From patchwork Wed Dec 7 08:52:32 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Noah Goldstein X-Patchwork-Id: 1713105 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.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=) Authentication-Results: legolas.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=uQ4T6bXI; dkim-atps=neutral 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 ECDSA (P-384) server-digest SHA384) (No client certificate requested) by legolas.ozlabs.org (Postfix) with ESMTPS id 4NRrms0Cw4z23yq for ; Wed, 7 Dec 2022 19:58:53 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 07DCA3AAA042 for ; Wed, 7 Dec 2022 08:58:51 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 07DCA3AAA042 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1670403531; bh=Re0XsbCOeROOTUsuGZEMdLoewHT3Gs7cFradAMgM+9o=; h=To:Cc:Subject:Date:In-Reply-To:References:List-Id: List-Unsubscribe:List-Archive:List-Post:List-Help:List-Subscribe: From:Reply-To:From; b=uQ4T6bXIk1Lp6/9YFj/Ne6EtZsWAhTDLxuygjaAHvjVvoIK9+kkh1x2potakSxZch piSdZ1nLlULUWTlThyhXcbSsfxfhtnQfhxafzTI3el2zlJiem+RfaaAlfD6sNLTl5+ n3V9n7YgDNrTFZFyw3rRzm7HmOZdWLU+7SzCBMKQ= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from mail-ej1-x62e.google.com (mail-ej1-x62e.google.com [IPv6:2a00:1450:4864:20::62e]) by sourceware.org (Postfix) with ESMTPS id D8894394743E for ; Wed, 7 Dec 2022 08:53:23 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org D8894394743E Received: by mail-ej1-x62e.google.com with SMTP id b2so12304546eja.7 for ; Wed, 07 Dec 2022 00:53:23 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=Re0XsbCOeROOTUsuGZEMdLoewHT3Gs7cFradAMgM+9o=; b=eNLmR4fZnv17g9u5cuwllAhEVl9o72wzsR0ALEV2NspvTW7YosaP681GgffqH6Qx7x tCXyroIOKeX3/wC+9IIoBxmAYnGlhZkgsmtAX6X+zDWo2S1C5BnGXPF5JQtFOHXLc/ng xQmw3vzvzu+i+FxYM+TOdG/t4eb2CI2+rRHnZhdfl0zvzoSvSbdvq8B6B0DtTr56cije 5n2V3P6BvZQfiyL60M6hmfPjNauICtY54uTwrTgSHOJfLMOFMzrycrztbFfoZI79o9Xy 86RaF6aUUM6FU4lppWYyURt6pTz2jxxy7cPzx14k9uF+ZsHsqp0/ZoCf3Y0v/qDiYR5E sJ7Q== X-Gm-Message-State: ANoB5pnJRN/5G2LPhqxtqiDU4yO1sjmEnUpDLXZBzrZ6N6fy7zJ4KrcP QGi46py2u1jbC7kWfCqnnfCDrGeXuAY= X-Google-Smtp-Source: AA0mqf7Krs+rppPa+jyX+imkSLCfM7MG6u7kCrdnAo948fTjGn2Am2IttoyDyU2ccW0QGRVCfgg97Q== X-Received: by 2002:a17:906:840e:b0:7c0:d94c:7384 with SMTP id n14-20020a170906840e00b007c0d94c7384mr15017128ejx.109.1670403202329; Wed, 07 Dec 2022 00:53:22 -0800 (PST) Received: from noahgold-desk.lan (2603-8080-1301-76c6-feb7-1b9b-f2dd-08f7.res6.spectrum.com. [2603:8080:1301:76c6:feb7:1b9b:f2dd:8f7]) by smtp.gmail.com with ESMTPSA id k17-20020aa7c051000000b0046bd3b366f9sm1931767edo.32.2022.12.07.00.53.20 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 07 Dec 2022 00:53:22 -0800 (PST) To: libc-alpha@sourceware.org Cc: goldstein.w.n@gmail.com, hjl.tools@gmail.com, andrey.kolesov@intel.com, carlos@systemhalted.org Subject: [PATCH v1 23/27] x86/fpu: Optimize svml_s_log2f8_core_avx2.S Date: Wed, 7 Dec 2022 00:52:32 -0800 Message-Id: <20221207085236.1424424-23-goldstein.w.n@gmail.