From patchwork Thu Mar 6 23:34:02 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexander Graf X-Patchwork-Id: 327710 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.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 D32322C00AD for ; Fri, 7 Mar 2014 12:50:15 +1100 (EST) Received: from localhost ([::1]:33502 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WLicR-0005qP-AT for incoming@patchwork.ozlabs.org; Thu, 06 Mar 2014 19:26:31 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:58996) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WLhob-0001Jn-74 for qemu-devel@nongnu.org; Thu, 06 Mar 2014 18:35:40 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1WLhnz-0003QZ-DX for qemu-devel@nongnu.org; Thu, 06 Mar 2014 18:35:01 -0500 Received: from cantor2.suse.de ([195.135.220.15]:55899 helo=mx2.suse.de) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WLhnz-0003GM-3D; Thu, 06 Mar 2014 18:34:23 -0500 Received: from relay2.suse.de (charybdis-ext.suse.de [195.135.220.254]) by mx2.suse.de (Postfix) with ESMTP id D2F39AD3A; Thu, 6 Mar 2014 23:34:22 +0000 (UTC) From: Alexander Graf To: qemu-devel@nongnu.org Date: Fri, 7 Mar 2014 00:34:02 +0100 Message-Id: <1394148857-19607-116-git-send-email-agraf@suse.de> X-Mailer: git-send-email 1.7.12.4 In-Reply-To: <1394148857-19607-1-git-send-email-agraf@suse.de> References: <1394148857-19607-1-git-send-email-agraf@suse.de> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x X-Received-From: 195.135.220.15 Cc: Peter Maydell , Tom Musta , blauwirbel@gmail.com, qemu-ppc@nongnu.org, aliguori@amazon.com, aurelien@aurel32.net Subject: [Qemu-devel] [PULL 115/130] target-ppc: Altivec 2.07: Binary Coded Decimal Instructions X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 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-bounces+incoming=patchwork.ozlabs.org@nongnu.org From: Tom Musta This patch add the Binary Coded Decimal instructions bcdadd. and bcdsub. Signed-off-by: Tom Musta Signed-off-by: Alexander Graf --- target-ppc/helper.h | 3 + target-ppc/int_helper.c | 201 ++++++++++++++++++++++++++++++++++++++++++++++++ target-ppc/translate.c | 45 ++++++++++- 3 files changed, 245 insertions(+), 4 deletions(-) diff --git a/target-ppc/helper.h b/target-ppc/helper.h index ca9eba5..ef6aa58 100644 --- a/target-ppc/helper.h +++ b/target-ppc/helper.h @@ -316,6 +316,9 @@ DEF_HELPER_3(vpmsumh, void, avr, avr, avr) DEF_HELPER_3(vpmsumw, void, avr, avr, avr) DEF_HELPER_3(vpmsumd, void, avr, avr, avr) +DEF_HELPER_4(bcdadd, i32, avr, avr, avr, i32) +DEF_HELPER_4(bcdsub, i32, avr, avr, avr, i32) + DEF_HELPER_2(xsadddp, void, env, i32) DEF_HELPER_2(xssubdp, void, env, i32) DEF_HELPER_2(xsmuldp, void, env, i32) diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c index 4e8e507..ce7c6a0 100644 --- a/target-ppc/int_helper.c +++ b/target-ppc/int_helper.c @@ -2136,6 +2136,207 @@ void helper_vsubecuq(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) #endif } +#define BCD_PLUS_PREF_1 0xC +#define BCD_PLUS_PREF_2 0xF +#define BCD_PLUS_ALT_1 0xA +#define BCD_NEG_PREF 0xD +#define