From patchwork Mon Mar 7 15:00:08 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sunil Pandey X-Patchwork-Id: 1602339 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: bilbo.ozlabs.org; dkim=pass (1024-bit key; secure) header.d=sourceware.org header.i=@sourceware.org header.a=rsa-sha256 header.s=default header.b=wsIdd56r; dkim-atps=neutral Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=sourceware.org (client-ip=2620:52:3:1:0:246e:9693:128c; helo=sourceware.org; envelope-from=libc-alpha-bounces+incoming=patchwork.ozlabs.org@sourceware.org; receiver=) Received: from sourceware.org (server2.sourceware.org [IPv6:2620:52:3:1:0:246e:9693:128c]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by bilbo.ozlabs.org (Postfix) with ESMTPS id 4KC2xp5j9pz9sFw for ; Tue, 8 Mar 2022 02:51:26 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id E96FC385842E for ; Mon, 7 Mar 2022 15:51:23 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org E96FC385842E DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1646668283; bh=lK3tN5rzoziQBYDr0orSTroNxxjnKtBcl6xrLp6ZF0s=; h=To:Subject:Date:In-Reply-To:References:List-Id:List-Unsubscribe: List-Archive:List-Post:List-Help:List-Subscribe:From:Reply-To: From; b=wsIdd56rrO4cWPtVxWFqBwl0HCASOivcc8oMPbNQw9z1WXQc0yW/BMIUs9pDd/PVh BbOZ4zzECH6Xk3aPMs8a6XtI9bfnJkII9dq95cCc8aXj27SdLeamKy6hBm/fHUISyY pX5wUWOCXwnICTndyx/+b15zWJKHMR+6qhQUH0Ko= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by sourceware.org (Postfix) with ESMTPS id EDA69385841A for ; Mon, 7 Mar 2022 15:02:44 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org EDA69385841A X-IronPort-AV: E=McAfee;i="6200,9189,10278"; a="251983658" X-IronPort-AV: E=Sophos;i="5.90,162,1643702400"; d="scan'208";a="251983658" Received: from fmsmga004.fm.intel.com ([10.253.24.48]) by fmsmga102.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 07 Mar 2022 07:02:03 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.90,162,1643702400"; d="scan'208";a="610639862" Received: from scymds01.sc.intel.com ([10.148.94.138]) by fmsmga004.fm.intel.com with ESMTP; 07 Mar 2022 07:02:03 -0800 Received: from gskx-1.sc.intel.com (gskx-1.sc.intel.com [172.25.149.211]) by scymds01.sc.intel.com with ESMTP id 227F21dl016772; Mon, 7 Mar 2022 07:02:03 -0800 To: libc-alpha@sourceware.org Subject: [PATCH 013/126] x86_64: Fix svml_s_asinf16_core_avx512.S code formatting Date: Mon, 7 Mar 2022 07:00:08 -0800 Message-Id: <20220307150201.10590-14-skpgkp2@gmail.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: <20220307150201.10590-1-skpgkp2@gmail.com> References: <20220307150201.10590-1-skpgkp2@gmail.com> MIME-Version: 1.0 X-Spam-Status: No, score=-7.6 required=5.0 tests=BAYES_00, DKIM_ADSP_CUSTOM_MED, FORGED_GMAIL_RCVD, FREEMAIL_ENVFROM_END_DIGIT, FREEMAIL_FROM, GIT_PATCH_0, HK_RANDOM_ENVFROM, HK_RANDOM_FROM, KAM_DMARC_NONE, KAM_DMARC_STATUS, NML_ADSP_CUSTOM_MED, RCVD_IN_MSPIKE_H2, SPF_HELO_NONE, SPF_SOFTFAIL, TXREP, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Patchwork-Original-From: Sunil K Pandey via Libc-alpha From: Sunil Pandey Reply-To: Sunil K Pandey Errors-To: libc-alpha-bounces+incoming=patchwork.ozlabs.org@sourceware.org Sender: "Libc-alpha" This commit contains following formatting changes 1. Instructions proceeded by a tab. 2. Instruction less than 8 characters in length have a tab between it and the first operand. 