diff options
author | Sunil K Pandey <skpgkp2@gmail.com> | 2022-03-07 10:47:09 -0800 |
---|---|---|
committer | Sunil K Pandey <skpgkp2@gmail.com> | 2022-03-07 21:14:09 -0800 |
commit | bb57b9d766f626ce052142a6f212fb122c5fb6b7 (patch) | |
tree | 5a63a7f595bb728ffcc607133a2b17bd543e6aef | |
parent | a3ed5cf2ab8a7399100a4aa23a484e44080b6278 (diff) | |
download | glibc-bb57b9d766f626ce052142a6f212fb122c5fb6b7.tar.gz glibc-bb57b9d766f626ce052142a6f212fb122c5fb6b7.tar.xz glibc-bb57b9d766f626ce052142a6f212fb122c5fb6b7.zip |
x86_64: Fix svml_d_asin8_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 <goldstein.w.n@gmail.com>
-rw-r--r-- | sysdeps/x86_64/fpu/multiarch/svml_d_asin8_core_avx512.S | 477 |
1 files changed, 238 insertions, 239 deletions
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_asin8_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_d_asin8_core_avx512.S index 2574d80cbd..0f5b773b04 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_d_asin8_core_avx512.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_d_asin8_core_avx512.S @@ -27,269 +27,268 @@ /* Offsets for data table __svml_dasin_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 sqrt_coeff_3 448 -#define sqrt_coeff_4 512 -#define poly_coeff_1 576 -#define poly_coeff_2 640 -#define poly_coeff_3 704 -#define poly_coeff_4 768 -#define poly_coeff_5 832 -#define poly_coeff_6 896 -#define poly_coeff_7 960 -#define poly_coeff_8 1024 -#define poly_coeff_9 1088 -#define poly_coeff_10 1152 -#define poly_coeff_11 1216 -#define poly_coeff_12 1280 -#define Pi2H 1344 +#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 sqrt_coeff_3 448 +#define sqrt_coeff_4 512 +#define poly_coeff_1 576 +#define poly_coeff_2 640 +#define poly_coeff_3 704 +#define poly_coeff_4 768 +#define poly_coeff_5 832 +#define poly_coeff_6 896 +#define poly_coeff_7 960 +#define poly_coeff_8 1024 +#define poly_coeff_9 1088 +#define poly_coeff_10 1152 +#define poly_coeff_11 1216 +#define poly_coeff_12 1280 +#define Pi2H 1344 #include <sysdep.h> - .text - .section .text.evex512,"ax",@progbits + .section .text.evex512, "ax", @progbits ENTRY(_ZGVeN8v_asin_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 OneHalf+__svml_dasin_data_internal(%rip), %zmm8 - -/* S ~ -2*sqrt(Y) */ - vmovups SmallNorm+__svml_dasin_data_internal(%rip), %zmm10 - vmovups Two+__svml_dasin_data_internal(%rip), %zmm14 - vmovups sqrt_coeff_1+__svml_dasin_data_internal(%rip), %zmm15 - vmovups sqrt_coeff_2+__svml_dasin_data_internal(%rip), %zmm2 - vmovups sqrt_coeff_3+__svml_dasin_data_internal(%rip), %zmm1 - vmovups One+__svml_dasin_data_internal(%rip), %zmm9 - vmovaps %zmm0, %zmm6 - -/* x = |arg| */ - vandpd __svml_dasin_data_internal(%rip), %zmm6, %zmm4 - -/* Y = 0.5 - 0.5*x */ - vmovaps %zmm8, %zmm11 - vfnmadd231pd {rn-sae}, %zmm4, %zmm8, %zmm11 - -/* x^2 */ - vmulpd {rn-sae}, %zmm4, %zmm4, %zmm7 - vrsqrt14pd %zmm11, %zmm12 - vcmppd $17, {sae}, %zmm10, %zmm11, %k1 - vcmppd $21, {sae}, %zmm8, %zmm4, %k2 - vcmppd $17, {sae}, %zmm4, %zmm9, %k0 - vmovups poly_coeff_5+__svml_dasin_data_internal(%rip), %zmm10 - -/* polynomial */ - vmovups poly_coeff_1+__svml_dasin_data_internal(%rip), %zmm8 - vmovups poly_coeff_3+__svml_dasin_data_internal(%rip), %zmm9 - vminpd {sae}, %zmm11, %zmm7, %zmm3 - vxorpd %zmm12, %zmm12, %zmm12{%k1} - vaddpd {rn-sae}, %zmm11, %zmm11, %zmm0 - vxorpd %zmm6, %zmm4, %zmm5 - vmulpd {rn-sae}, %zmm12, %zmm12, %zmm13 - vmulpd {rn-sae}, %zmm12, %zmm0, %zmm7 - vmovups poly_coeff_7+__svml_dasin_data_internal(%rip), %zmm11 - vmovups poly_coeff_4+__svml_dasin_data_internal(%rip), %zmm12 - vfmsub213pd {rn-sae}, %zmm14, %zmm13, %zmm0 - vmovups sqrt_coeff_4+__svml_dasin_data_internal(%rip), %zmm13 - vfmadd231pd {rn-sae}, %zmm3, %zmm9, %zmm12 - vmovups poly_coeff_11+__svml_dasin_data_internal(%rip), %zmm9 - vfmadd231pd {rn-sae}, %zmm0, %zmm15, %zmm2 - vmovups poly_coeff_9+__svml_dasin_data_internal(%rip), %zmm15 - vmulpd {rn-sae}, %zmm0, %zmm7, %zmm14 - vfmadd213pd {rn-sae}, %zmm1, %zmm0, %zmm2 - vmovups poly_coeff_2+__svml_dasin_data_internal(%rip), %zmm1 - kmovw %k0, %edx - vfmadd213pd {rn-sae}, %zmm13, %zmm0, %zmm2 - vfmadd231pd {rn-sae}, %zmm3, %zmm8, %zmm1 - vmovups poly_coeff_10+__svml_dasin_data_internal(%rip), %zmm8 - vmulpd {rn-sae}, %zmm3, %zmm3, %zmm0 - vfmsub213pd {rn-sae}, %zmm7, %zmm14, %zmm2 - vmovups poly_coeff_6+__svml_dasin_data_internal(%rip), %zmm7 - vfmadd231pd {rn-sae}, %zmm3, %zmm15, %zmm8 - vfmadd213pd {rn-sae}, %zmm12, %zmm0, %zmm1 - vblendmpd %zmm2, %zmm4, %zmm2{%k2} - vfmadd231pd {rn-sae}, %zmm3, %zmm10, %zmm7 - vmovups poly_coeff_8+__svml_dasin_data_internal(%rip), %zmm10 - vmovups Pi2H+__svml_dasin_data_internal(%rip), %zmm4 - vfmadd231pd {rn-sae}, %zmm3, %zmm11, %zmm10 - vmovups poly_coeff_12+__svml_dasin_data_internal(%rip), %zmm11 - vfmadd213pd {rn-sae}, %zmm10, %zmm0, %zmm7 - vfmadd231pd {rn-sae}, %zmm3, %zmm9, %zmm11 - vmulpd {rn-sae}, %zmm0, %zmm0, %zmm10 - vfmadd213pd {rn-sae}, %zmm7, %zmm10, %zmm1 - vfmadd213pd {rn-sae}, %zmm8, %zmm0, %zmm1 - vfmadd213pd {rn-sae}, %zmm11, %zmm0, %zmm1 - vmulpd {rn-sae}, %zmm3, %zmm1, %zmm3 - vfmadd213pd {rn-sae}, %zmm2, %zmm2, %zmm3 - vaddpd {rn-sae}, %zmm4, %zmm3, %zmm3{%k2} - vxorpd %zmm5, %zmm3, %zmm0 - testl %edx, %edx - -/* Go to special inputs processing branch */ - jne L(SPECIAL_VALUES_BRANCH) - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm6 - -/* 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 OneHalf+__svml_dasin_data_internal(%rip), %zmm8 + + /* S ~ -2*sqrt(Y) */ + vmovups SmallNorm+__svml_dasin_data_internal(%rip), %zmm10 + vmovups Two+__svml_dasin_data_internal(%rip), %zmm14 + vmovups sqrt_coeff_1+__svml_dasin_data_internal(%rip), %zmm15 + vmovups sqrt_coeff_2+__svml_dasin_data_internal(%rip), %zmm2 + vmovups sqrt_coeff_3+__svml_dasin_data_internal(%rip), %zmm1 + vmovups One+__svml_dasin_data_internal(%rip), %zmm9 + vmovaps %zmm0, %zmm6 + + /* x = |arg| */ + vandpd __svml_dasin_data_internal(%rip), %zmm6, %zmm4 + + /* Y = 0.5 - 0.5*x */ + vmovaps %zmm8, %zmm11 + vfnmadd231pd {rn-sae}, %zmm4, %zmm8, %zmm11 + + /* x^2 */ + vmulpd {rn-sae}, %zmm4, %zmm4, %zmm7 + vrsqrt14pd %zmm11, %zmm12 + vcmppd $17, {sae}, %zmm10, %zmm11, %k1 + vcmppd $21, {sae}, %zmm8, %zmm4, %k2 + vcmppd $17, {sae}, %zmm4, %zmm9, %k0 + vmovups poly_coeff_5+__svml_dasin_data_internal(%rip), %zmm10 + + /* polynomial */ + vmovups poly_coeff_1+__svml_dasin_data_internal(%rip), %zmm8 + vmovups poly_coeff_3+__svml_dasin_data_internal(%rip), %zmm9 + vminpd {sae}, %zmm11, %zmm7, %zmm3 + vxorpd %zmm12, %zmm12, %zmm12{%k1} + vaddpd {rn-sae}, %zmm11, %zmm11, %zmm0 + vxorpd %zmm6, %zmm4, %zmm5 + vmulpd {rn-sae}, %zmm12, %zmm12, %zmm13 + vmulpd {rn-sae}, %zmm12, %zmm0, %zmm7 + vmovups poly_coeff_7+__svml_dasin_data_internal(%rip), %zmm11 + vmovups poly_coeff_4+__svml_dasin_data_internal(%rip), %zmm12 + vfmsub213pd {rn-sae}, %zmm14, %zmm13, %zmm0 + vmovups sqrt_coeff_4+__svml_dasin_data_internal(%rip), %zmm13 + vfmadd231pd {rn-sae}, %zmm3, %zmm9, %zmm12 + vmovups poly_coeff_11+__svml_dasin_data_internal(%rip), %zmm9 + vfmadd231pd {rn-sae}, %zmm0, %zmm15, %zmm2 + vmovups poly_coeff_9+__svml_dasin_data_internal(%rip), %zmm15 + vmulpd {rn-sae}, %zmm0, %zmm7, %zmm14 + vfmadd213pd {rn-sae}, %zmm1, %zmm0, %zmm2 + vmovups poly_coeff_2+__svml_dasin_data_internal(%rip), %zmm1 + kmovw %k0, %edx + vfmadd213pd {rn-sae}, %zmm13, %zmm0, %zmm2 + vfmadd231pd {rn-sae}, %zmm3, %zmm8, %zmm1 + vmovups poly_coeff_10+__svml_dasin_data_internal(%rip), %zmm8 + vmulpd {rn-sae}, %zmm3, %zmm3, %zmm0 + vfmsub213pd {rn-sae}, %zmm7, %zmm14, %zmm2 + vmovups poly_coeff_6+__svml_dasin_data_internal(%rip), %zmm7 + vfmadd231pd {rn-sae}, %zmm3, %zmm15, %zmm8 + vfmadd213pd {rn-sae}, %zmm12, %zmm0, %zmm1 + vblendmpd %zmm2, %zmm4, %zmm2{%k2} + vfmadd231pd {rn-sae}, %zmm3, %zmm10, %zmm7 + vmovups poly_coeff_8+__svml_dasin_data_internal(%rip), %zmm10 + vmovups Pi2H+__svml_dasin_data_internal(%rip), %zmm4 + vfmadd231pd {rn-sae}, %zmm3, %zmm11, %zmm10 + vmovups poly_coeff_12+__svml_dasin_data_internal(%rip), %zmm11 + vfmadd213pd {rn-sae}, %zmm10, %zmm0, %zmm7 + vfmadd231pd {rn-sae}, %zmm3, %zmm9, %zmm11 + vmulpd {rn-sae}, %zmm0, %zmm0, %zmm10 + vfmadd213pd {rn-sae}, %zmm7, %zmm10, %zmm1 + vfmadd213pd {rn-sae}, %zmm8, %zmm0, %zmm1 + vfmadd213pd {rn-sae}, %zmm11, %zmm0, %zmm1 + vmulpd {rn-sae}, %zmm3, %zmm1, %zmm3 + vfmadd213pd {rn-sae}, %zmm2, %zmm2, %zmm3 + vaddpd {rn-sae}, %zmm4, %zmm3, %zmm3{%k2} + vxorpd %zmm5, %zmm3, %zmm0 + testl %edx, %edx + + /* Go to special inputs processing branch */ + jne L(SPECIAL_VALUES_BRANCH) + # LOE rbx r12 r13 r14 r15 edx zmm0 zmm6 + + /* 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 %zmm6, 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 %zmm6, 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 asin@PLT - # LOE rbx r14 r15 r12d r13d xmm0 + movl %r12d, %r14d + movsd 64(%rsp, %r14, 8), %xmm0 + call asin@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_asin_skx) - .section .rodata, "a" - .align 64 + .section .rodata, "a" + .align 64 #ifdef __svml_dasin_data_internal_typedef typedef unsigned int VUINT32; typedef struct { - __declspec(align(64)) VUINT32 AbsMask[8][2]; - __declspec(align(64)) VUINT32 OneHalf[8][2]; - __declspec(align(64)) VUINT32 SmallNorm[8][2]; - __declspec(align(64)) VUINT32 One[8][2]; - __declspec(align(64)) VUINT32 Two[8][2]; - __declspec(align(64)) VUINT32 sqrt_coeff[4][8][2]; - __declspec(align(64)) VUINT32 poly_coeff[12][8][2]; - __declspec(align(64)) VUINT32 Pi2H[8][2]; + __declspec(align(64)) VUINT32 AbsMask[8][2]; + __declspec(align(64)) VUINT32 OneHalf[8][2]; + __declspec(align(64)) VUINT32 SmallNorm[8][2]; + __declspec(align(64)) VUINT32 One[8][2]; + __declspec(align(64)) VUINT32 Two[8][2]; + __declspec(align(64)) VUINT32 sqrt_coeff[4][8][2]; + __declspec(align(64)) VUINT32 poly_coeff[12][8][2]; + __declspec(align(64)) VUINT32 Pi2H[8][2]; } __svml_dasin_data_internal; #endif __svml_dasin_data_internal: - /*== AbsMask ==*/ - .quad 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff - /*== OneHalf ==*/ - .align 64 - .quad 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000 - /*== SmallNorm ==*/ - .align 64 - .quad 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000 - /*== One ==*/ - .align 64 - .quad 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000 - /*== Two ==*/ - .align 64 - .quad 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000 - /*== sqrt_coeff[4] ==*/ - .align 64 - .quad 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3 /* sqrt_coeff4 */ - .quad 