BCD_NEG_ALT 0xB +#define BCD_PLUS_ALT_2 0xE + +#if defined(HOST_WORDS_BIGENDIAN) +#define BCD_DIG_BYTE(n) (15 - (n/2)) +#else +#define BCD_DIG_BYTE(n) (n/2) +#endif + +static int bcd_get_sgn(ppc_avr_t *bcd) +{ + switch (bcd->u8[BCD_DIG_BYTE(0)] & 0xF) { + case BCD_PLUS_PREF_1: + case BCD_PLUS_PREF_2: + case BCD_PLUS_ALT_1: + case BCD_PLUS_ALT_2: + { + return 1; + } + + case BCD_NEG_PREF: + case BCD_NEG_ALT: + { + return -1; + } + + default: + { + return 0; + } + } +} + +static int bcd_preferred_sgn(int sgn, int ps) +{ + if (sgn >= 0) { + return (ps == 0) ? BCD_PLUS_PREF_1 : BCD_PLUS_PREF_2; + } else { + return BCD_NEG_PREF; + } +} + +static uint8_t bcd_get_digit(ppc_avr_t *bcd, int n, int *invalid) +{ + uint8_t result; + if (n & 1) { + result = bcd->u8[BCD_DIG_BYTE(n)] >> 4; + } else { + result = bcd->u8[BCD_DIG_BYTE(n)] & 0xF; + } + + if (unlikely(result > 9)) { + *invalid = true; + } + return result; +} + +static void bcd_put_digit(ppc_avr_t *bcd, uint8_t digit, int n) +{ + if (n & 1) { + bcd->u8[BCD_DIG_BYTE(n)] &= 0x0F; + bcd->u8[BCD_DIG_BYTE(n)] |= (digit<<4); + } else { + bcd->u8[BCD_DIG_BYTE(n)] &= 0xF0; + bcd->u8[BCD_DIG_BYTE(n)] |= digit; + } +} + +static int bcd_cmp_mag(ppc_avr_t *a, ppc_avr_t *b) +{ + int i; + int invalid = 0; + for (i = 31; i > 0; i--) { + uint8_t dig_a = bcd_get_digit(a, i, &invalid); + uint8_t dig_b = bcd_get_digit(b, i, &invalid); + if (unlikely(invalid)) { + return 0; /* doesnt matter */ + } else if (dig_a > dig_b) { + return 1; + } else if (dig_a < dig_b) { + return -1; + } + } + + return 0; +} + +static int bcd_add_mag(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b, int *invalid, + int *overflow) +{ + int carry = 0; + int i; + int is_zero = 1; + for (i = 1; i <= 31; i++) { + uint8_t digit = bcd_get_digit(a, i, invalid) + + bcd_get_digit(b, i, invalid) + carry; + is_zero &= (digit == 0); + if (digit > 9) { + carry = 1; + digit -= 10; + } else { + carry = 0; + } + + bcd_put_digit(t, digit, i); + + if (unlikely(*invalid)) { + return -1; + } + } + + *overflow = carry; + return is_zero; +} + +static int bcd_sub_mag(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b, int *invalid, + int *overflow) +{ + int carry = 0; + int i; + int is_zero = 1; + for (i = 1; i <= 31; i++) { + uint8_t digit = bcd_get_digit(a, i, invalid) - + bcd_get_digit(b, i, invalid) + carry; + is_zero &= (digit == 0); + if (digit & 0x80) { + carry = -1; + digit += 10; + } else { + carry = 0; + } + + bcd_put_digit(t, digit, i); + + if (unlikely(*invalid)) { + return -1; + } + } + + *overflow = carry; + return is_zero; +} + +uint32_t helper_bcdadd(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) +{ + + int sgna = bcd_get_sgn(a); + int sgnb = bcd_get_sgn(b); + int invalid = (sgna == 0) || (sgnb == 0); + int overflow = 0; + int zero = 0; + uint32_t cr = 0; + ppc_avr_t result = { .u64 = { 0, 0 } }; + + if (!invalid) { + if (sgna == sgnb) { + result.u8[BCD_DIG_BYTE(0)] = bcd_preferred_sgn(sgna, ps); + zero = bcd_add_mag(&result, a, b, &invalid, &overflow); + cr = (sgna > 0) ? 