From 8f4d11aa4f9b67a970c2a951e0ac3cc135012e5f Mon Sep 17 00:00:00 2001 From: Sunil K Pandey Date: Mon, 7 Mar 2022 10:47:14 -0800 Subject: x86_64: Fix svml_s_log2f8_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 --- .../x86_64/fpu/multiarch/svml_s_log2f8_core_avx2.S | 335 ++++++++++----------- 1 file changed, 167 insertions(+), 168 deletions(-) (limited to 'sysdeps') 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 968f380..eaa5112 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 @@ -29,198 +29,197 @@ /* 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 MinNorm 0 +#define MaxNorm 32 +#define iBrkValue 64 +#define iOffExpoMask 96 +#define One 128 +#define sPoly 160 #include - .text - .section .text.avx2,"ax",@progbits + .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 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 - 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 - testl %edx, %edx - -/* 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 - */ + 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 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 + 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 + testl %edx, %edx + + /* 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) - -/* Branch to process - * special inputs - */ + 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) + + /* Branch to process + * special inputs + */ L(SPECIAL_VALUES_BRANCH): - vmovups %ymm0, 32(%rsp) - vmovups %ymm1, 64(%rsp) - # LOE rbx r12 r13 r14 r15 edx ymm1 - - 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 %ymm0, 32(%rsp) + vmovups %ymm1, 64(%rsp) + # LOE rbx r12 r13 r14 r15 edx ymm1 + + 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), %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 - */ + 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 - movss 32(%rsp,%r14,4), %xmm0 - call log2f@PLT - # LOE rbx r14 r15 r12d r13d xmm0 + movl %r12d, %r14d + movss 32(%rsp, %r14, 4), %xmm0 + call log2f@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_log2f_avx2) - .section .rodata, "a" - .align 32 + .section .rodata, "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]; + __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 + /* 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 -- cgit v1.1