] * (int64_t)m_indexed[i * 4 + 1]; d1 += n[i * 4 + 6] * (int64_t)m_indexed[i * 4 + 2]; d1 += n[i * 4 + 7] * (int64_t)m_indexed[i * 4 + 3]; @@ -476,15 +488,15 @@ void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) d[i + 0] += d0; d[i + 1] += d1; } - clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; intptr_t index = simd_data(desc); - uint64_t *d = vd; + uint64_t *d = vd, *a = va; uint16_t *n = vn; uint16_t *m_indexed = (uint16_t *)vm + index * 4; @@ -492,14 +504,17 @@ void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) * Process the entire segment all at once, writing back the results * only after we've consumed all of the inputs. */ - for (i = 0; i < opr_sz_8 ; i += 2) { + for (i = 0; i < opr_sz_8; i += 2) { uint64_t d0, d1; - d0 = n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0]; + d0 = a[i + 0]; + d0 += n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0]; d0 += n[i * 4 + 1] * (uint64_t)m_indexed[i * 4 + 1]; d0 += n[i * 4 + 2] * (uint64_t)m_indexed[i * 4 + 2]; d0 += n[i * 4 + 3] * (uint64_t)m_indexed[i * 4 + 3]; - d1 = n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0]; + + d1 = a[i + 1]; + d1 += n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0]; d1 += n[i * 4 + 5] * (uint64_t)m_indexed[i * 4 + 1]; d1 += n[i * 4 + 6] * (uint64_t)m_indexed[i * 4 + 2]; d1 += n[i * 4 + 7] * (uint64_t)m_indexed[i * 4 + 3]; @@ -507,7 +522,6 @@ void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) d[i + 0] += d0; d[i + 1] += d1; } - clear_tail(d, opr_sz, simd_maxsz(desc)); }