From patchwork Fri Jun 29 14:53:07 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 936977 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=nongnu.org (client-ip=2001:4830:134:3::11; helo=lists.gnu.org; envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=linaro.org Received: from lists.gnu.org (lists.gnu.org [IPv6:2001:4830:134:3::11]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 41HKxT2FxQz9ryk for ; Sat, 30 Jun 2018 01:16:45 +1000 (AEST) Received: from localhost ([::1]:42891 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fYv8c-0001Xh-R1 for incoming@patchwork.ozlabs.org; Fri, 29 Jun 2018 11:16:42 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:33801) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fYumk-0007Qe-NU for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:10 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fYumh-0006RI-EF for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:06 -0400 Received: from orth.archaic.org.uk ([2001:8b0:1d0::2]:43094) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fYumg-0006MP-Nx for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:03 -0400 Received: from pm215 by orth.archaic.org.uk with local (Exim 4.89) (envelope-from ) id 1fYumf-0004aE-IX for qemu-devel@nongnu.org; Fri, 29 Jun 2018 15:54:01 +0100 From: Peter Maydell To: qemu-devel@nongnu.org Date: Fri, 29 Jun 2018 15:53:07 +0100 Message-Id: <20180629145347.652-16-peter.maydell@linaro.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20180629145347.652-1-peter.maydell@linaro.org> References: <20180629145347.652-1-peter.maydell@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2001:8b0:1d0::2 Subject: [Qemu-devel] [PULL 15/55] target/arm: Implement SVE load and broadcast element 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: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20180627043328.11531-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper-sve.h | 5 +++ target/arm/sve_helper.c | 41 +++++++++++++++++++++++++ target/arm/translate-sve.c | 62 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 5 +++ 4 files changed, 113 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 68e55a8d031..a5d3bb121c7 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -274,6 +274,11 @@ DEF_HELPER_FLAGS_3(sve_clr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_clr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_clr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_movz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_movz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_movz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_movz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_asr_zpzi_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_asr_zpzi_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_asr_zpzi_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index 2d08b7dcd3d..93f29425907 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -995,6 +995,47 @@ void HELPER(sve_clr_d)(void *vd, void *vg, uint32_t desc) } } +/* Copy Zn into Zd, and store zero into inactive elements. */ +void HELPER(sve_movz_b)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + for (i = 0; i < opr_sz; i += 1) { + d[i] = n[i] & expand_pred_b(pg[H1(i)]); + } +} + +void HELPER(sve_movz_h)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + for (i = 0; i < opr_sz; i += 1) { + d[i] = n[i] & expand_pred_h(pg[H1(i)]); + } +} + +void HELPER(sve_movz_s)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + for (i = 0; i < opr_sz; i += 1) { + d[i] = n[i] & expand_pred_s(pg[H1(i)]); + } +} + +void HELPER(sve_movz_d)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + for (i = 0; i < opr_sz; i += 1) { + d[i] = n[1] & -(uint64_t)(pg[H1(i)] & 1); + } +} + /* Three-operand expander, immediate operand, controlled by a predicate. */ #define DO_ZPZI(NAME, TYPE, H, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index ceb46895e0d..a0d5b0fd586 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -606,6 +606,20 @@ static bool do_clr_zp(DisasContext *s, int rd, int pg, int esz) return true; } +/* Copy Zn into Zd, storing zeros into inactive elements. */ +static void do_movz_zpz(DisasContext *s, int rd, int rn, int pg, int esz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve_movz_b, gen_helper_sve_movz_h, + gen_helper_sve_movz_s, gen_helper_sve_movz_d, + }; + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + pred_full_reg_offset(s, pg), + vsz, vsz, 0, fns[esz]); +} + static bool do_zpzi_ool(DisasContext *s, arg_rpri_esz *a, gen_helper_gvec_3 *fn) { @@ -3999,6 +4013,54 @@ static bool trans_LD1RQ_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) return true; } +/* Load and broadcast element. */ +static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) +{ + if (!sve_access_check(s)) { + return true; + } + + unsigned vsz = vec_full_reg_size(s); + unsigned psz = pred_full_reg_size(s); + unsigned esz = dtype_esz[a->dtype]; + TCGLabel *over = gen_new_label(); + TCGv_i64 temp; + + /* If the guarding predicate has no bits set, no load occurs. */ + if (psz <= 8) { + /* Reduce the pred_esz_masks value simply to reduce the + * size of the code generated here. + */ + uint64_t psz_mask = MAKE_64BIT_MASK(0, psz * 8); + temp = tcg_temp_new_i64(); + tcg_gen_ld_i64(temp, cpu_env, pred_full_reg_offset(s, a->pg)); + tcg_gen_andi_i64(temp, temp, pred_esz_masks[esz] & psz_mask); + tcg_gen_brcondi_i64(TCG_COND_EQ, temp, 0, over); + tcg_temp_free_i64(temp); + } else { + TCGv_i32 t32 = tcg_temp_new_i32(); + find_last_active(s, t32, esz, a->pg); + tcg_gen_brcondi_i32(TCG_COND_LT, t32, 0, over); + tcg_temp_free_i32(t32); + } + + /* Load the data. */ + temp = tcg_temp_new_i64(); + tcg_gen_addi_i64(temp, cpu_reg_sp(s, a->rn), a->imm << esz); + tcg_gen_qemu_ld_i64(temp, temp, get_mem_index(s), + s->be_data | dtype_mop[a->dtype]); + + /* Broadcast to *all* elements. */ + tcg_gen_gvec_dup_i64(esz, vec_full_reg_offset(s, a->rd), + vsz, vsz, temp); + tcg_temp_free_i64(temp); + + /* Zero the inactive elements. */ + gen_set_label(over); + do_movz_zpz(s, a->rd, a->rd, a->pg, esz); + return true; +} + static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz, int esz, int nreg) { diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 675b81aaa03..765e7e479b1 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -28,6 +28,7 @@ %imm8_16_10 16:5 10:3 %imm9_16_10 16:s6 10:3 %size_23 23:2 +%dtype_23_13 23:2 13:2 # A combination of tsz:imm3 -- extract esize. %tszimm_esz 22:2 5:5 !function=tszimm_esz @@ -751,6 +752,10 @@ LDR_pri 10000101 10 ...... 000 ... ..... 0 .... @pd_rn_i9 # SVE load vector register LDR_zri 10000101 10 ...... 010 ... ..... ..... @rd_rn_i9 +# SVE load and broadcast element +LD1R_zpri 1000010 .. 1 imm:6 1.. pg:3 rn:5 rd:5 \ + &rpri_load dtype=%dtype_23_13 nreg=0 + ### SVE Memory Contiguous Load Group # SVE contiguous load (scalar plus scalar)