From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 7852) id 901E53857416; Tue, 8 Mar 2022 06:12:50 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 901E53857416 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_s_log1pf8_core_avx2.S code formatting X-Act-Checkin: glibc X-Git-Author: Sunil K Pandey X-Git-Refname: refs/heads/master X-Git-Oldrev: 389464a23374e51063731c56fbf670531a06ff09 X-Git-Newrev: b44b6f4288a772816d8d92785e9106086d593172 Message-Id: <20220308061250.901E53857416@sourceware.org> Date: Tue, 8 Mar 2022 06:12:50 +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 06:12:50 -0000 https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=b44b6f4288a772816d8d92785e9106086d593172 commit b44b6f4288a772816d8d92785e9106086d593172 Author: Sunil K Pandey Date: Mon Mar 7 10:47:14 2022 -0800 x86_64: Fix svml_s_log1pf8_core_avx2.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_s_log1pf8_core_avx2.S | 391 ++++++++++----------- 1 file changed, 195 insertions(+), 196 deletions(-) diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_log1pf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_log1pf8_core_avx2.S index 9da828bce7..54d6a9a685 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_s_log1pf8_core_avx2.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_log1pf8_core_avx2.S @@ -19,7 +19,7 @@ /* * ALGORITHM DESCRIPTION: * - * 1+x = 2^k*(xh + xl) is computed in high-low parts; xh in [1,2) + * 1+x = 2^k*(xh + xl) is computed in high-low parts; xh in [1, 2) * Get short reciprocal approximation Rcp ~ 1/xh * R = (Rcp*xh - 1.0) + Rcp*xl * log1p(x) = k*log(2.0) - log(Rcp) + poly(R) @@ -30,225 +30,224 @@ /* Offsets for data table __svml_slog1p_data_internal */ -#define SgnMask 0 -#define sOne 32 -#define sPoly 64 -#define iHiDelta 320 -#define iLoRange 352 -#define iBrkValue 384 -#define iOffExpoMask 416 -#define sLn2 448 +#define SgnMask 0 +#define sOne 32 +#define sPoly 64 +#define iHiDelta 320 +#define iLoRange 352 +#define iBrkValue 384 +#define iOffExpoMask 416 +#define sLn2 448 #include - .text - .section .text.avx2,"ax",@progbits + .section .text.avx2, "ax", @progbits ENTRY(_ZGVdN8v_log1pf_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 - vmovups sOne+__svml_slog1p_data_internal(%rip), %ymm2 - -/* reduction: compute r,n */ - vmovups iBrkValue+__svml_slog1p_data_internal(%rip), %ymm13 - vmovups SgnMask+__svml_slog1p_data_internal(%rip), %ymm4 - vmovups iLoRange+__svml_slog1p_data_internal(%rip), %ymm8 - vmovaps %ymm0, %ymm3 - -/* compute 1+x as high, low parts */ - vmaxps %ymm3, %ymm2, %ymm5 - vminps %ymm3, %ymm2, %ymm6 - vaddps %ymm6, %ymm5, %ymm10 - vpsubd %ymm13, %ymm10, %ymm11 - -/* check argument value ranges */ - vpaddd iHiDelta+__svml_slog1p_data_internal(%rip), %ymm10, %ymm9 - vsubps %ymm10, %ymm5, %ymm7 - vpsrad $23, %ymm11, %ymm14 - vpand iOffExpoMask+__svml_slog1p_data_internal(%rip), %ymm11, %ymm12 - vpslld $23, %ymm14, %ymm15 - vcvtdq2ps %ymm14, %ymm0 - vpsubd %ymm15, %ymm2, %ymm14 - vandnps %ymm3, %ymm4, %ymm1 - vaddps %ymm7, %ymm6, %ymm4 - vpaddd %ymm13, %ymm12, %ymm6 - vmulps %ymm4, %ymm14, %ymm7 - -/* polynomial evaluation */ - vsubps %ymm2, %ymm6, %ymm2 - vpcmpgtd %ymm9, %ymm8, %ymm5 - vmovups sPoly+224+__svml_slog1p_data_internal(%rip), %ymm8 - vaddps %ymm2, %ymm7, %ymm9 - vfmadd213ps sPoly+192+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 - vfmadd213ps sPoly+160+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 - vfmadd213ps sPoly+128+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 - vfmadd213ps sPoly+96+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 - vfmadd213ps sPoly+64+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 - vfmadd213ps