4 : 8; + } else if (bcd_cmp_mag(a, b) > 0) { + result.u8[BCD_DIG_BYTE(0)] = bcd_preferred_sgn(sgna, ps); + zero = bcd_sub_mag(&result, a, b, &invalid, &overflow); + cr = (sgna > 0) ? 4 : 8; + } else { + result.u8[BCD_DIG_BYTE(0)] = bcd_preferred_sgn(sgnb, ps); + zero = bcd_sub_mag(&result, b, a, &invalid, &overflow); + cr = (sgnb > 0) ? 4 : 8; + } + } + + if (unlikely(invalid)) { + result.u64[HI_IDX] = result.u64[LO_IDX] = -1; + cr = 1; + } else if (overflow) { + cr |= 1; + } else if (zero) { + cr = 2; + } + + *r = result; + + return cr; +} + +uint32_t helper_bcdsub(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) +{ + ppc_avr_t bcopy = *b; + int sgnb = bcd_get_sgn(b); + if (sgnb < 0) { + bcd_put_digit(&bcopy, BCD_PLUS_PREF_1, 0); + } else if (sgnb > 0) { + bcd_put_digit(&bcopy, BCD_NEG_PREF, 0); + } + /* else invalid ... defer to bcdadd code for proper handling */ + + return helper_bcdadd(r, a, &bcopy, ps); +} #undef VECTOR_FOR_INORDER_I #undef HI_IDX diff --git a/target-ppc/translate.c b/target-ppc/translate.c index 706bd5d..2b46cd6 100644 --- a/target-ppc/translate.c +++ b/target-ppc/translate.c @@ -7377,6 +7377,43 @@ GEN_VXFORM(vpmsumh, 4, 17) GEN_VXFORM(vpmsumw, 4, 18) GEN_VXFORM(vpmsumd, 4, 19) +#define GEN_BCD(op) \ +static void gen_##op(DisasContext *ctx) \ +{ \ + TCGv_ptr ra, rb, rd; \ + TCGv_i32 ps; \ + \ + if (unlikely(!ctx->altivec_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VPU); \ + return; \ + } \ + \ + ra = gen_avr_ptr(rA(ctx->opcode)); \ + rb = gen_avr_ptr(rB(ctx->opcode)); \ + rd = gen_avr_ptr(rD(ctx->opcode)); \ + \ + ps = tcg_const_i32((ctx->opcode & 0x200) != 0); \ + \ + gen_helper_##op(cpu_crf[6], rd, ra, rb, ps); \ + \ + tcg_temp_free_ptr(ra); \ + tcg_temp_free_ptr(rb); \ + tcg_temp_free_ptr(rd); \ + tcg_temp_free_i32(ps); \ +} + +GEN_BCD(bcdadd) +GEN_BCD(bcdsub) + +GEN_VXFORM_DUAL(vsububm, PPC_ALTIVEC, PPC_NONE, \ + bcdadd, PPC_NONE, PPC2_ALTIVEC_207) +GEN_VXFORM_DUAL(vsububs, PPC_ALTIVEC, PPC_NONE, \ + bcdadd, PPC_NONE, PPC2_ALTIVEC_207) +GEN_VXFORM_DUAL(vsubuhm, PPC_ALTIVEC, PPC_NONE, \ + bcdsub, PPC_NONE, PPC2_ALTIVEC_207) +GEN_VXFORM_DUAL(vsubuhs, PPC_ALTIVEC, PPC_NONE, \ + bcdsub, PPC_NONE, PPC2_ALTIVEC_207) + /*** VSX extension ***/ static inline TCGv_i64 cpu_vsrh(int n) @@ -10442,8 +10479,8 @@ GEN_VXFORM(vaddubm, 0, 0), GEN_VXFORM(vadduhm, 0, 1), GEN_VXFORM(vadduwm, 0, 2), GEN_VXFORM_207(vaddudm, 0, 3), -GEN_VXFORM(vsububm, 0, 16), -GEN_VXFORM(vsubuhm, 0, 17), +GEN_VXFORM_DUAL(vsububm, bcdadd, 0, 16, PPC_ALTIVEC, PPC_NONE), +GEN_VXFORM_DUAL(vsubuhm, bcdsub, 0, 17, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM(vsubuwm, 0, 18), GEN_VXFORM_207(vsubudm, 0, 19), GEN_VXFORM(vmaxub, 1, 0), @@ -10510,8 +10547,8 @@ GEN_VXFORM(vadduws, 0, 10), GEN_VXFORM(vaddsbs, 0, 12), GEN_VXFORM(vaddshs, 0, 13), GEN_VXFORM(vaddsws, 0, 14), -GEN_VXFORM(vsububs, 0, 24), -GEN_VXFORM(vsubuhs, 0, 25), +GEN_VXFORM_DUAL(vsububs, bcdadd, 0, 24, PPC_ALTIVEC, PPC_NONE), +GEN_VXFORM_DUAL(vsubuhs, bcdsub, 0, 25, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM(vsubuws, 0, 26), GEN_VXFORM(vsubsbs, 0, 28), GEN_VXFORM(vsubshs, 0, 29),