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20221207085236.1424424-1-goldstein.w.n@gmail.com> References: <20221207085236.1424424-1-goldstein.w.n@gmail.com> MIME-Version: 1.0 X-Spam-Status: No, score=-12.1 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, FREEMAIL_FROM, GIT_PATCH_0, RCVD_IN_DNSWL_NONE, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) 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: Noah Goldstein via Libc-alpha From: Noah Goldstein Reply-To: Noah Goldstein Errors-To: libc-alpha-bounces+incoming=patchwork.ozlabs.org@sourceware.org Sender: "Libc-alpha" 1. Improve special values case which ends up covering ~half of all float bit patterns. 2. Cleanup some missed optimizations in instruction selection / unnecissary repeated rodata references. 3. Remove unused rodata. 4. Use common data definitions where possible. Code Size Change: -43 Bytes (251 - 294) Input New Time / Old Time 0F (0x00000000) -> 0.8543 0F (0x0000ffff, Denorm) -> 0.9722 .1F (0x3dcccccd) -> 0.9009 5F (0x40a00000) -> 0.9432 2315255808F (0x4f0a0000) -> 0.8680 -NaN (0xffffffff) -> 0.8154 --- .../fpu/multiarch/svml_s_log2f8_core_avx2.S | 290 ++++++++---------- 1 file changed, 123 insertions(+), 167 deletions(-) diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_log2f8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_log2f8_core_avx2.S index 2245d40f84..2c56159323 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_s_log2f8_core_avx2.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_log2f8_core_avx2.S @@ -27,199 +27,155 @@ * */ -/* Offsets for data table __svml_slog2_data_internal - */ -#define MinNorm 0 -#define MaxNorm 32 -#define iBrkValue 64 -#define iOffExpoMask 96 -#define One 128 -#define sPoly 160 +#define LOCAL_DATA_NAME __svml_slog2_data_internal +#include "svml_s_common_avx2_rodata_offsets.h" +/* Offsets for data table __svml_slog2_data_internal. */ +#define _Coeff_9 0 +#define _Coeff_8 32 +#define _Coeff_7 64 +#define _Coeff_6 96 +#define _Coeff_5 128 +#define _Coeff_4 160 +#define _Coeff_3 192 +#define _Coeff_2 224 +#define _Coeff_1 256 #include .section .text.avx2, "ax", @progbits ENTRY(_ZGVdN8v_log2f_avx2) - pushq %rbp - cfi_def_cfa_offset(16) - movq %rsp, %rbp - cfi_def_cfa(6, 16) - cfi_offset(6, -16) - andq $-32, %rsp - subq $96, %rsp + /* reduction: compute r, n. */ + vmovups COMMON_DATA(_IBrkValue)(%rip), %ymm4 + - /* reduction: compute r, n */ - vmovups iBrkValue+__svml_slog2_data_internal(%rip), %ymm4 - vmovups sPoly+64+__svml_slog2_data_internal(%rip), %ymm9 - vmovups sPoly+128+__svml_slog2_data_internal(%rip), %ymm10 - vmovups sPoly+192+__svml_slog2_data_internal(%rip), %ymm12 vpsubd %ymm4, %ymm0, %ymm1 - vcmplt_oqps MinNorm+__svml_slog2_data_internal(%rip), %ymm0, %ymm5 - vcmpnle_uqps MaxNorm+__svml_slog2_data_internal(%rip), %ymm0, %ymm6 - vpand iOffExpoMask+__svml_slog2_data_internal(%rip), %ymm1, %ymm3 + vmovups COMMON_DATA(_NotiOffExpoMask)(%rip), %ymm2 + vpsubd %ymm2, %ymm0, %ymm5 + vmovups COMMON_DATA(_ILoRange)(%rip), %ymm6 + vpcmpgtd %ymm5, %ymm6, %ymm6 + vpandn %ymm1, %ymm2, %ymm3 vpsrad $23, %ymm1, %ymm2 - vmovups sPoly+__svml_slog2_data_internal(%rip), %ymm1 - vpaddd %ymm4, %ymm3, %ymm8 - vcvtdq2ps %ymm2, %ymm14 - vsubps One+__svml_slog2_data_internal(%rip), %ymm8, %ymm13 - vfmadd213ps sPoly+32+__svml_slog2_data_internal(%rip), %ymm13, %ymm1 - vfmadd213ps sPoly+96+__svml_slog2_data_internal(%rip), %ymm13, %ymm9 - vmulps %ymm13, %ymm13, %ymm11 - vfmadd213ps sPoly+160+__svml_slog2_data_internal(%rip), %ymm13, %ymm10 - vfmadd213ps sPoly+224+__svml_slog2_data_internal(%rip), %ymm13, %ymm12 - vfmadd213ps %ymm9, %ymm11, %ymm1 - vfmadd213ps %ymm10, %ymm11, %ymm1 - vfmadd213ps %ymm12, %ymm11, %ymm1 - vfmadd213ps sPoly+256+__svml_slog2_data_internal(%rip), %ymm13, %ymm1 - vorps %ymm6, %ymm5, %ymm7 - - /* combine and get argument value range mask */ - vmovmskps %ymm7, %edx - vfmadd213ps %ymm14, %ymm13, %ymm1 + vmovups LOCAL_DATA(_Coeff_9)(%rip), %ymm1 + vpaddd %ymm4, %ymm3, %ymm3 + + vsubps COMMON_DATA(_OneF)(%rip), %ymm3, %ymm3 + vfmadd213ps LOCAL_DATA(_Coeff_8)(%rip), %ymm3, %ymm1 + vmovups LOCAL_DATA(_Coeff_7)(%rip), %ymm4 + vfmadd213ps LOCAL_DATA(_Coeff_6)(%rip), %ymm3, %ymm4 + vmulps %ymm3, %ymm3, %ymm5 + vmovups LOCAL_DATA(_Coeff_5)(%rip), %ymm7 + vfmadd213ps LOCAL_DATA(_Coeff_4)(%rip), %ymm3, %ymm7 + vmovmskps %ymm6, %edx + + vmovups LOCAL_DATA(_Coeff_3)(%rip), %ymm6 + vfmadd213ps LOCAL_DATA(_Coeff_2)(%rip), %ymm3, %ymm6 + vfmadd213ps %ymm4, %ymm5, %ymm1 + vfmadd213ps %ymm7, %ymm5, %ymm1 + vfmadd213ps %ymm6, %ymm5, %ymm1 + vfmadd213ps LOCAL_DATA(_Coeff_1)(%rip), %ymm3, %ymm1 + vcvtdq2ps %ymm2, %ymm2 + + /* combine and get argument value range mask. */ + + vfmadd213ps %ymm2, %ymm3, %ymm1 testl %edx, %edx - /* Go to special inputs processing branch */ + /* Go to special inputs processing branch. */ jne L(SPECIAL_VALUES_BRANCH) - # LOE rbx r12 r13 r14 r15 edx ymm0 ymm1 - /* Restore registers - * and exit the function - */ -L(EXIT): vmovaps %ymm1, %ymm0 - movq %rbp, %rsp - popq %rbp - cfi_def_cfa(7, 8) - cfi_restore(6) ret - cfi_def_cfa(6, 16) - cfi_offset(6, -16) + /* Cold case. edx has 1s where there was a special value that + needs to be handled by a atanhf call. Optimize for code size + more so than speed here. */ +L(SPECIAL_VALUES_BRANCH): - /* Branch to process - * special inputs - */ + /* Use r13 to save/restore the stack. This allows us to use rbp + as callee save register saving code size. */ + pushq %r13 + cfi_adjust_cfa_offset (8) + cfi_offset (r13, -16) + /* Need to callee save registers to preserve state across tanhf + calls. */ + pushq %rbx + cfi_adjust_cfa_offset (8) + cfi_offset (rbx, -24) + pushq %rbp + cfi_adjust_cfa_offset (8) + cfi_offset (rbp, -32) + movq %rsp, %r13 + cfi_def_cfa_register (r13) -L(SPECIAL_VALUES_BRANCH): - vmovups %ymm0, 32(%rsp) - vmovups %ymm1, 64(%rsp) - # LOE