From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 7852) id 948D2385AC1C; Tue, 8 Mar 2022 06:13:36 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 948D2385AC1C Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Sunil Pandey To: glibc-cvs@sourceware.org Subject: [glibc] x86_64: Fix svml_d_log28_core_avx512.S code formatting X-Act-Checkin: glibc X-Git-Author: Sunil K Pandey X-Git-Refname: refs/heads/master X-Git-Oldrev: 26b648892a4ff2ee2c3f8cdb511d6550c8396731 X-Git-Newrev: 993be2001c200fb8d4be89ac165e7d4518a1226d Message-Id: <20220308061336.948D2385AC1C@sourceware.org> Date: Tue, 8 Mar 2022 06:13:36 +0000 (GMT) X-BeenThere: glibc-cvs@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Glibc-cvs mailing list List-Unsubscribe: , List-Archive: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Mar 2022 06:13:36 -0000 https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=993be2001c200fb8d4be89ac165e7d4518a1226d commit 993be2001c200fb8d4be89ac165e7d4518a1226d Author: Sunil K Pandey Date: Mon Mar 7 10:47:14 2022 -0800 x86_64: Fix svml_d_log28_core_avx512.S code formatting 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. 8. 1 space between line content and line comment. 9. Space after all commas. Reviewed-by: Noah Goldstein Diff: --- .../fpu/multiarch/svml_d_log28_core_avx512.S | 471 ++++++++++----------- 1 file changed, 235 insertions(+), 236 deletions(-) diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_log28_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_d_log28_core_avx512.S index 9a2322ecad..bcb6736dec 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_d_log28_core_avx512.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_d_log28_core_avx512.S @@ -29,265 +29,264 @@ /* Offsets for data table __svml_dlog2_data_internal_avx512 */ -#define Log_tbl 0 -#define One 128 -#define C075 192 -#define poly_coeff9 256 -#define poly_coeff8 320 -#define poly_coeff7 384 -#define poly_coeff6 448 -#define poly_coeff5 512 -#define poly_coeff4 576 -#define poly_coeff3 640 -#define poly_coeff2 704 -#define poly_coeff1 768 +#define Log_tbl 0 +#define One 128 +#define C075 192 +#define poly_coeff9 256 +#define poly_coeff8 320 +#define poly_coeff7 384 +#define poly_coeff6 448 +#define poly_coeff5 512 +#define poly_coeff4 576 +#define poly_coeff3 640 +#define poly_coeff2 704 +#define poly_coeff1 768 #include - .text - .section .text.evex512,"ax",@progbits + .section .text.evex512, "ax", @progbits ENTRY(_ZGVeN8v_log2_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 - vmovaps %zmm0, %zmm7 - vgetmantpd $8, {sae}, %zmm7, %zmm6 - vmovups One+__svml_dlog2_data_internal_avx512(%rip), %zmm2 - vmovups poly_coeff5+__svml_dlog2_data_internal_avx512(%rip), %zmm12 - vmovups poly_coeff3+__svml_dlog2_data_internal_avx512(%rip), %zmm13 - -/* Start polynomial evaluation */ - vmovups poly_coeff9+__svml_dlog2_data_internal_avx512(%rip), %zmm10 - vmovups poly_coeff8+__svml_dlog2_data_internal_avx512(%rip), %zmm0 - vmovups poly_coeff7+__svml_dlog2_data_internal_avx512(%rip), %zmm11 - vmovups poly_coeff6+__svml_dlog2_data_internal_avx512(%rip), %zmm14 - -/* Prepare exponent correction: DblRcp<0.75? */ - vmovups C075+__svml_dlog2_data_internal_avx512(%rip), %zmm1 - -/* Table lookup */ - vmovups __svml_dlog2_data_internal_avx512(%rip), %zmm4 - -/* GetExp(x) */ - vgetexppd {sae}, %zmm7, %zmm5 - -/* DblRcp ~ 1/Mantissa */ - vrcp14pd %zmm6, %zmm8 - -/* x<=0? */ - vfpclasspd $94, %zmm7, %k0 - -/* round DblRcp to 4 fractional bits (RN mode, no Precision exception) */ - vrndscalepd $88, {sae}, %zmm8, %zmm3 - vmovups poly_coeff4+__svml_dlog2_data_internal_avx512(%rip), %zmm8 - kmovw %k0, %edx - -/* Reduced argument: R = DblRcp*Mantissa - 1 */ - vfmsub213pd {rn-sae}, %zmm2, %zmm3, %zmm6 - vcmppd $17, {sae}, %zmm1, %zmm3, %k1 - vfmadd231pd {rn-sae}, %zmm6, %zmm12, %zmm8 - vmovups poly_coeff2+__svml_dlog2_data_internal_avx512(%rip), %zmm12 - vfmadd231pd {rn-sae}, %zmm6, %zmm10, %zmm0 - vfmadd231pd {rn-sae}, %zmm6, %zmm11, %zmm14 - vmovups poly_coeff1+__svml_dlog2_data_internal_avx512(%rip), %zmm1 - -/* R^2 */ - vmulpd {rn-sae}, %zmm6, %zmm6, %zmm15 - vfmadd231pd {rn-sae}, %zmm6, %zmm13, %zmm12 - -/* Prepare table index */ - vpsrlq $48, %zmm3, %zmm9 - -/* add 1 to Expon if DblRcp<0.75 */ - vaddpd {rn-sae}, %zmm2, %zmm5, %zmm5{%k1} - vmulpd {rn-sae}, %zmm15, %zmm15, %zmm13 - vfmadd213pd {rn-sae}, %zmm14, %zmm15, %zmm0 - vfmadd213pd {rn-sae}, %zmm12, %zmm15, %zmm8 - vpermt2pd Log_tbl+64+__svml_dlog2_data_internal_avx512(%rip), %zmm9, %zmm4 - -/* polynomial */ - vfmadd213pd {rn-sae}, %zmm8, %zmm13, %zmm0 - vfmadd213pd {rn-sae}, %zmm1, %zmm6, %zmm0 - vfmadd213pd {rn-sae}, %zmm4, %zmm0, %zmm6 - vaddpd {rn-sae}, %zmm6, %zmm5, %zmm0 - testl %edx, %edx - -/* Go to special inputs processing branch */ - jne L(SPECIAL_VALUES_BRANCH) - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm7 - -/* 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 + vmovaps %zmm0, %zmm7 + vgetmantpd $8, {sae}, %zmm7, %zmm6 + vmovups One+__svml_dlog2_data_internal_avx512(%rip), %zmm2 + vmovups poly_coeff5+__svml_dlog2_data_internal_avx512(%rip), %zmm12 + vmovups poly_coeff3+__svml_dlog2_data_internal_avx512(%rip), %zmm13 + + /* Start polynomial evaluation */ + vmovups poly_coeff9+__svml_dlog2_data_internal_avx512(%rip), %zmm10 + vmovups poly_coeff8+__svml_dlog2_data_internal_avx512(%rip), %zmm0 + vmovups poly_coeff7+__svml_dlog2_data_internal_avx512(%rip), %zmm11 + vmovups poly_coeff6+__svml_dlog2_data_internal_avx512(%rip), %zmm14 + + /* Prepare exponent correction: DblRcp<0.75? */ + vmovups C075+__svml_dlog2_data_internal_avx512(%rip), %zmm1 + + /* Table lookup */ + vmovups __svml_dlog2_data_internal_avx512(%rip), %zmm4 + + /* GetExp(x) */ + vgetexppd {sae}, %zmm7, %zmm5 + + /* DblRcp ~ 1/Mantissa */ + vrcp14pd %zmm6, %zmm8 + + /* x<=0? */ + vfpclasspd $94, %zmm7, %k0 + + /* round DblRcp to 4 fractional bits (RN mode, no Precision exception) */ + vrndscalepd $88, {sae}, %zmm8, %zmm3 + vmovups poly_coeff4+__svml_dlog2_data_internal_avx512(%rip), %zmm8 + kmovw %k0, %edx + + /* Reduced argument: R = DblRcp*Mantissa - 1 */ + vfmsub213pd {rn-sae}, %zmm2, %zmm3, %zmm6 + vcmppd $17, {sae}, %zmm1, %zmm3, %k1 + vfmadd231pd {rn-sae}, %zmm6, %zmm12, %zmm8 + vmovups poly_coeff2+__svml_dlog2_data_internal_avx512(%rip), %zmm12 + vfmadd231pd {rn-sae}, %zmm6, %zmm10, %zmm0 + vfmadd231pd {rn-sae}, %zmm6, %zmm11, %zmm14 + vmovups poly_coeff1+__svml_dlog2_data_internal_avx512(%rip), %zmm1 + + /* R^2 */ + vmulpd {rn-sae}, %zmm6, %zmm6, %zmm15 + vfmadd231pd {rn-sae}, %zmm6, %zmm13, %zmm12 + + /* Prepare table index */ + vpsrlq $48, %zmm3, %zmm9 + + /* add 1 to Expon if DblRcp<0.75 */ + vaddpd {rn-sae}, %zmm2, %zmm5, %zmm5{%k1} + vmulpd {rn-sae}, %zmm15, %zmm15, %zmm13 + vfmadd213pd {rn-sae}, %zmm14, %zmm15, %zmm0 + vfmadd213pd {rn-sae}, %zmm12, %zmm15, %zmm8 + vpermt2pd Log_tbl+64+__svml_dlog2_data_internal_avx512(%rip), %zmm9, %zmm4 + + /* polynomial */ + vfmadd213pd {rn-sae}, %zmm8, %zmm13, %zmm0 + vfmadd213pd {rn-sae}, %zmm1, %zmm6, %zmm0 + vfmadd213pd {rn-sae}, %zmm4, %zmm0, %zmm6 + vaddpd {rn-sae}, %zmm6, %zmm5, %zmm0 + testl %edx, %edx + + /* Go to special inputs processing branch */ + jne L(SPECIAL_VALUES_BRANCH) + # LOE rbx r12 r13 r14 r15 edx zmm0 zmm7 + + /* 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 %zmm7, 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 %zmm7, 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 $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 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 $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 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 - movsd 64(%rsp,%r14,8), %xmm0 - call log2@PLT - # LOE rbx r14 r15 r12d r13d xmm0 + movl %r12d, %r14d + movsd 64(%rsp, %r14, 8), %xmm0 + call log2@PLT + # LOE rbx r14 r15 r12d r13d xmm0 - movsd %xmm0, 128(%rsp,%r14,8) + movsd %xmm0, 128(%rsp, %r14, 8) -/* 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(_ZGVeN8v_log2_skx) - .section .rodata, "a" - .align 64 + .section .rodata, "a" + .align 64 #ifdef __svml_dlog2_data_internal_avx512_typedef typedef unsigned int VUINT32; typedef struct { - __declspec(align(64)) VUINT32 Log_tbl[16][2]; - __declspec(align(64)) VUINT32 One[8][2]; - __declspec(align(64)) VUINT32 C075[8][2]; - __declspec(align(64)) VUINT32 poly_coeff9[8][2]; - __declspec(align(64)) VUINT32 poly_coeff8[8][2]; - __declspec(align(64)) VUINT32 poly_coeff7[8][2]; - __declspec(align(64)) VUINT32 poly_coeff6[8][2]; - __declspec(align(64)) VUINT32 poly_coeff5[8][2]; - __declspec(align(64)) VUINT32 poly_coeff4[8][2]; - __declspec(align(64)) VUINT32 poly_coeff3[8][2]; - __declspec(align(64)) VUINT32 poly_coeff2[8][2]; - __declspec(align(64)) VUINT32 poly_coeff1[8][2]; - } __svml_dlog2_data_internal_avx512; + __declspec(align(64)) VUINT32 Log_tbl[16][2]; + __declspec(align(64)) VUINT32 One[8][2]; + __declspec(align(64)) VUINT32 C075[8][2]; + __declspec(align(64)) VUINT32 poly_coeff9[8][2]; + __declspec(align(64)) VUINT32 poly_coeff8[8][2]; + __declspec(align(64)) VUINT32 poly_coeff7[8][2]; + __declspec(align(64)) VUINT32 poly_coeff6[8][2]; + __declspec(align(64)) VUINT32 poly_coeff5[8][2]; + __declspec(align(64)) VUINT32 poly_coeff4[8][2]; + __declspec(align(64)) VUINT32 poly_coeff3[8][2]; + __declspec(align(64)) VUINT32 poly_coeff2[8][2]; + __declspec(align(64)) VUINT32 poly_coeff1[8][2]; +} __svml_dlog2_data_internal_avx512; #endif __svml_dlog2_data_internal_avx512: - /*== Log_tbl ==*/ - .quad 0x0000000000000000 - .quad 0xbfb663f6fac91316 - .quad 0xbfc5c01a39fbd688 - .quad 0xbfcfbc16b902680a - .quad 0xbfd49a784bcd1b8b - .quad 0xbfd91bba891f1709 - .quad 0xbfdd6753e032ea0f - .quad 0xbfe0c10500d63aa6 - .quad 0x3fda8ff971810a5e - .quad 