aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSunil K Pandey <skpgkp2@gmail.com>2022-03-07 10:47:12 -0800
committerSunil K Pandey <skpgkp2@gmail.com>2022-03-07 21:14:10 -0800
commit9f38eff64028f236826c269958382dd7b786254f (patch)
tree1f7c6bb211af9eb951bbfbaced5156883dd6b3b2
parentdaae8562387b20f6057fea1e484206416e9f8dd5 (diff)
downloadglibc-9f38eff64028f236826c269958382dd7b786254f.tar.xz
glibc-9f38eff64028f236826c269958382dd7b786254f.zip
x86_64: Fix svml_s_erfcf8_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 <goldstein.w.n@gmail.com>
-rw-r--r--sysdeps/x86_64/fpu/multiarch/svml_s_erfcf8_core_avx2.S1794
1 files changed, 896 insertions, 898 deletions
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_erfcf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_erfcf8_core_avx2.S
index ec459644f0..4cafc1bcd5 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_erfcf8_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_erfcf8_core_avx2.S
@@ -29,929 +29,927 @@
/* Offsets for data table __svml_serfc_data_internal
*/
-#define _erfc_tbl 0
-#define _AbsMask 5184
-#define _MaxThreshold 5216
-#define _SgnMask 5248
-#define _One 5280
-#define _SRound 5312
-#define _TwoM48 5344
-#define _poly1_0 5376
-#define _poly1_1 5408
-#define _poly3_0 5440
-#define _poly3_1 5472
-#define _poly1_2 5504
-#define _poly1_3 5536
-#define _UF_Threshold 5568
+#define _erfc_tbl 0
+#define _AbsMask 5184
+#define _MaxThreshold 5216
+#define _SgnMask 5248
+#define _One 5280
+#define _SRound 5312
+#define _TwoM48 5344
+#define _poly1_0 5376
+#define _poly1_1 5408
+#define _poly3_0 5440
+#define _poly3_1 5472
+#define _poly1_2 5504
+#define _poly1_3 5536
+#define _UF_Threshold 5568
/* Lookup bias for data table __svml_serfc_data_internal. */
-#define Table_Lookup_Bias -0x40000000
+#define Table_Lookup_Bias -0x40000000
#include <sysdep.h>
- .text
- .section .text.avx2,"ax",@progbits
+ .section .text.avx2, "ax", @progbits
ENTRY(_ZGVdN8v_erfcf_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
-
-/* vector gather: erfc_h(x0), (erfc_l(x0), 2/sqrt(pi)*exp(-x0^2)) */
- lea Table_Lookup_Bias+__svml_serfc_data_internal(%rip), %rax
- vmovaps %ymm0, %ymm6
- vmovups _SRound+__svml_serfc_data_internal(%rip), %ymm1
- vmovups _TwoM48+__svml_serfc_data_internal(%rip), %ymm10
- vmovups _One+__svml_serfc_data_internal(%rip), %ymm0
- vandps _AbsMask+__svml_serfc_data_internal(%rip), %ymm6, %ymm5
-
-/*
- * erfc(10.125) underflows to 0
- * can compute all results in the main path
- */
- vminps _MaxThreshold+__svml_serfc_data_internal(%rip), %ymm5, %ymm4
- vaddps %ymm1, %ymm4, %ymm8
- vmaxps %ymm10, %ymm4, %ymm2
- vsubps %ymm1, %ymm8, %ymm12
- vpslld $3, %ymm8, %ymm7
- vandps _SgnMask+__svml_serfc_data_internal(%rip), %ymm6, %ymm13
- vorps %ymm13, %ymm0, %ymm3
-
-/* 2.0 if x<0, 0.0 otherwise */
- vsubps %ymm3, %ymm0, %ymm5
- vsubps %ymm12, %ymm2, %ymm0
-
-/* Start polynomial evaluation */
- vmovups _poly1_0+__svml_serfc_data_internal(%rip), %ymm3