sPoly+32+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 - vfmadd213ps sPoly+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 - vmulps %ymm8, %ymm9, %ymm10 - vfmadd213ps %ymm9, %ymm9, %ymm10 - -/* final reconstruction */ - vfmadd132ps sLn2+__svml_slog1p_data_internal(%rip), %ymm10, %ymm0 - -/* combine and get argument value range mask */ - vmovmskps %ymm5, %edx - vorps %ymm1, %ymm0, %ymm0 - testl %edx, %edx - -/* Go to special inputs processing branch */ - jne L(SPECIAL_VALUES_BRANCH) - # LOE rbx r12 r13 r14 r15 edx ymm0 ymm3 - -/* 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 $-32, %rsp + subq $96, %rsp + vmovups sOne+__svml_slog1p_data_internal(%rip), %ymm2 + + /* reduction: compute r, n */ + vmovups iBrkValue+__svml_slog1p_data_internal(%rip), %ymm13 + vmovups SgnMask+__svml_slog1p_data_internal(%rip), %ymm4 + vmovups iLoRange+__svml_slog1p_data_internal(%rip), %ymm8 + vmovaps %ymm0, %ymm3 + + /* compute 1+x as high, low parts */ + vmaxps %ymm3, %ymm2, %ymm5 + vminps %ymm3, %ymm2, %ymm6 + vaddps %ymm6, %ymm5, %ymm10 + vpsubd %ymm13, %ymm10, %ymm11 + + /* check argument value ranges */ + vpaddd iHiDelta+__svml_slog1p_data_internal(%rip), %ymm10, %ymm9 + vsubps %ymm10, %ymm5, %ymm7 + vpsrad $23, %ymm11, %ymm14 + vpand iOffExpoMask+__svml_slog1p_data_internal(%rip), %ymm11, %ymm12 + vpslld $23, %ymm14, %ymm15 + vcvtdq2ps %ymm14, %ymm0 + vpsubd %ymm15, %ymm2, %ymm14 + vandnps %ymm3, %ymm4, %ymm1 + vaddps %ymm7, %ymm6, %ymm4 + vpaddd %ymm13, %ymm12, %ymm6 + vmulps %ymm4, %ymm14, %ymm7 + + /* polynomial evaluation */ + vsubps %ymm2, %ymm6, %ymm2 + vpcmpgtd %ymm9, %ymm8, %ymm5 + vmovups sPoly+224+__svml_slog1p_data_internal(%rip), %ymm8 + vaddps %ymm2, %ymm7, %ymm9 + vfmadd213ps sPoly+192+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 + vfmadd213ps sPoly+160+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 + vfmadd213ps sPoly+128+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 + vfmadd213ps sPoly+96+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 + vfmadd213ps sPoly+64+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 + vfmadd213ps sPoly+32+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 + vfmadd213ps sPoly+__svml_slog1p_data_internal(%rip), %ymm9, %ymm8 + vmulps %ymm8, %ymm9, %ymm10 + vfmadd213ps %ymm9, %ymm9, %ymm10 + + /* final reconstruction */ + vfmadd132ps sLn2+__svml_slog1p_data_internal(%rip), %ymm10, %ymm0 + + /* combine and get argument value range mask */ + vmovmskps %ymm5, %edx + vorps %ymm1, %ymm0, %ymm0 + testl %edx, %edx + + /* Go to special inputs processing branch */ + jne L(SPECIAL_VALUES_BRANCH) + # LOE rbx r12 r13 r14 r15 edx ymm0 ymm3 + + /* 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 %ymm3, 32(%rsp) - vmovups %ymm0, 64(%rsp) - # LOE rbx r12 r13 r14 r15 edx ymm0 - - 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: -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 - */ + vmovups %ymm3, 32(%rsp) + vmovups %ymm0, 64(%rsp) + # LOE rbx r12 r13 r14 r15 edx ymm0 + + 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: -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 + 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 64(%rsp), %ymm0 - -/* 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 ymm0 - -/* 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 64(%rsp), %ymm0 + + /* 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 ymm0 + + /* Scalar math fucntion call + * to process special input + */ L(SCALAR_MATH_CALL): - movl %r12d, %r14d - movss 32(%rsp,%r14,4), %xmm0 - call log1pf@PLT - # LOE rbx r14 r15 r12d r13d xmm0 + movl %r12d, %r14d + movss 32(%rsp, %r14, 4), %xmm0 + call log1pf@PLT + # LOE rbx r14 r15 r12d r13d xmm0 - movss %xmm0, 64(%rsp,%r14,4) + movss %xmm0, 64(%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(_ZGVdN8v_log1pf_avx2) - .section .rodata, "a" - .align 32 + .section .rodata, "a" + .align 32 #ifdef __svml_slog1p_data_internal_typedef typedef unsigned int VUINT32; typedef struct { - __declspec(align(32)) VUINT32 SgnMask[8][1]; - __declspec(align(32)) VUINT32 sOne[8][1]; - __declspec(align(32)) VUINT32 sPoly[8][8][1]; - __declspec(align(32)) VUINT32 iHiDelta[8][1]; - __declspec(align(32)) VUINT32 iLoRange[8][1]; - __declspec(align(32)) VUINT32 iBrkValue[8][1]; - __declspec(align(32)) VUINT32 iOffExpoMask[8][1]; - __declspec(align(32)) VUINT32 sLn2[8][1]; + __declspec(align(32)) VUINT32 SgnMask[8][1]; + __declspec(align(32)) VUINT32 sOne[8][1]; + __declspec(align(32)) VUINT32 sPoly[8][8][1]; + __declspec(align(32)) VUINT32 iHiDelta[8][1]; + __declspec(align(32)) VUINT32 iLoRange[8][1]; + __declspec(align(32)) VUINT32 iBrkValue[8][1]; + __declspec(align(32)) VUINT32 iOffExpoMask[8][1]; + __declspec(align(32)) VUINT32 sLn2[8][1]; } __svml_slog1p_data_internal; #endif __svml_slog1p_data_internal: - /*== SgnMask ==*/ - .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff - /*== sOne = SP 1.0 ==*/ - .align 32 - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 - /*== sPoly[] = SP polynomial ==*/ - .align 32 - .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */ - .long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */ - .long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */ - .long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */ - .long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */ - .long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */ - .long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */ - .long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */ - /*== iHiDelta = SP 80000000-7f000000 ==*/ - .align 32 - .long 0x01000000, 0x01000000, 0x01000000, 0x01000000, 0x01000000, 0x01000000, 0x01000000, 0x01000000 - /*== iLoRange = SP 00800000+iHiDelta ==*/ - .align 32 - .long 0x01800000, 0x01800000, 0x01800000, 0x01800000, 0x01800000, 0x01800000, 0x01800000, 0x01800000 - /*== 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 - /*== sLn2 = SP ln(2) ==*/ - .align 32 - .long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218 - .align 32 - .type __svml_slog1p_data_internal,@object - .size __svml_slog1p_data_internal,.-__svml_slog1p_data_internal + /* SgnMask */ + .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff + /* sOne = SP 1.0 */ + .align 32 + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 + /* sPoly[] = SP polynomial */ + .align 32 + .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */ + .long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */ + .long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */ + .long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */ + .long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */ + .long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */ + .long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */ + .long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */ + /* iHiDelta = SP 80000000-7f000000 */ + .align 32 + .long 0x01000000, 0x01000000, 0x01000000, 0x01000000, 0x01000000, 0x01000000, 0x01000000, 0x01000000 + /* iLoRange = SP 00800000+iHiDelta */ + .align 32 + .long 0x01800000, 0x01800000, 0x01800000, 0x01800000, 0x01800000, 0x01800000, 0x01800000, 0x01800000 + /* 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 + /* sLn2 = SP ln(2) */ + .align 32 + .long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218 + .align 32 + .type __svml_slog1p_data_internal, @object + .size __svml_slog1p_data_internal, .-__svml_slog1p_data_internal