From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:57419) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ULEpl-0001RQ-A5 for qemu-devel@nongnu.org; Thu, 28 Mar 2013 11:33:48 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ULEpe-0003b9-Sc for qemu-devel@nongnu.org; Thu, 28 Mar 2013 11:33:45 -0400 Received: from mail-pb0-f51.google.com ([209.85.160.51]:44845) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ULEpe-0003b2-8Z for qemu-devel@nongnu.org; Thu, 28 Mar 2013 11:33:38 -0400 Received: by mail-pb0-f51.google.com with SMTP id rr4so3161851pbb.38 for ; Thu, 28 Mar 2013 08:33:37 -0700 (PDT) Sender: Richard Henderson From: Richard Henderson Date: Thu, 28 Mar 2013 08:32:53 -0700 Message-Id: <1364484781-15561-13-git-send-email-rth@twiddle.net> In-Reply-To: <1364484781-15561-1-git-send-email-rth@twiddle.net> References: <1364484781-15561-1-git-send-email-rth@twiddle.net> Subject: [Qemu-devel] [PATCH v3 12/20] tcg-arm: Cleanup multiply subroutines List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: Peter Maydell , Aurelien Jarno Make the code more readable by only having one copy of the magic numbers, swapping registers as needed prior to that. Speed the compiler by not applying the rd == rn avoidance for v6 or later. Signed-off-by: Richard Henderson --- tcg/arm/tcg-target.c | 85 +++++++++++++++++++++++++++------------------------- 1 file changed, 45 insertions(+), 40 deletions(-) diff --git a/tcg/arm/tcg-target.c b/tcg/arm/tcg-target.c index d7b8b88..e5ec999 100644 --- a/tcg/arm/tcg-target.c +++ b/tcg/arm/tcg-target.c @@ -542,55 +542,60 @@ static void tcg_out_dat_rIN(TCGContext *s, int cond, int opc, int opneg, } } -static inline void tcg_out_mul32(TCGContext *s, - int cond, int rd, int rs, int rm) -{ - if (rd != rm) - tcg_out32(s, (cond << 28) | (rd << 16) | (0 << 12) | - (rs << 8) | 0x90 | rm); - else if (rd != rs) - tcg_out32(s, (cond << 28) | (rd << 16) | (0 << 12) | - (rm << 8) | 0x90 | rs); - else { - tcg_out32(s, (cond << 28) | (TCG_REG_TMP << 16) | (0 << 12) | - (rs << 8) | 0x90 | rm); - tcg_out_dat_reg(s, cond, ARITH_MOV, - rd, 0, TCG_REG_TMP, SHIFT_IMM_LSL(0)); +static inline void tcg_out_mul32(TCGContext *s, int cond, TCGReg rd, + TCGReg rn, TCGReg rm) +{ + /* if ArchVersion() < 6 && d == n then UNPREDICTABLE; */ + if (!use_armv6_instructions && rd == rn) { + if (rd == rm) { + /* rd == rn == rm; copy an input to tmp first. */ + tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn); + rm = rn = TCG_REG_TMP; + } else { + rn = rm; + rm = rd; + } } + /* mul */ + tcg_out32(s, (cond << 28) | 0x90 | (rd << 16) | (rm << 8) | rn); } -static inline void tcg_out_umull32(TCGContext *s, - int cond, int rd0, int rd1, int rs, int rm) +static inline void tcg_out_umull32(TCGContext *s, int cond, TCGReg rd0, + TCGReg rd1, TCGReg rn, TCGReg rm) { - if (rd0 != rm && rd1 != rm) - tcg_out32(s, (cond << 28) | 0x800090 | - (rd1 << 16) | (rd0 << 12) | (rs << 8) | rm); - else if (rd0 != rs && rd1 != rs) - tcg_out32(s, (cond << 28) | 0x800090 | - (rd1 << 16) | (rd0 << 12) | (rm << 8) | rs); - else { - tcg_out_dat_reg(s, cond, ARITH_MOV, - TCG_REG_TMP, 0, rm, SHIFT_IMM_LSL(0)); - tcg_out32(s, (cond << 28) | 0x800090 | TCG_REG_TMP | - (rd1 << 16) | (rd0 << 12) | (rs << 8)); + /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE; */ + if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) { + if (rd0 == rm || rd1 == rm) { + tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn); + rn = TCG_REG_TMP; + } else { + TCGReg t = rn; + rn = rm; + rm = t; + } } + /* umull */ + tcg_out32(s, (cond << 28) | 0x00800090 | + (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn); } -static inline void tcg_out_smull32(TCGContext *s, - int cond, int rd0, int rd1, int rs, int rm) +static inline void tcg_out_smull32(TCGContext *s, int cond, TCGReg rd0, + TCGReg rd1, TCGReg rn, TCGReg rm) { - if (rd0 != rm && rd1 != rm) - tcg_out32(s, (cond << 28) | 0xc00090 | - (rd1 << 16) | (rd0 << 12) | (rs << 8) | rm); - else if (rd0 != rs && rd1 != rs) - tcg_out32(s, (cond << 28) | 0xc00090 | - (rd1 << 16) | (rd0 << 12) | (rm << 8) | rs); - else { - tcg_out_dat_reg(s, cond, ARITH_MOV, - TCG_REG_TMP, 0, rm, SHIFT_IMM_LSL(0)); - tcg_out32(s, (cond << 28) | 0xc00090 | TCG_REG_TMP | - (rd1 << 16) | (rd0 << 12) | (rs << 8)); + /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE; */ + if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) { + if (rd0 == rm || rd1 == rm) { + tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn); + rn = TCG_REG_TMP; + } else { + TCGReg t = rn; + rn = rm; + rm = t; + } } + /* smull */ + tcg_out32(s, (cond << 28) | 0x00c00090 | + (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn); } static inline void tcg_out_sdiv(TCGContext *s, int cond, int rd, int rn, int rm) -- 1.8.1.4