3. Instruction greater than 7 characters in length have a space between it and the first operand. 4. Tabs after `#define`d names and their value. 5. 8 space at the beginning of line replaced by tab. 6. Indent comments with code. 7. Remove redundent .text section. --- .../multiarch/svml_s_asinf16_core_avx512.S | 405 +++++++++--------- 1 file changed, 202 insertions(+), 203 deletions(-) diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_asinf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_asinf16_core_avx512.S index 280b5c256c..4e9984d870 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_s_asinf16_core_avx512.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_asinf16_core_avx512.S @@ -28,233 +28,232 @@ /* Offsets for data table __svml_sasin_data_internal */ -#define AbsMask 0 -#define OneHalf 64 -#define SmallNorm 128 -#define One 192 -#define Two 256 -#define sqrt_coeff_1 320 -#define sqrt_coeff_2 384 -#define poly_coeff_1 448 -#define poly_coeff_2 512 -#define poly_coeff_3 576 -#define poly_coeff_4 640 -#define poly_coeff_5 704 -#define Pi2H 768 +#define AbsMask 0 +#define OneHalf 64 +#define SmallNorm 128 +#define One 192 +#define Two 256 +#define sqrt_coeff_1 320 +#define sqrt_coeff_2 384 +#define poly_coeff_1 448 +#define poly_coeff_2 512 +#define poly_coeff_3 576 +#define poly_coeff_4 640 +#define poly_coeff_5 704 +#define Pi2H 768 #include - .text - .section .text.exex512,"ax",@progbits + .section .text.exex512, "ax", @progbits ENTRY(_ZGVeN16v_asinf_skx) - pushq %rbp - cfi_def_cfa_offset(16) - movq %rsp, %rbp - cfi_def_cfa(6, 16) - cfi_offset(6, -16) - andq $-64, %rsp - subq $192, %rsp - vmovups __svml_sasin_data_internal(%rip), %zmm4 - vmovups OneHalf+__svml_sasin_data_internal(%rip), %zmm6 - -/* SQ ~ -2*sqrt(Y) */ - vmovups SmallNorm+__svml_sasin_data_internal(%rip), %zmm8 - vmovups Two+__svml_sasin_data_internal(%rip), %zmm12 - vmovups sqrt_coeff_1+__svml_sasin_data_internal(%rip), %zmm13 - vmovups One+__svml_sasin_data_internal(%rip), %zmm7 - vmovaps %zmm0, %zmm3 - -/* x = |arg| */ - vandps %zmm3, %zmm4, %zmm2 - vandnps %zmm3, %zmm4, %zmm1 - -/* x^2 */ - vmulps {rn-sae}, %zmm2, %zmm2, %zmm5 - vcmpps $17, {sae}, %zmm2, %zmm7, %k0 - vcmpps $21, {sae}, %zmm6, %zmm2, %k2 - vmovups poly_coeff_2+__svml_sasin_data_internal(%rip), %zmm7 - kmovw %k0, %edx - -/* Y = 0.5 - 0.5*x */ - vmovaps %zmm6, %zmm9 - vfnmadd231ps {rn-sae}, %zmm2, %zmm6, %zmm9 - vmovups poly_coeff_5+__svml_sasin_data_internal(%rip), %zmm6 - vrsqrt14ps %zmm9, %zmm10 - vcmpps $17, {sae}, %zmm8, %zmm9, %k1 - vminps {sae}, %zmm9, %zmm5, %zmm0 - vmovups sqrt_coeff_2+__svml_sasin_data_internal(%rip), %zmm8 - vmovups poly_coeff_4+__svml_sasin_data_internal(%rip), %zmm5 - vxorps %zmm10, %zmm10, %zmm10{%k1} - vaddps {rn-sae}, %zmm9, %zmm9, %zmm14 - vmulps {rn-sae}, %zmm10, %zmm10, %zmm11 - vmulps {rn-sae}, %zmm10, %zmm14, %zmm4 - vfmsub213ps {rn-sae}, %zmm12, %zmm11, %zmm14 - vmulps {rn-sae}, %zmm14, %zmm4, %zmm15 - vfmadd231ps {rn-sae}, %zmm14, %zmm13, %zmm8 - vmovups poly_coeff_3+__svml_sasin_data_internal(%rip), %zmm14 - -/* polynomial */ - vmovups poly_coeff_1+__svml_sasin_data_internal(%rip), %zmm13 - vfmsub213ps {rn-sae}, %zmm4, %zmm15, %zmm8 - vfmadd231ps {rn-sae}, %zmm0, %zmm14, %zmm5 - vfmadd231ps {rn-sae}, %zmm0, %zmm13, %zmm7 - vmulps {rn-sae}, %zmm0, %zmm0, %zmm15 - vblendmps %zmm8, %zmm2, %zmm2{%k2} - vfmadd213ps {rn-sae}, %zmm5, %zmm15, %zmm7 - vfmadd213ps {rn-sae}, %zmm6, %zmm0, %zmm7 - vmulps {rn-sae}, %zmm0, %zmm7, %zmm9 - vmovups Pi2H+__svml_sasin_data_internal(%rip), %zmm0 - vfmadd213ps {rn-sae}, %zmm2, %zmm2, %zmm9 - vaddps {rn-sae}, %zmm0, %zmm9, %zmm9{%k2} - vxorps %zmm1, %zmm9, %zmm0 - testl %edx, %edx - -/* Go to special inputs processing branch */ - jne L(SPECIAL_VALUES_BRANCH) - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm3 - -/* Restore registers - * and exit the function - */ + pushq %rbp + cfi_def_cfa_offset(16) + movq %rsp, %rbp + cfi_def_cfa(6, 16) + cfi_offset(6, -16) + andq $-64, %rsp + subq $192, %rsp + vmovups __svml_sasin_data_internal(%rip), %zmm4 + vmovups OneHalf+__svml_sasin_data_internal(%rip), %zmm6 + + /* SQ ~ -2*sqrt(Y) */ + vmovups SmallNorm+__svml_sasin_data_internal(%rip), %zmm8 + vmovups Two+__svml_sasin_data_internal(%rip), %zmm12 + vmovups sqrt_coeff_1+__svml_sasin_data_internal(%rip), %zmm13 + vmovups One+__svml_sasin_data_internal(%rip), %zmm7 + vmovaps %zmm0, %zmm3 + + /* x = |arg| */ + vandps %zmm3, %zmm4, %zmm2 + vandnps %zmm3, %zmm4, %zmm1 + + /* x^2 */ + vmulps {rn-sae}, %zmm2, %zmm2, %zmm5 + vcmpps $17, {sae}, %zmm2, %zmm7, %k0 + vcmpps $21, {sae}, %zmm6, %zmm2, %k2 + vmovups poly_coeff_2+__svml_sasin_data_internal(%rip), %zmm7 + kmovw %k0, %edx + + /* Y = 0.5 - 0.5*x */ + vmovaps %zmm6, %zmm9 + vfnmadd231ps {rn-sae}, %zmm2, %zmm6, %zmm9 + vmovups poly_coeff_5+__svml_sasin_data_internal(%rip), %zmm6 + vrsqrt14ps %zmm9, %zmm10 + vcmpps $17, {sae}, %zmm8, %zmm9, %k1 + vminps {sae}, %zmm9, %zmm5, %zmm0 + vmovups sqrt_coeff_2+__svml_sasin_data_internal(%rip), %zmm8 + vmovups poly_coeff_4+__svml_sasin_data_internal(%rip), %zmm5 + vxorps %zmm10, %zmm10, %zmm10{%k1} + vaddps {rn-sae}, %zmm9, %zmm9, %zmm14 + vmulps {rn-sae}, %zmm10, %zmm10, %zmm11 + vmulps {rn-sae}, %zmm10, %zmm14, %zmm4 + vfmsub213ps {rn-sae}, %zmm12, %zmm11, %zmm14 + vmulps {rn-sae}, %zmm14, %zmm4, %zmm15 + vfmadd231ps {rn-sae}, %zmm14, %zmm13, %zmm8 + vmovups poly_coeff_3+__svml_sasin_data_internal(%rip), %zmm14 + + /* polynomial */ + vmovups poly_coeff_1+__svml_sasin_data_internal(%rip), %zmm13 + vfmsub213ps {rn-sae}, %zmm4, %zmm15, %zmm8 + vfmadd231ps {rn-sae}, %zmm0, %zmm14, %zmm5 + vfmadd231ps {rn-sae}, %zmm0, %zmm13, %zmm7 + vmulps {rn-sae}, %zmm0, %zmm0, %zmm15 + vblendmps %zmm8, %zmm2, %zmm2{%k2} + vfmadd213ps {rn-sae}, %zmm5, %zmm15, %zmm7 + vfmadd213ps {rn-sae}, %zmm6, %zmm0, %zmm7 + vmulps {rn-sae}, %zmm0, %zmm7, %zmm9 + vmovups Pi2H+__svml_sasin_data_internal(%rip), %zmm0 + vfmadd213ps {rn-sae}, %zmm2, %zmm2, %zmm9 + vaddps {rn-sae}, %zmm0, %zmm9, %zmm9{%k2} + vxorps %zmm1, %zmm9, %zmm0 + testl %edx, %edx + + /* Go to special inputs processing branch */ + jne L(SPECIAL_VALUES_BRANCH) + # LOE rbx r12 r13 r14 r15 edx zmm0 zmm3 + + /* Restore registers + * and exit the function + */ L(EXIT): - movq %rbp, %rsp - popq %rbp - cfi_def_cfa(7, 8) - cfi_restore(6) - ret - cfi_def_cfa(6, 16) - cfi_offset(6, -16) - -/* Branch to process - * special inputs - */ + movq %rbp, %rsp + popq %rbp + cfi_def_cfa(7, 8) + cfi_restore(6) + ret + cfi_def_cfa(6, 16) + cfi_offset(6, -16) + + /* Branch to process + * special inputs + */ L(SPECIAL_VALUES_BRANCH): - vmovups %zmm3, 64(%rsp) - vmovups %zmm0, 128(%rsp) - # LOE rbx r12 r13 r14 r15 edx zmm0 - - xorl %eax, %eax - # LOE rbx r12 r13 r14 r15 eax edx - - vzeroupper - movq %r12, 16(%rsp) - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 - movl %eax, %r12d - movq %r13, 8(%rsp) - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 - movl %edx, %r13d - movq %r14, (%rsp) - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 - # LOE rbx r15 r12d r13d - -/* Range mask - * bits check - */ + vmovups %zmm3, 64(%rsp) + vmovups %zmm0, 128(%rsp) + # LOE rbx r12 r13 r14 r15 edx zmm0 + + xorl %eax, %eax + # LOE rbx r12 r13 r14 r15 eax edx + + vzeroupper + movq %r12, 16(%rsp) + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ + .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 + movl %eax, %r12d + movq %r13, 8(%rsp) + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ + .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 + movl %edx, %r13d + movq %r14, (%rsp) + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ + .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 + # LOE rbx r15 r12d r13d + + /* Range mask + * bits check + */ L(RANGEMASK_CHECK): - btl %r12d, %r13d + btl %r12d, %r13d -/* Call scalar math function */ - jc L(SCALAR_MATH_CALL) - # LOE rbx r15 r12d r13d + /* Call scalar math function */ + jc L(SCALAR_MATH_CALL) + # LOE rbx r15 r12d r13d -/* Special inputs - * processing loop - */ + /* Special inputs + * processing loop + */ L(SPECIAL_VALUES_LOOP): - incl %r12d - cmpl $16, %r12d - -/* Check bits in range mask */ - jl L(RANGEMASK_CHECK) - # LOE rbx r15 r12d r13d - - movq 16(%rsp), %r12 - cfi_restore(12) - movq 8(%rsp), %r13 - cfi_restore(13) - movq (%rsp), %r14 - cfi_restore(14) - vmovups 128(%rsp), %zmm0 - -/* Go to exit */ - jmp L(EXIT) - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 - # LOE rbx r12 r13 r14 r15 zmm0 - -/* Scalar math fucntion call - * to process special input - */ + incl %r12d + cmpl $16, %r12d + + /* Check bits in range mask */ + jl L(RANGEMASK_CHECK) + # LOE rbx r15 r12d r13d + + movq 16(%rsp), %r12 + cfi_restore(12) + movq 8(%rsp), %r13 + cfi_restore(13) + movq (%rsp), %r14 + cfi_restore(14) + vmovups 128(%rsp), %zmm0 + + /* Go to exit */ + jmp L(EXIT) + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ + .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ + .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ + .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 + # LOE rbx r12 r13 r14 r15 zmm0 + + /* Scalar math fucntion call + * to process special input + */ L(SCALAR_MATH_CALL): - movl %r12d, %r14d - movss 64(%rsp,%r14,4), %xmm0 - call asinf@PLT - # LOE rbx r14 r15 r12d r13d xmm0 + movl %r12d, %r14d + movss 64(%rsp, %r14, 4), %xmm0 + call asinf@PLT + # LOE rbx r14 r15 r12d r13d xmm0 - movss %xmm0, 128(%rsp,%r14,4) + movss %xmm0, 128(%rsp, %r14, 4) -/* Process special inputs in loop */ - jmp L(SPECIAL_VALUES_LOOP) - # LOE rbx r15 r12d r13d + /* Process special inputs in loop */ + jmp L(SPECIAL_VALUES_LOOP) + # LOE rbx r15 r12d r13d END(_ZGVeN16v_asinf_skx) - .section .rodata, "a" - .align 64 + .section .rodata, "a" + .align 64 #ifdef __svml_sasin_data_internal_typedef typedef unsigned int VUINT32; typedef struct { - __declspec(align(64)) VUINT32 AbsMask[16][1]; - __declspec(align(64)) VUINT32 