rbx r12 r13 r14 r15 edx ymm1 + /* Align stack and make room for 2x ymm vectors. */ + andq $-32, %rsp + addq $-64, %rsp - xorl %eax, %eax - # LOE rbx r12 r13 r14 r15 eax edx + /* Save all already computed inputs. */ + vmovups %ymm1, (%rsp) + /* Save original input (ymm0 unchanged up to this point). */ + vmovups %ymm0, 32(%rsp) vzeroupper - movq %r12, 16(%rsp) - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus) */ - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 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: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus) */ - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22 - movl %edx, %r13d - movq %r14, (%rsp) - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus) */ - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22 - # LOE rbx r15 r12d r13d - - /* Range mask - * bits check - */ - -L(RANGEMASK_CHECK): - btl %r12d, %r13d - - /* Call scalar math function */ - jc L(SCALAR_MATH_CALL) - # LOE rbx r15 r12d r13d - - /* Special inputs - * processing loop - */ + /* edx has 1s where there was a special value that needs to be + handled by a atanhf call. */ + movl %edx, %ebx L(SPECIAL_VALUES_LOOP): - incl %r12d - cmpl $8, %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 64(%rsp), %ymm1 - - /* Go to exit */ - jmp L(EXIT) - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus) */ - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22 - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus) */ - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22 - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus) */ - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22 - # LOE rbx r12 r13 r14 r15 ymm1 - - /* Scalar math fucntion call - * to process special input - */ - -L(SCALAR_MATH_CALL): - movl %r12d, %r14d - vmovss 32(%rsp, %r14, 4), %xmm0 + + /* use rbp as index for special value that is saved across calls + to atanhf. We technically don't need a callee save register + here as offset to rsp is always [0, 28] so we can restore + rsp by realigning to 64. Essentially the tradeoff is 1 extra + save/restore vs 2 extra instructions in the loop. Realigning + also costs more code size. */ + xorl %ebp, %ebp + tzcntl %ebx, %ebp + + /* Scalar math fucntion call to process special input. */ + vmovss 32(%rsp, %rbp, 4), %xmm0 call log2f@PLT - # LOE rbx r14 r15 r12d r13d xmm0 + /* No good way to avoid the store-forwarding fault this will + cause on return. `lfence` avoids the SF fault but at greater + cost as it serialized stack/callee save restoration. */ + vmovss %xmm0, (%rsp, %rbp, 4) + + blsrl %ebx, %ebx + jnz L(SPECIAL_VALUES_LOOP) + - vmovss %xmm0, 64(%rsp, %r14, 4) - /* Process special inputs in loop */ - jmp L(SPECIAL_VALUES_LOOP) - # LOE rbx r15 r12d r13d + /* All results have been written to (%rsp). */ + vmovups (%rsp), %ymm0 + /* Restore rsp. */ + movq %r13, %rsp + cfi_def_cfa_register (rsp) + /* Restore callee save registers. */ + popq %rbp + cfi_adjust_cfa_offset (-8) + cfi_restore (rbp) + popq %rbx + cfi_adjust_cfa_offset (-8) + cfi_restore (rbp) + popq %r13 + cfi_adjust_cfa_offset (-8) + cfi_restore (r13) + ret END(_ZGVdN8v_log2f_avx2) - .section .rodata, "a" + .section .rodata.avx2, "a" .align 32 -#ifdef __svml_slog2_data_internal_typedef -typedef unsigned int VUINT32; -typedef struct { - __declspec(align(32)) VUINT32 MinNorm[8][1]; - __declspec(align(32)) VUINT32 MaxNorm[8][1]; - __declspec(align(32)) VUINT32 iBrkValue[8][1]; - __declspec(align(32)) VUINT32 iOffExpoMask[8][1]; - __declspec(align(32)) VUINT32 One[8][1]; - __declspec(align(32)) VUINT32 sPoly[9][8][1]; -} __svml_slog2_data_internal; -#endif -__svml_slog2_data_internal: - /* MinNorm */ - .long 0x00800000, 0x00800000, 0x00800000, 0x00800000, 0x00800000, 0x00800000, 0x00800000, 0x00800000 - /* MaxNorm */ - .align 32 - .long 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff - /* iBrkValue = SP 2/3 */ - .align 32 - .long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab - /* iOffExpoMask = SP significand mask */ - .align 32 - .long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff - /* sOne = SP 1.0 */ - .align 32 - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 - /* spoly[9] */ - .align 32 - .long 0x3e554012, 0x3e554012, 0x3e554012, 0x3e554012, 0x3e554012, 0x3e554012, 0x3e554012, 0x3e554012 /* coeff9 */ - .long 0xbe638E14, 0xbe638E14, 0xbe638E14, 0xbe638E14, 0xbe638E14, 0xbe638E14, 0xbe638E14, 0xbe638E14 /* coeff8 */ - .long 0x3e4D660B, 0x3e4D660B, 0x3e4D660B, 0x3e4D660B, 0x3e4D660B, 0x3e4D660B, 0x3e4D660B, 0x3e4D660B /* coeff7 */ - .long 0xbe727824, 0xbe727824, 0xbe727824, 0xbe727824, 0xbe727824, 0xbe727824, 0xbe727824, 0xbe727824 /* coeff6 */ - .long 0x3e93DD07, 0x3e93DD07, 0x3e93DD07, 0x3e93DD07, 0x3e93DD07, 0x3e93DD07, 0x3e93DD07, 0x3e93DD07 /* coeff5 */ - .long 0xbeB8B969, 0xbeB8B969, 0xbeB8B969, 0xbeB8B969, 0xbeB8B969, 0xbeB8B969, 0xbeB8B969, 0xbeB8B969 /* coeff4 */ - .long 0x3eF637C0, 0x3eF637C0, 0x3eF637C0, 0x3eF637C0, 0x3eF637C0, 0x3eF637C0, 0x3eF637C0, 0x3eF637C0 /* coeff3 */ - .long 0xbf38AA2B, 0xbf38AA2B, 0xbf38AA2B, 0xbf38AA2B, 0xbf38AA2B, 0xbf38AA2B, 0xbf38AA2B, 0xbf38AA2B /* coeff2 */ - .long 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B /* coeff1 */ - .align 32 - .type __svml_slog2_data_internal, @object - .size __svml_slog2_data_internal, .-__svml_slog2_data_internal +LOCAL_DATA_NAME: + DATA_VEC (LOCAL_DATA_NAME, _Coeff_9, 0x3e554012) + DATA_VEC (LOCAL_DATA_NAME, _Coeff_8, 0xbe638e14) + DATA_VEC (LOCAL_DATA_NAME, _Coeff_7, 0x3e4d660b) + DATA_VEC (LOCAL_DATA_NAME, _Coeff_6, 0xbe727824) + DATA_VEC (LOCAL_DATA_NAME, _Coeff_5, 0x3e93dd07) + DATA_VEC (LOCAL_DATA_NAME, _Coeff_4, 0xbeb8b969) + DATA_VEC (LOCAL_DATA_NAME, _Coeff_3, 0x3ef637c0) + DATA_VEC (LOCAL_DATA_NAME, _Coeff_2, 0xbf38aa2b) + DATA_VEC (LOCAL_DATA_NAME, _Coeff_1, 0x3fb8aa3b) + + .type LOCAL_DATA_NAME, @object + .size LOCAL_DATA_NAME, .-LOCAL_DATA_NAME