From patchwork Fri Jan 19 04:54:25 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 863306 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; dkim=fail reason="signature verification failed" (1024-bit key; unprotected) header.d=linaro.org header.i=@linaro.org header.b="hKZcTZti"; dkim-atps=neutral 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 3zN7r80xNkz9sNx for ; Fri, 19 Jan 2018 15:58:16 +1100 (AEDT) Received: from localhost ([::1]:52271 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ecOko-0004bG-02 for incoming@patchwork.ozlabs.org; Thu, 18 Jan 2018 23:58:14 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:58614) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ecOhY-00028h-99 for qemu-devel@nongnu.org; Thu, 18 Jan 2018 23:54:54 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ecOhW-0008Te-Ap for qemu-devel@nongnu.org; Thu, 18 Jan 2018 23:54:52 -0500 Received: from mail-pf0-x243.google.com ([2607:f8b0:400e:c00::243]:33532) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1ecOhW-0008TI-2u for qemu-devel@nongnu.org; Thu, 18 Jan 2018 23:54:50 -0500 Received: by mail-pf0-x243.google.com with SMTP id t5so537828pfi.0 for ; Thu, 18 Jan 2018 20:54:49 -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=cqrA8CU4eKHFUueqSZ+9jYOSEtrX5Z7lO22SsZclNa8=; b=hKZcTZtipnou93Si/P8M65jD2QZkAz+Gzk3k/kXmIAIJwNaLbrpgv8/y16ZE6AhPFf iKRr+gr2MzKcFrMW5jAE2TubvN4bOdet3OdxEgRMNzNYOx6h6mPF2pTEMtiqm/OF6QrW BrCCpjbcWcywqG9gEpd2wwMhFAhRlIUIoZCxI= 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=cqrA8CU4eKHFUueqSZ+9jYOSEtrX5Z7lO22SsZclNa8=; b=SQW9tCpm4WQey4UyF0YZmMIFp+k7qtJViiXGUZfQplqZKSBHXPUwrx1q1cumbG/cYf suT2+rYMo46KFeo0rrONCD9FTX37JCx0nOYlohKFitScFXtuqG3Zbuj/IqxRTQ2KhM7z TDEHAa7iOLbPM/RnH/pIOr1yZNh4vzemrbFV+5Gwbf3z0O7CtYcgwHrq/kHm+jSvXXG0 oGo6gaYoGa0Z4gDyh5ZNJmgh+wkwvBZlQ+WNrVFrV1ymDKRBe7F9wPg4iGUVuQ61hsFb jwSyW06gN5IbacorKDYpvxeHQzM9GYwRerYhRtJeG++BfAdI4A9puuXTxyEe7LVAOyc/ icqA== X-Gm-Message-State: AKGB3mKjoqN95I3Y4m7Sli1FB9Qp3sMr2hABtKCbK0M6OoPYgA5RoJZe lqZ6mzSWVF76z/xQ3XNlmiiFEa/l4sQ= X-Google-Smtp-Source: ACJfBovM5goBKRdSGdtU6WztfnQ+ppkWxU9UPIgPTgf0d/H4B/fogVQPRy6OOqkzmOLgpl4rn/hqIQ== X-Received: by 10.99.175.66 with SMTP id s2mr39379313pgo.168.1516337688489; Thu, 18 Jan 2018 20:54:48 -0800 (PST) Received: from cloudburst.twiddle.net (97-113-183-164.tukw.qwest.net. [97.113.183.164]) by smtp.gmail.com with ESMTPSA id m12sm13690022pga.68.2018.01.18.20.54.47 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Thu, 18 Jan 2018 20:54:47 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Date: Thu, 18 Jan 2018 20:54:25 -0800 Message-Id: <20180119045438.28582-4-richard.henderson@linaro.org> X-Mailer: git-send-email 2.14.3 In-Reply-To: <20180119045438.28582-1-richard.henderson@linaro.org> References: <20180119045438.28582-1-richard.henderson@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:400e:c00::243 Subject: [Qemu-devel] [PATCH v2 03/16] target/arm: Use pointers in neon zip/uzp helpers 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+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" Rather than passing regnos to the helpers, pass pointers to the vector registers directly. This eliminates the need to pass in the environment pointer and reduces the number of places that directly access env->vfp.regs[]. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Reviewed-by: Alex Bennée Reviewed-by: Alex Bennée --- target/arm/helper.h | 20 +++--- target/arm/neon_helper.c | 162 +++++++++++++++++++++++++---------------------- target/arm/translate.c | 42 ++++++------ 3 files changed, 120 insertions(+), 104 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 688380af6b..dbdc38fcb7 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -511,16 +511,16 @@ DEF_HELPER_3(iwmmxt_muladdsl, i64, i64, i32, i32) DEF_HELPER_3(iwmmxt_muladdsw, i64, i64, i32, i32) DEF_HELPER_3(iwmmxt_muladdswl, i64, i64, i32, i32) -DEF_HELPER_3(neon_unzip8, void, env, i32, i32) -DEF_HELPER_3(neon_unzip16, void, env, i32, i32) -DEF_HELPER_3(neon_qunzip8, void, env, i32, i32) -DEF_HELPER_3(neon_qunzip16, void, env, i32, i32) -DEF_HELPER_3(neon_qunzip32, void, env, i32, i32) -DEF_HELPER_3(neon_zip8, void, env, i32, i32) -DEF_HELPER_3(neon_zip16, void, env, i32, i32) -DEF_HELPER_3(neon_qzip8, void, env, i32, i32) -DEF_HELPER_3(neon_qzip16, void, env, i32, i32) -DEF_HELPER_3(neon_qzip32, void, env, i32, i32) +DEF_HELPER_FLAGS_2(neon_unzip8, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_unzip16, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_qunzip8, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_qunzip16, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_qunzip32, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_zip8, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_zip16, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_qzip8, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_qzip16, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_2(neon_qzip32, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_3(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index ebdf7c9b10..689491cad3 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -2027,12 +2027,12 @@ uint64_t HELPER(neon_acgt_f64)(uint64_t a, uint64_t b, void *fpstp) #define ELEM(V, N, SIZE) (((V) >> ((N) * (SIZE))) & ((1ull << (SIZE)) - 1)) -void HELPER(neon_qunzip8)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_qunzip8)(void *vd, void *vm) { - uint64_t zm0 = float64_val(env->vfp.regs[rm]); - uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]); - uint64_t zd0 = float64_val(env->vfp.regs[rd]); - uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd0 = rd[0], zd1 = rd[1]; + uint64_t zm0 = rm[0], zm1 = rm[1]; + uint64_t d0 = ELEM(zd0, 0, 8) | (ELEM(zd0, 2, 8) << 8) | (ELEM(zd0, 4, 8) << 16) | (ELEM(zd0, 6, 8) << 24) | (ELEM(zd1, 0, 8) << 32) | (ELEM(zd1, 2, 8) << 40) @@ -2049,18 +2049,19 @@ void HELPER(neon_qunzip8)(CPUARMState *env, uint32_t rd, uint32_t rm) | (ELEM(zm0, 5, 8) << 16) | (ELEM(zm0, 7, 8) << 24) | (ELEM(zm1, 1, 8) << 32) | (ELEM(zm1, 3, 8) << 40) | (ELEM(zm1, 5, 8) << 48) | (ELEM(zm1, 7, 8) << 56); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rm + 1] = make_float64(m1); - env->vfp.regs[rd] = make_float64(d0); - env->vfp.regs[rd + 1] = make_float64(d1); + + rm[0] = m0; + rm[1] = m1; + rd[0] = d0; + rd[1] = d1; } -void HELPER(neon_qunzip16)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_qunzip16)(void *vd, void *vm) { - uint64_t zm0 = float64_val(env->vfp.regs[rm]); - uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]); - uint64_t zd0 = float64_val(env->vfp.regs[rd]); - uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd0 = rd[0], zd1 = rd[1]; + uint64_t zm0 = rm[0], zm1 = rm[1]; + uint64_t d0 = ELEM(zd0, 0, 16) | (ELEM(zd0, 2, 16) << 16) | (ELEM(zd1, 0, 16) << 32) | (ELEM(zd1, 2, 16) << 48); uint64_t d1 = ELEM(zm0, 0, 16) | (ELEM(zm0, 2, 16) << 16) @@ -2069,32 +2070,35 @@ void HELPER(neon_qunzip16)(CPUARMState *env, uint32_t rd, uint32_t rm) | (ELEM(zd1, 1, 16) << 32) | (ELEM(zd1, 3, 16) << 48); uint64_t m1 = ELEM(zm0, 1, 16) | (ELEM(zm0, 3, 16) << 16) | (ELEM(zm1, 1, 16) << 32) | (ELEM(zm1, 3, 16) << 48); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rm + 1] = make_float64(m1); - env->vfp.regs[rd] = make_float64(d0); - env->vfp.regs[rd + 1] = make_float64(d1); + + rm[0] = m0; + rm[1] = m1; + rd[0] = d0; + rd[1] = d1; } -void HELPER(neon_qunzip32)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_qunzip32)(void *vd, void *vm) { - uint64_t zm0 = float64_val(env->vfp.regs[rm]); - uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]); - uint64_t zd0 = float64_val(env->vfp.regs[rd]); - uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd0 = rd[0], zd1 = rd[1]; + uint64_t zm0 = rm[0], zm1 = rm[1]; + uint64_t d0 = ELEM(zd0, 0, 32) | (ELEM(zd1, 0, 32) << 32); uint64_t d1 = ELEM(zm0, 0, 32) | (ELEM(zm1, 0, 32) << 32); uint64_t m0 = ELEM(zd0, 1, 32) | (ELEM(zd1, 1, 32) << 32); uint64_t m1 = ELEM(zm0, 1, 32) | (ELEM(zm1, 1, 32) << 32); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rm + 1] = make_float64(m1); - env->vfp.regs[rd] = make_float64(d0); - env->vfp.regs[rd + 1] = make_float64(d1); + + rm[0] = m0; + rm[1] = m1; + rd[0] = d0; + rd[1] = d1; } -void HELPER(neon_unzip8)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_unzip8)(void *vd, void *vm) { - uint64_t zm = float64_val(env->vfp.regs[rm]); - uint64_t zd = float64_val(env->vfp.regs[rd]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd = rd[0], zm = rm[0]; + uint64_t d0 = ELEM(zd, 0, 8) | (ELEM(zd, 2, 8) << 8) | (ELEM(zd, 4, 8) << 16) | (ELEM(zd, 6, 8) << 24) | (ELEM(zm, 0, 8) << 32) | (ELEM(zm, 2, 8) << 40) @@ -2103,28 +2107,31 @@ void HELPER(neon_unzip8)(CPUARMState *env, uint32_t rd, uint32_t rm) | (ELEM(zd, 5, 8) << 16) | (ELEM(zd, 7, 8) << 24) | (ELEM(zm, 1, 8) << 32) | (ELEM(zm, 3, 8) << 40) | (ELEM(zm, 5, 8) << 48) | (ELEM(zm, 7, 8) << 56); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rd] = make_float64(d0); + + rm[0] = m0; + rd[0] = d0; } -void HELPER(neon_unzip16)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_unzip16)(void *vd, void *vm) { - uint64_t zm = float64_val(env->vfp.regs[rm]); - uint64_t zd = float64_val(env->vfp.regs[rd]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd = rd[0], zm = rm[0]; + uint64_t d0 = ELEM(zd, 0, 16) | (ELEM(zd, 2, 16) << 16) | (ELEM(zm, 0, 16) << 32) | (ELEM(zm, 2, 16) << 48); uint64_t m0 = ELEM(zd, 1, 16) | (ELEM(zd, 3, 16) << 16) | (ELEM(zm, 1, 16) << 32) | (ELEM(zm, 3, 16) << 48); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rd] = make_float64(d0); + + rm[0] = m0; + rd[0] = d0; } -void HELPER(neon_qzip8)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_qzip8)(void *vd, void *vm) { - uint64_t zm0 = float64_val(env->vfp.regs[rm]); - uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]); - uint64_t zd0 = float64_val(env->vfp.regs[rd]); - uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd0 = rd[0], zd1 = rd[1]; + uint64_t zm0 = rm[0], zm1 = rm[1]; + uint64_t d0 = ELEM(zd0, 0, 8) | (ELEM(zm0, 0, 8) << 8) | (ELEM(zd0, 1, 8) << 16) | (ELEM(zm0, 1, 8) << 24) | (ELEM(zd0, 2, 8) << 32) | (ELEM(zm0, 2, 8) << 40) @@ -2141,18 +2148,19 @@ void HELPER(neon_qzip8)(CPUARMState *env, uint32_t rd, uint32_t rm) | (ELEM(zd1, 5, 8) << 16) | (ELEM(zm1, 5, 8) << 24) | (ELEM(zd1, 6, 8) << 32) | (ELEM(zm1, 6, 8) << 40) | (ELEM(zd1, 7, 8) << 48) | (ELEM(zm1, 7, 8) << 56); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rm + 1] = make_float64(m1); - env->vfp.regs[rd] = make_float64(d0); - env->vfp.regs[rd + 1] = make_float64(d1); + + rm[0] = m0; + rm[1] = m1; + rd[0] = d0; + rd[1] = d1; } -void HELPER(neon_qzip16)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_qzip16)(void *vd, void *vm) { - uint64_t zm0 = float64_val(env->vfp.regs[rm]); - uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]); - uint64_t zd0 = float64_val(env->vfp.regs[rd]); - uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd0 = rd[0], zd1 = rd[1]; + uint64_t zm0 = rm[0], zm1 = rm[1]; + uint64_t d0 = ELEM(zd0, 0, 16) | (ELEM(zm0, 0, 16) << 16) | (ELEM(zd0, 1, 16) << 32) | (ELEM(zm0, 1, 16) << 48); uint64_t d1 = ELEM(zd0, 2, 16) | (ELEM(zm0, 2, 16) << 16) @@ -2161,32 +2169,35 @@ void HELPER(neon_qzip16)(CPUARMState *env, uint32_t rd, uint32_t rm) | (ELEM(zd1, 1, 16) << 32) | (ELEM(zm1, 1, 16) << 48); uint64_t m1 = ELEM(zd1, 2, 16) | (ELEM(zm1, 2, 16) << 16) | (ELEM(zd1, 3, 16) << 32) | (ELEM(zm1, 3, 16) << 48); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rm + 1] = make_float64(m1); - env->vfp.regs[rd] = make_float64(d0); - env->vfp.regs[rd + 1] = make_float64(d1); + + rm[0] = m0; + rm[1] = m1; + rd[0] = d0; + rd[1] = d1; } -void HELPER(neon_qzip32)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_qzip32)(void *vd, void *vm) { - uint64_t zm0 = float64_val(env->vfp.regs[rm]); - uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]); - uint64_t zd0 = float64_val(env->vfp.regs[rd]); - uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd0 = rd[0], zd1 = rd[1]; + uint64_t zm0 = rm[0], zm1 = rm[1]; + uint64_t d0 = ELEM(zd0, 0, 32) | (ELEM(zm0, 0, 32) << 32); uint64_t d1 = ELEM(zd0, 1, 32) | (ELEM(zm0, 1, 32) << 32); uint64_t m0 = ELEM(zd1, 0, 32) | (ELEM(zm1, 0, 32) << 32); uint64_t m1 = ELEM(zd1, 1, 32) | (ELEM(zm1, 1, 32) << 32); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rm + 1] = make_float64(m1); - env->vfp.regs[rd] = make_float64(d0); - env->vfp.regs[rd + 1] = make_float64(d1); + + rm[0] = m0; + rm[1] = m1; + rd[0] = d0; + rd[1] = d1; } -void HELPER(neon_zip8)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_zip8)(void *vd, void *vm) { - uint64_t zm = float64_val(env->vfp.regs[rm]); - uint64_t zd = float64_val(env->vfp.regs[rd]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd = rd[0], zm = rm[0]; + uint64_t d0 = ELEM(zd, 0, 8) | (ELEM(zm, 0, 8) << 8) | (ELEM(zd, 1, 8) << 16) | (ELEM(zm, 1, 8) << 24) | (ELEM(zd, 2, 8) << 32) | (ELEM(zm, 2, 8) << 40) @@ -2195,20 +2206,23 @@ void HELPER(neon_zip8)(CPUARMState *env, uint32_t rd, uint32_t rm) | (ELEM(zd, 5, 8) << 16) | (ELEM(zm, 5, 8) << 24) | (ELEM(zd, 6, 8) << 32) | (ELEM(zm, 6, 8) << 40) | (ELEM(zd, 7, 8) << 48) | (ELEM(zm, 7, 8) << 56); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rd] = make_float64(d0); + + rm[0] = m0; + rd[0] = d0; } -void HELPER(neon_zip16)(CPUARMState *env, uint32_t rd, uint32_t rm) +void HELPER(neon_zip16)(void *vd, void *vm) { - uint64_t zm = float64_val(env->vfp.regs[rm]); - uint64_t zd = float64_val(env->vfp.regs[rd]); + uint64_t *rd = vd, *rm = vm; + uint64_t zd = rd[0], zm = rm[0]; + uint64_t d0 = ELEM(zd, 0, 16) | (ELEM(zm, 0, 16) << 16) | (ELEM(zd, 1, 16) << 32) | (ELEM(zm, 1, 16) << 48); uint64_t m0 = ELEM(zd, 2, 16) | (ELEM(zm, 2, 16) << 16) | (ELEM(zd, 3, 16) << 32) | (ELEM(zm, 3, 16) << 48); - env->vfp.regs[rm] = make_float64(m0); - env->vfp.regs[rd] = make_float64(d0); + + rm[0] = m0; + rd[0] = d0; } /* Helper function for 64 bit polynomial multiply case: diff --git a/target/arm/translate.c b/target/arm/translate.c index 7b5db15861..6f02c56abb 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -4687,22 +4687,23 @@ static inline TCGv_i32 neon_get_scalar(int size, int reg) static int gen_neon_unzip(int rd, int rm, int size, int q) { - TCGv_i32 tmp, tmp2; + TCGv_ptr pd, pm; + if (!q && size == 2) { return 1; } - tmp = tcg_const_i32(rd); - tmp2 = tcg_const_i32(rm); + pd = vfp_reg_ptr(true, rd); + pm = vfp_reg_ptr(true, rm); if (q) { switch (size) { case 0: - gen_helper_neon_qunzip8(cpu_env, tmp, tmp2); + gen_helper_neon_qunzip8(pd, pm); break; case 1: - gen_helper_neon_qunzip16(cpu_env, tmp, tmp2); + gen_helper_neon_qunzip16(pd, pm); break; case 2: - gen_helper_neon_qunzip32(cpu_env, tmp, tmp2); + gen_helper_neon_qunzip32(pd, pm); break; default: abort(); @@ -4710,38 +4711,39 @@ static int gen_neon_unzip(int rd, int rm, int size, int q) } else { switch (size) { case 0: - gen_helper_neon_unzip8(cpu_env, tmp, tmp2); + gen_helper_neon_unzip8(pd, pm); break; case 1: - gen_helper_neon_unzip16(cpu_env, tmp, tmp2); + gen_helper_neon_unzip16(pd, pm); break; default: abort(); } } - tcg_temp_free_i32(tmp); - tcg_temp_free_i32(tmp2); + tcg_temp_free_ptr(pd); + tcg_temp_free_ptr(pm); return 0; } static int gen_neon_zip(int rd, int rm, int size, int q) { - TCGv_i32 tmp, tmp2; + TCGv_ptr pd, pm; + if (!q && size == 2) { return 1; } - tmp = tcg_const_i32(rd); - tmp2 = tcg_const_i32(rm); + pd = vfp_reg_ptr(true, rd); + pm = vfp_reg_ptr(true, rm); if (q) { switch (size) { case 0: - gen_helper_neon_qzip8(cpu_env, tmp, tmp2); + gen_helper_neon_qzip8(pd, pm); break; case 1: - gen_helper_neon_qzip16(cpu_env, tmp, tmp2); + gen_helper_neon_qzip16(pd, pm); break; case 2: - gen_helper_neon_qzip32(cpu_env, tmp, tmp2); + gen_helper_neon_qzip32(pd, pm); break; default: abort(); @@ -4749,17 +4751,17 @@ static int gen_neon_zip(int rd, int rm, int size, int q) } else { switch (size) { case 0: - gen_helper_neon_zip8(cpu_env, tmp, tmp2); + gen_helper_neon_zip8(pd, pm); break; case 1: - gen_helper_neon_zip16(cpu_env, tmp, tmp2); + gen_helper_neon_zip16(pd, pm); break; default: abort(); } } - tcg_temp_free_i32(tmp); - tcg_temp_free_i32(tmp2); + tcg_temp_free_ptr(pd); + tcg_temp_free_ptr(pm); return 0; }