0x3fd6cb0f6865c8ea - .quad 0x3fd32bfee370ee68 - .quad 0x3fcf5fd8a9063e35 - .quad 0x3fc8a8980abfbd32 - .quad 0x3fc22dadc2ab3497 - .quad 0x3fb7d60496cfbb4c - .quad 0x3fa77394c9d958d5 - /*== One ==*/ - .align 64 - .quad 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000 - /*== C075 0.75 ==*/ - .align 64 - .quad 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000 - /*== poly_coeff9 ==*/ - .align 64 - .quad 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12 - /*== poly_coeff8 ==*/ - .align 64 - .quad 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce - /*== poly_coeff7 ==*/ - .align 64 - .quad 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613 - /*== poly_coeff6 ==*/ - .align 64 - .quad 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c - /*== poly_coeff5 ==*/ - .align 64 - .quad 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a - /*== poly_coeff4 ==*/ - .align 64 - .quad 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d - /*== poly_coeff3 ==*/ - .align 64 - .quad 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f - /*== poly_coeff2 ==*/ - .align 64 - .quad 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4 - /*== poly_coeff1 ==*/ - .align 64 - .quad 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe - .align 64 - .type __svml_dlog2_data_internal_avx512,@object - .size __svml_dlog2_data_internal_avx512,.-__svml_dlog2_data_internal_avx512 + /* Log_tbl */ + .quad 0x0000000000000000 + .quad 0xbfb663f6fac91316 + .quad 0xbfc5c01a39fbd688 + .quad 0xbfcfbc16b902680a + .quad 0xbfd49a784bcd1b8b + .quad 0xbfd91bba891f1709 + .quad 0xbfdd6753e032ea0f + .quad 0xbfe0c10500d63aa6 + .quad 0x3fda8ff971810a5e + .quad 0x3fd6cb0f6865c8ea + .quad 0x3fd32bfee370ee68 + .quad 0x3fcf5fd8a9063e35 + .quad 0x3fc8a8980abfbd32 + .quad 0x3fc22dadc2ab3497 + .quad 0x3fb7d60496cfbb4c + .quad 0x3fa77394c9d958d5 + /* One */ + .align 64 + .quad 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000 + /* C075 0.75 */ + .align 64 + .quad 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000, 0x3fe8000000000000 + /* poly_coeff9 */ + .align 64 + .quad 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12, 0x3fc4904bda0e1d12 + /* poly_coeff8 */ + .align 64 + .quad 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce, 0xbfc71fb84deb5cce + /* poly_coeff7 */ + .align 64 + .quad 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613, 0x3fca617351818613 + /* poly_coeff6 */ + .align 64 + .quad 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c, 0xbfcec707e4e3144c + /* poly_coeff5 */ + .align 64 + .quad 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a, 0x3fd2776c5114d91a + /* poly_coeff4 */ + .align 64 + .quad 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d, 0xbfd71547653d0f8d + /* poly_coeff3 */ + .align 64 + .quad 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f, 0x3fdec709dc3a029f + /* poly_coeff2 */ + .align 64 + .quad 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4, 0xbfe71547652b82d4 + /* poly_coeff1 */ + .align 64 + .quad 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe, 0x3ff71547652b82fe + .align 64 + .type __svml_dlog2_data_internal_avx512, @object + .size __svml_dlog2_data_internal_avx512, .-__svml_dlog2_data_internal_avx512