diff options
Diffstat (limited to 'sysdeps/x86_64/fpu')
-rw-r--r-- | sysdeps/x86_64/fpu/multiarch/svml_s_expm1f16_core_avx512.S | 443 |
1 files changed, 221 insertions, 222 deletions
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f16_core_avx512.S index caf23e10af..71d23e632c 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f16_core_avx512.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f16_core_avx512.S @@ -31,251 +31,250 @@ /* Offsets for data table __svml_sexpm1_data_internal_avx512 */ -#define Exp_tbl_H 0 -#define Exp_tbl_L 128 -#define L2E 256 -#define Shifter 320 -#define Threshold 384 -#define SgnMask 448 -#define L2H 512 -#define L2L 576 -#define EMask 640 -#define poly_coeff3 704 -#define poly_coeff2 768 -#define One 832 +#define Exp_tbl_H 0 +#define Exp_tbl_L 128 +#define L2E 256 +#define Shifter 320 +#define Threshold 384 +#define SgnMask 448 +#define L2H 512 +#define L2L 576 +#define EMask 640 +#define poly_coeff3 704 +#define poly_coeff2 768 +#define One 832 #include <sysdep.h> - .text - .section .text.exex512,"ax",@progbits + .section .text.exex512, "ax", @progbits ENTRY(_ZGVeN16v_expm1f_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 L2E+__svml_sexpm1_data_internal_avx512(%rip), %zmm5 - vmovups Shifter+__svml_sexpm1_data_internal_avx512(%rip), %zmm3 - vmovups L2H+__svml_sexpm1_data_internal_avx512(%rip), %zmm8 - vmovups L2L+__svml_sexpm1_data_internal_avx512(%rip), %zmm4 - vmovups __svml_sexpm1_data_internal_avx512(%rip), %zmm6 - -/* polynomial */ - vmovups poly_coeff3+__svml_sexpm1_data_internal_avx512(%rip), %zmm9 - vmovups poly_coeff2+__svml_sexpm1_data_internal_avx512(%rip), %zmm12 - vmovups Exp_tbl_L+__svml_sexpm1_data_internal_avx512(%rip), %zmm11 - vmovups Threshold+__svml_sexpm1_data_internal_avx512(%rip), %zmm2 - -/* Th - 1 */ - vmovups One+__svml_sexpm1_data_internal_avx512(%rip), %zmm14 - vmovaps %zmm0, %zmm1 - -/* 2^(52-5)*1.5 + x * log2(e) */ - vfmadd213ps {rn-sae}, %zmm3, %zmm1, %zmm5 - vcmpps $29, {sae}, %zmm2, %zmm1, %k0 - -/* Z0 ~ x*log2(e), rounded to 5 fractional bits */ - vsubps {rn-sae}, %zmm3, %zmm5, %zmm7 - vpermt2ps Exp_tbl_H+64+__svml_sexpm1_data_internal_avx512(%rip), %zmm5, %zmm6 - vpermt2ps Exp_tbl_L+64+__svml_sexpm1_data_internal_avx512(%rip), %zmm5, %zmm11 - vandps SgnMask+__svml_sexpm1_data_internal_avx512(%rip), %zmm1, %zmm0 - -/* R = x - Z0*log(2) */ - vfnmadd213ps {rn-sae}, %zmm1, %zmm7, %zmm8 - -/* scale Th */ - vscalefps {rn-sae}, %zmm7, %zmm6, %zmm2 - vfnmadd231ps {rn-sae}, %zmm7, %zmm4, %zmm8 - kmovw %k0, %edx - -/* ensure |R|<2 even for special cases */ - vandps EMask+__svml_sexpm1_data_internal_avx512(%rip), %zmm8, %zmm13 - vsubps {rn-sae}, %zmm14, %zmm2, %zmm8 - vmulps {rn-sae}, %zmm13, %zmm13, %zmm10 - vfmadd231ps {rn-sae}, %zmm13, %zmm9, %zmm12 - -/* Tlr + R+ R2*Poly */ - vfmadd213ps {rn-sae}, %zmm11, %zmm10, %zmm12 - vaddps {rn-sae}, %zmm13, %zmm12, %zmm15 - -/* (Th-1)+Th*(Tlr + R+ R*Poly) */ - vfmadd213ps {rn-sae}, %zmm8, %zmm15, %zmm2 - vorps %zmm0, %zmm2, %zmm0 - testl %edx, %edx - -/* Go to special inputs processing branch */ - jne L(SPECIAL_VALUES_BRANCH) - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm1 - -/* 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 L2E+__svml_sexpm1_data_internal_avx512(%rip), %zmm5 + vmovups Shifter+__svml_sexpm1_data_internal_avx512(%rip), %zmm3 + vmovups L2H+__svml_sexpm1_data_internal_avx512(%rip), %zmm8 + vmovups L2L+__svml_sexpm1_data_internal_avx512(%rip), %zmm4 + vmovups __svml_sexpm1_data_internal_avx512(%rip), %zmm6 + + /* polynomial */ + vmovups poly_coeff3+__svml_sexpm1_data_internal_avx512(%rip), %zmm9 + vmovups poly_coeff2+__svml_sexpm1_data_internal_avx512(%rip), %zmm12 + vmovups Exp_tbl_L+__svml_sexpm1_data_internal_avx512(%rip), %zmm11 + vmovups Threshold+__svml_sexpm1_data_internal_avx512(%rip), %zmm2 + + /* Th - 1 */ + vmovups One+__svml_sexpm1_data_internal_avx512(%rip), %zmm14 + vmovaps %zmm0, %zmm1 + + /* 2^(52-5)*1.5 + x * log2(e) */ + vfmadd213ps {rn-sae}, %zmm3, %zmm1, %zmm5 + vcmpps $29, {sae}, %zmm2, %zmm1, %k0 + + /* Z0 ~ x*log2(e), rounded to 5 fractional bits */ + vsubps {rn-sae}, %zmm3, %zmm5, %zmm7 + vpermt2ps Exp_tbl_H+64+__svml_sexpm1_data_internal_avx512(%rip), %zmm5, %zmm6 + vpermt2ps Exp_tbl_L+64+__svml_sexpm1_data_internal_avx512(%rip), %zmm5, %zmm11 + vandps SgnMask+__svml_sexpm1_data_internal_avx512(%rip), %zmm1, %zmm0 + + /* R = x - Z0*log(2) */ + vfnmadd213ps {rn-sae}, %zmm1, %zmm7, %zmm8 + + /* scale Th */ + vscalefps {rn-sae}, %zmm7, %zmm6, %zmm2 + vfnmadd231ps {rn-sae}, %zmm7, %zmm4, %zmm8 + kmovw %k0, %edx + + /* ensure |R|<2 even for special cases */ + vandps EMask+__svml_sexpm1_data_internal_avx512(%rip), %zmm8, %zmm13 + vsubps {rn-sae}, %zmm14, %zmm2, %zmm8 + vmulps {rn-sae}, %zmm13, %zmm13, %zmm10 + vfmadd231ps {rn-sae}, %zmm13, %zmm9, %zmm12 + + /* Tlr + R+ R2*Poly */ + vfmadd213ps {rn-sae}, %zmm11, %zmm10, %zmm12 + vaddps {rn-sae}, %zmm13, %zmm12, %zmm15 + + /* (Th-1)+Th*(Tlr + R+ R*Poly) */ + vfmadd213ps {rn-sae}, %zmm8, %zmm15, %zmm2 + vorps %zmm0, %zmm2, %zmm0 + testl %edx, %edx + + /* Go to special inputs processing branch */ + jne L(SPECIAL_VALUES_BRANCH) + # LOE rbx r12 r13 r14 r15 edx zmm0 zmm1 + + /* 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 %zmm1, 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 %zmm1, 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 expm1f@PLT - # LOE rbx r14 r15 r12d r13d xmm0 + movl %r12d, %r14d + movss 64(%rsp, %r14, 4), %xmm0 + call expm1f@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_expm1f_skx) - .section .rodata, "a" - .align 64 + .section .rodata, "a" + .align 64 #ifdef __svml_sexpm1_data_internal_avx512_typedef typedef unsigned int VUINT32; typedef struct { - __declspec(align(64)) VUINT32 Exp_tbl_H[32][1]; - __declspec(align(64)) VUINT32 Exp_tbl_L[32][1]; - __declspec(align(64)) VUINT32 L2E[16][1]; - __declspec(align(64)) VUINT32 Shifter[16][1]; - __declspec(align(64)) VUINT32 Threshold[16][1]; - __declspec(align(64)) VUINT32 SgnMask[16][1]; - __declspec(align(64)) VUINT32 L2H[16][1]; - __declspec(align(64)) VUINT32 L2L[16][1]; - __declspec(align(64)) VUINT32 EMask[16][1]; - __declspec(align(64)) VUINT32 poly_coeff3[16][1]; - __declspec(align(64)) VUINT32 poly_coeff2[16][1]; - __declspec(align(64)) VUINT32 One[16][1]; - } __svml_sexpm1_data_internal_avx512; + __declspec(align(64)) VUINT32 Exp_tbl_H[32][1]; + __declspec(align(64)) VUINT32 Exp_tbl_L[32][1]; + __declspec(align(64)) VUINT32 L2E[16][1]; + __declspec(align(64)) VUINT32 Shifter[16][1]; + __declspec(align(64)) VUINT32 Threshold[16][1]; + __declspec(align(64)) VUINT32 SgnMask[16][1]; + __declspec(align(64)) VUINT32 L2H[16][1]; + __declspec(align(64)) VUINT32 L2L[16][1]; + __declspec(align(64)) VUINT32 EMask[16][1]; + __declspec(align(64)) VUINT32 poly_coeff3[16][1]; + __declspec(align(64)) VUINT32 poly_coeff2[16][1]; + __declspec(align(64)) VUINT32 One[16][1]; +} __svml_sexpm1_data_internal_avx512; #endif __svml_sexpm1_data_internal_avx512: - /*== Exp_tbl_H ==*/ - .long 0x3f800000, 0x3f82cd87, 0x3f85aac3, 0x3f88980f - .long 0x3f8b95c2, 0x3f8ea43a, 0x3f91c3d3, 0x3f94f4f0 - .long 0x3f9837f0, 0x3f9b8d3a, 0x3f9ef532, 0x3fa27043 - .long 0x3fa5fed7, 0x3fa9a15b, 0x3fad583f, 0x3fb123f6 - .long 0x3fb504f3, 0x3fb8fbaf, 0x3fbd08a4, 0x3fc12c4d - .long 0x3fc5672a, 0x3fc9b9be, 0x3fce248c, 0x3fd2a81e - .long 0x3fd744fd, 0x3fdbfbb8, 0x3fe0ccdf, 0x3fe5b907 - .long 0x3feac0c7, 0x3fefe4ba, 0x3ff5257d, 0x3ffa83b3 - /*== Exp_tbl_L ==*/ - .align 64 - .long 0x00000000, 0xb34a3a0a, 0x3346cb6a, 0xb36ed17e - .long 0xb24e0611, 0xb3517dd9, 0x334b2482, 0xb31586de - .long 0x33092801, 0xb2e6f467, 0x331b85f2, 0x3099b6f1 - .long 0xb3051aa8, 0xb2e2a0da, 0xb2006c56, 0xb3365942 - .long 0x329302ae, 0x32c595dc, 0xb302e5a2, 0xb28e10a1 - .long 0x31b3d0e5, 0xb31a472b, 0x31d1daf2, 0xb305bf64 - .long 0xb27ce182, 0xb2f26443, 0xb1b4b0da, 0xb1da8a8f - .long 0xb1d290be, 0xb2d5b899, 0x31b0a147, 0xb2156afc - /*== log2(e) ==*/ - .align 64 - .long 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B - /*== Shifter=2^(23-5)*1.5 ==*/ - .align 64 - .long 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000 - /*== Threshold ==*/ - .align 64 - .long 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B - /*== Sgn ==*/ - .align 64 - .