- vmovups _poly3_0+__svml_serfc_data_internal(%rip), %ymm2
- vmulps %ymm0, %ymm12, %ymm1
- vfmadd213ps _poly1_1+__svml_serfc_data_internal(%rip), %ymm1, %ymm3
- vfmadd213ps _poly3_1+__svml_serfc_data_internal(%rip), %ymm1, %ymm2
- vfmadd213ps _poly1_2+__svml_serfc_data_internal(%rip), %ymm1, %ymm3
-
-/* 2^(-64) with sign of input */
- vorps %ymm13, %ymm10, %ymm4
- vfmadd213ps _poly1_3+__svml_serfc_data_internal(%rip), %ymm1, %ymm3
- vextractf128 $1, %ymm7, %xmm12
- vmovd %xmm7, %edx
- vmovd %xmm12, %r8d
- vpextrd $1, %xmm7, %ecx
- vpextrd $2, %xmm7, %esi
- vpextrd $3, %xmm7, %edi
- vpextrd $1, %xmm12, %r9d
- vpextrd $2, %xmm12, %r10d
- vpextrd $3, %xmm12, %r11d
- movslq %edx, %rdx
- movslq %ecx, %rcx
- movslq %esi, %rsi
- movslq %edi, %rdi
- movslq %r8d, %r8
- movslq %r9d, %r9
- movslq %r10d, %r10
- movslq %r11d, %r11
- vmovq (%rax,%rdx), %xmm13
- vmovq (%rax,%rcx), %xmm11
- vmovq (%rax,%rsi), %xmm14
- vmovq (%rax,%rdi), %xmm15
- vmovq (%rax,%r8), %xmm7
- vmovq (%rax,%r9), %xmm8
- vmovq (%rax,%r10), %xmm9
- vmovq (%rax,%r11), %xmm10
- vunpcklps %xmm14, %xmm13, %xmm12
- vunpcklps %xmm15, %xmm11, %xmm11
- vunpcklps %xmm9, %xmm7, %xmm9
- vunpcklps %xmm10, %xmm8, %xmm14
- vinsertf128 $1, %xmm9, %ymm12, %ymm15
- vinsertf128 $1, %xmm14, %ymm11, %ymm7
- vunpcklps %ymm7, %ymm15, %ymm9
- vunpckhps %ymm7, %ymm15, %ymm8
-
-/* Diff^2 */
- vmulps %ymm0, %ymm0, %ymm15
-
-/* P3*D2 */
- vmulps %ymm15, %ymm2, %ymm2
-
-/* P1 = P1*T + P3*D2 */
- vfmadd213ps %ymm2, %ymm1, %ymm3
-
-/* Special arguments (for flags only) */
- vcmplt_oqps _UF_Threshold+__svml_serfc_data_internal(%rip), %ymm6, %ymm1
-
-/* EXP_X0H * (1+P1) */
- vfmadd213ps %ymm8, %ymm8, %ymm3
-
-/* erfc_high(x0) - Diff * (2/sqrt(pi)*exp(-x0^2))*(1+P1) */
- vfnmadd213ps %ymm9, %ymm3, %ymm0
-
-/* combine and get argument value range mask */
- vmovmskps %ymm1, %edx
- notl %edx
- movzbl %dl, %edx
- vfmadd213ps %ymm5, %ymm4, %ymm0
- testl %edx, %edx
-
-/* Go to special inputs processing branch */
- jne L(SPECIAL_VALUES_BRANCH)
- # LOE rbx r12 r13 r14 r15 edx ymm0 ymm6
-
-/* 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
+
+ /* vector gather: erfc_h(x0), (erfc_l(x0), 2/sqrt(pi)*exp(-x0^2)) */
+ lea Table_Lookup_Bias+__svml_serfc_data_internal(%rip), %rax
+ vmovaps %ymm0, %ymm6
+ vmovups _SRound+__svml_serfc_data_internal(%rip), %ymm1
+ vmovups _TwoM48+__svml_serfc_data_internal(%rip), %ymm10
+ vmovups _One+__svml_serfc_data_internal(%rip), %ymm0
+ vandps _AbsMask+__svml_serfc_data_internal(%rip), %ymm6, %ymm5
+
+ /*
+ * erfc(10.125) underflows to 0
+ * can compute all results in the main path
+ */
+ vminps _MaxThreshold+__svml_serfc_data_internal(%rip), %ymm5, %ymm4
+ vaddps %ymm1, %ymm4, %ymm8
+ vmaxps %ymm10, %ymm4, %ymm2
+ vsubps %ymm1, %ymm8, %ymm12
+ vpslld $3, %ymm8, %ymm7
+ vandps _SgnMask+__svml_serfc_data_internal(%rip), %ymm6, %ymm13
+ vorps %ymm13, %ymm0, %ymm3
+
+ /* 2.0 if x<0, 0.0 otherwise */
+ vsubps %ymm3, %ymm0, %ymm5
+ vsubps %ymm12, %ymm2, %ymm0
+
+ /* Start polynomial evaluation */