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D /* sqrt_coeff3 */ - .quad 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97 /* sqrt_coeff2 */ - .quad 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D /* sqrt_coeff1 */ - /*== poly_coeff[12] ==*/ - .align 64 - .quad 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909 /* poly_coeff12 */ - .quad 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED /* poly_coeff11 */ - .quad 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE /* poly_coeff10 */ - .quad 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5 /* poly_coeff9 */ - .quad 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6 /* poly_coeff8 */ - .quad 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57 /* poly_coeff7 */ - .quad 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E /* poly_coeff6 */ - .quad 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd /* poly_coeff5 */ - .quad 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE /* poly_coeff4 */ - .quad 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8 /* poly_coeff3 */ - .quad 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE /* poly_coeff2 */ - .quad 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C /* poly_coeff1 */ - /*== Pi2H ==*/ - .align 64 - .quad 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18 - .align 64 - .type __svml_dasin_data_internal,@object - .size __svml_dasin_data_internal,.-__svml_dasin_data_internal + /* AbsMask */ + .quad 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff + /* OneHalf */ + .align 64 + .quad 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000 + /* SmallNorm */ + .align 64 + .quad 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000 + /* One */ + .align 64 + .quad 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000, 0x3ff0000000000000 + /* Two */ + .align 64 + .quad 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000 + /* sqrt_coeff[4] */ + .align 64 + .quad 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3 /* sqrt_coeff4 */ + .quad 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D /* sqrt_coeff3 */ + .quad 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97 /* sqrt_coeff2 */ + .quad 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D /* sqrt_coeff1 */ + /* poly_coeff[12] */ + .align 64 + .quad 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909 /* poly_coeff12 */ + .quad 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED /* poly_coeff11 */ + .quad 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE /* poly_coeff10 */ + .quad 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5 /* poly_coeff9 */ + .quad 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6 /* poly_coeff8 */ + .quad 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57 /* poly_coeff7 */ + .quad 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E /* poly_coeff6 */ + .quad 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd /* poly_coeff5 */ + .quad 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE /* poly_coeff4 */ + .quad 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8 /* poly_coeff3 */ + .quad 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE /* poly_coeff2 */ + .quad 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C /* poly_coeff1 */ + /* Pi2H */ + .align 64 + .quad 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18 + .align 64 + .type __svml_dasin_data_internal, @object + .size __svml_dasin_data_internal, .-__svml_dasin_data_internal |