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000 - /*== L2H = log(2)_high ==*/ - .align 64 - .long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218 - /*== L2L = log(2)_low ==*/ - .align 64 - .long 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308 - /*== EMask ==*/ - .align 64 - .long 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff - /*== poly_coeff3 ==*/ - .align 64 - .long 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3 - /*== poly_coeff2 ==*/ - .align 64 - .long 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6 - /*== One ==*/ - .align 64 - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 - .align 64 - .type __svml_sexpm1_data_internal_avx512,@object - .size __svml_sexpm1_data_internal_avx512,.-__svml_sexpm1_data_internal_avx512 + /* Exp_tbl_H */ + .long 0x3f800000, 0x3f82cd87, 0x3f85aac3, 0x3f88980f + .long 0x3f8b95c2, 0x3f8ea43a, 0x3f91c3d3, 0x3f94f4f0 + .long 0x3f9837f0, 0x3f9b8d3a, 0x3f9ef532, 0x3fa27043 + .long 0x3fa5fed7, 0x3fa9a15b, 0x3fad583f, 0x3fb123f6 + .long 0x3fb504f3, 0x3fb8fbaf, 0x3fbd08a4, 0x3fc12c4d + .long 0x3fc5672a, 0x3fc9b9be, 0x3fce248c, 0x3fd2a81e + .long 0x3fd744fd, 0x3fdbfbb8, 0x3fe0ccdf, 0x3fe5b907 + .long 0x3feac0c7, 0x3fefe4ba, 0x3ff5257d, 0x3ffa83b3 + /* Exp_tbl_L */ + .align 64 + .long 0x00000000, 0xb34a3a0a, 0x3346cb6a, 0xb36ed17e + .long 0xb24e0611, 0xb3517dd9, 0x334b2482, 0xb31586de + .long 0x33092801, 0xb2e6f467, 0x331b85f2, 0x3099b6f1 + .long 0xb3051aa8, 0xb2e2a0da, 0xb2006c56, 0xb3365942 + .long 0x329302ae, 0x32c595dc, 0xb302e5a2, 0xb28e10a1 + .long 0x31b3d0e5, 0xb31a472b, 0x31d1daf2, 0xb305bf64 + .long 0xb27ce182, 0xb2f26443, 0xb1b4b0da, 0xb1da8a8f + .long 0xb1d290be, 0xb2d5b899, 0x31b0a147, 0xb2156afc + /* log2(e) */ + .align 64 + .long 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B, 0x3fB8AA3B + /* Shifter=2^(23-5)*1.5 */ + .align 64 + .long 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000, 0x48c00000 + /* Threshold */ + .align 64 + .long 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B + /* Sgn */ + .align 64 + .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000 + /* L2H = log(2)_high */ + .align 64 + .long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218 + /* L2L = log(2)_low */ + .align 64 + .long 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308, 0xb102e308 + /* EMask */ + .align 64 + .long 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff, 0xbfffffff + /* poly_coeff3 */ + .align 64 + .long 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3, 0x3e2AABF3 + /* poly_coeff2 */ + .align 64 + .long 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6, 0x3f0000F6 + /* One */ + .align 64 + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 + .align 64 + .type __svml_sexpm1_data_internal_avx512, @object + .size __svml_sexpm1_data_internal_avx512, .-__svml_sexpm1_data_internal_avx512 |