+ vmovups _poly1_0+__svml_serfc_data_internal(%rip), %ymm3
+ vmovups _poly3_0+__svml_serfc_data_internal(%rip), %ymm2
+ vmulps %ymm0, %ymm12, %ymm1
+ vfmadd213ps _poly1_1+__svml_serfc_data_internal(%rip), %ymm1, %ymm3
+ vfmadd213ps _poly3_1+__svml_serfc_data_internal(%rip), %ymm1, %ymm2
+ vfmadd213ps _poly1_2+__svml_serfc_data_internal(%rip), %ymm1, %ymm3
+
+ /* 2^(-64) with sign of input */
+ vorps %ymm13, %ymm10, %ymm4
+ vfmadd213ps _poly1_3+__svml_serfc_data_internal(%rip), %ymm1, %ymm3
+ vextractf128 $1, %ymm7, %xmm12
+ vmovd %xmm7, %edx
+ vmovd %xmm12, %r8d
+ vpextrd $1, %xmm7, %ecx
+ vpextrd $2, %xmm7, %esi
+ vpextrd $3, %xmm7, %edi
+ vpextrd $1, %xmm12, %r9d
+ vpextrd $2, %xmm12, %r10d
+ vpextrd $3, %xmm12, %r11d
+ movslq %edx, %rdx
+ movslq %ecx, %rcx
+ movslq %esi, %rsi
+ movslq %edi, %rdi
+ movslq %r8d, %r8
+ movslq %r9d, %r9
+ movslq %r10d, %r10
+ movslq %r11d, %r11
+ vmovq (%rax, %rdx), %xmm13
+ vmovq (%rax, %rcx), %xmm11
+ vmovq (%rax, %rsi), %xmm14
+ vmovq (%rax, %rdi), %xmm15
+ vmovq (%rax, %r8), %xmm7
+ vmovq (%rax, %r9), %xmm8
+ vmovq (%rax, %r10), %xmm9
+ vmovq (%rax, %r11), %xmm10
+ vunpcklps %xmm14, %xmm13, %xmm12
+ vunpcklps %xmm15, %xmm11, %xmm11
+ vunpcklps %xmm9, %xmm7, %xmm9
+ vunpcklps %xmm10, %xmm8, %xmm14
+ vinsertf128 $1, %xmm9, %ymm12, %ymm15
+ vinsertf128 $1, %xmm14, %ymm11, %ymm7
+ vunpcklps %ymm7, %ymm15, %ymm9
+ vunpckhps %ymm7, %ymm15, %ymm8
+
+ /* Diff^2 */
+ vmulps %ymm0, %ymm0, %ymm15
+
+ /* P3*D2 */
+ vmulps %ymm15, %ymm2, %ymm2
+
+ /* P1 = P1*T + P3*D2 */
+ vfmadd213ps %ymm2, %ymm1, %ymm3
+
+ /* Special arguments (for flags only) */
+ vcmplt_oqps _UF_Threshold+__svml_serfc_data_internal(%rip), %ymm6, %ymm1
+
+ /* EXP_X0H * (1+P1) */
+ vfmadd213ps %ymm8, %ymm8, %ymm3
+
+ /* erfc_high(x0) - Diff * (2/sqrt(pi)*exp(-x0^2))*(1+P1) */
+ vfnmadd213ps %ymm9, %ymm3, %ymm0
+
+ /* combine and get argument value range mask */
+ vmovmskps %ymm1, %edx
+ notl %edx
+ movzbl %dl, %edx
+ vfmadd213ps %ymm5, %ymm4, %ymm0
+ testl %edx, %edx
+
+ /* Go to special inputs processing branch */
+ jne L(SPECIAL_VALUES_BRANCH)
+ # LOE rbx r12 r13 r14 r15 edx ymm0 ymm6
+
+ /* 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 %ymm6, 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 %ymm6, 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 erfcf@PLT
- # LOE rbx r14 r15 r12d r13d xmm0
+ movl %r12d, %r14d
+ movss 32(%rsp, %r14, 4), %xmm0
+ call erfcf@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_erfcf_avx2)
- .section .rodata, "a"
- .align 32
+ .section .rodata, "a"
+ .align 32
#ifdef __svml_serfc_data_internal_typedef
typedef unsigned int VUINT32;
-typedef struct
-{
- __declspec(align(32)) VUINT32 _erfc_tbl[645*2][1];
- __declspec(align(32)) VUINT32 _AbsMask[8][1];
- __declspec(align(32)) VUINT32 _MaxThreshold[8][1];
- __declspec(align(32)) VUINT32 _SgnMask[8][1];
- __declspec(align(32)) VUINT32 _One[8][1];
- __declspec(align(32)) VUINT32 _SRound[8][1];
- __declspec(align(32)) VUINT32 _TwoM48[8][1];