OneHalf[16][1]; - __declspec(align(64)) VUINT32 SmallNorm[16][1]; - __declspec(align(64)) VUINT32 One[16][1]; - __declspec(align(64)) VUINT32 Two[16][1]; - __declspec(align(64)) VUINT32 sqrt_coeff[2][16][1]; - __declspec(align(64)) VUINT32 poly_coeff[5][16][1]; - __declspec(align(64)) VUINT32 Pi2H[16][1]; + __declspec(align(64)) VUINT32 AbsMask[16][1]; + __declspec(align(64)) VUINT32 OneHalf[16][1]; + __declspec(align(64)) VUINT32 SmallNorm[16][1]; + __declspec(align(64)) VUINT32 One[16][1]; + __declspec(align(64)) VUINT32 Two[16][1]; + __declspec(align(64)) VUINT32 sqrt_coeff[2][16][1]; + __declspec(align(64)) VUINT32 poly_coeff[5][16][1]; + __declspec(align(64)) VUINT32 Pi2H[16][1]; } __svml_sasin_data_internal; #endif __svml_sasin_data_internal: - /*== AbsMask ==*/ - .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff - /*== OneHalf ==*/ - .align 64 - .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 - /*== SmallNorm ==*/ - .align 64 - .long 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000 - /*== One ==*/ - .align 64 - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 - /*== Two ==*/ - .align 64 - .long 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000 - /*== sqrt_coeff[2] ==*/ - .align 64 - .long 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004 /* sqrt_coeff2 */ - .long 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001 /* sqrt_coeff1 */ - /*== poly_coeff[5] ==*/ - .align 64 - .long 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07 /* poly_coeff5 */ - .long 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B /* poly_coeff4 */ - .long 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4 /* poly_coeff3 */ - .long 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12 /* poly_coeff2 */ - .long 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF /* poly_coeff1 */ - /*== Pi2H ==*/ - .align 64 - .long 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB - .align 64 - .type __svml_sasin_data_internal,@object - .size __svml_sasin_data_internal,.-__svml_sasin_data_internal + /* AbsMask */ + .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff + /* OneHalf */ + .align 64 + .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 + /* SmallNorm */ + .align 64 + .long 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000 + /* One */ + .align 64 + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 + /* Two */ + .align 64 + .long 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000 + /* sqrt_coeff[2] */ + .align 64 + .long 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004 /* sqrt_coeff2 */ + .long 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001 /* sqrt_coeff1 */ + /* poly_coeff[5] */ + .align 64 + .long 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07 /* poly_coeff5 */ + .long 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B /* poly_coeff4 */ + .long 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4 /* poly_coeff3 */ + .long 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12 /* poly_coeff2 */ + .long 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF /* poly_coeff1 */ + /* Pi2H */ + .align 64 + .long 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB + .align 64 + .type __svml_sasin_data_internal, @object + .size __svml_sasin_data_internal, .-__svml_sasin_data_internal