- __declspec(align(32)) VUINT32 _poly1_0[8][1];
- __declspec(align(32)) VUINT32 _poly1_1[8][1];
- __declspec(align(32)) VUINT32 _poly3_0[8][1];
- __declspec(align(32)) VUINT32 _poly3_1[8][1];
- __declspec(align(32)) VUINT32 _poly1_2[8][1];
- __declspec(align(32)) VUINT32 _poly1_3[8][1];
- __declspec(align(32)) VUINT32 _UF_Threshold[8][1];
+typedef struct {
+ __declspec(align(32)) VUINT32 _erfc_tbl[645*2][1];
+ __declspec(align(32)) VUINT32 _AbsMask[8][1];
+ __declspec(align(32)) VUINT32 _MaxThreshold[8][1];
+ __declspec(align(32)) VUINT32 _SgnMask[8][1];
+ __declspec(align(32)) VUINT32 _One[8][1];
+ __declspec(align(32)) VUINT32 _SRound[8][1];
+ __declspec(align(32)) VUINT32 _TwoM48[8][1];
+ __declspec(align(32)) VUINT32 _poly1_0[8][1];
+ __declspec(align(32)) VUINT32 _poly1_1[8][1];
+ __declspec(align(32)) VUINT32 _poly3_0[8][1];
+ __declspec(align(32)) VUINT32 _poly3_1[8][1];
+ __declspec(align(32)) VUINT32 _poly1_2[8][1];
+ __declspec(align(32)) VUINT32 _poly1_3[8][1];
+ __declspec(align(32)) VUINT32 _UF_Threshold[8][1];
} __svml_serfc_data_internal;
#endif
__svml_serfc_data_internal:
- /*== _erfc_tbl ==*/
- .long 0x57800000, 0x57906ebb
- .long 0x577b7ca2, 0x579065b4
- .long 0x5776f9d5, 0x57904aa3
- .long 0x57727828, 0x57901d93
- .long 0x576df82b, 0x578fde94
- .long 0x57697a6e, 0x578f8dbd
- .long 0x5764ff7f, 0x578f2b2e
- .long 0x576087ea, 0x578eb70a
- .long 0x575c143d, 0x578e317d
- .long 0x5757a500, 0x578d9ab9
- .long 0x57533abf, 0x578cf2f5
- .long 0x574ed5fe, 0x578c3a6f
- .long 0x574a7744, 0x578b716c
- .long 0x57461f12, 0x578a9834
- .long 0x5741cdeb, 0x5789af18
- .long 0x573d844a, 0x5788b66c
- .long 0x573942ac, 0x5787ae8b
- .long 0x57350989, 0x578697d3
- .long 0x5730d956, 0x578572a8
- .long 0x572cb284, 0x57843f72
- .long 0x57289583, 0x5782fe9f
- .long 0x572482bd, 0x5781b0a0
- .long 0x57207a9b, 0x578055e8
- .long 0x571c7d80, 0x577ddddf
- .long 0x57188bcb, 0x577af867
- .long 0x5714a5da, 0x5777fc62
- .long 0x5710cc05, 0x5774ead4
- .long 0x570cfe9f, 0x5771c4c4
- .long 0x57093df9, 0x576e8b3e
- .long 0x57058a5e, 0x576b3f51
- .long 0x5701e415, 0x5767e20f
- .long 0x56fc96c6, 0x5764748e
- .long 0x56f5810a, 0x5760f7e5
- .long 0x56ee876d, 0x575d6d2d
- .long 0x56e7aa5a, 0x5759d57e
- .long 0x56e0ea35, 0x575631f4
- .long 0x56da4757, 0x575283a7
- .long 0x56d3c214, 0x574ecbb1
- .long 0x56cd5ab3, 0x574b0b28
- .long 0x56c71175, 0x57474323
- .long 0x56c0e692, 0x574374b5
- .long 0x56bada38, 0x573fa0ee
- .long 0x56b4ec8f, 0x573bc8dc
- .long 0x56af1db3, 0x5737ed89
- .long 0x56a96dbc, 0x57340ff9
- .long 0x56a3dcb7, 0x5730312e
- .long 0x569e6aaa, 0x572c5223
- .long 0x56991793, 0x572873cf
- .long 0x5693e369, 0x57249721
- .long 0x568ece1a, 0x5720bd06
- .long 0x5689d78f, 0x571ce661
- .long 0x5684ffa8, 0x5719140f
- .long 0x56804640, 0x571546e7
- .long 0x56775654, 0x57117fb9
- .long 0x566e5c65, 0x570dbf4c
- .long 0x56659e43, 0x570a0662
- .long 0x565d1b6d, 0x570655b1
- .long 0x5654d35d, 0x5702adeb
- .long 0x564cc57d, 0x56fe1f73
- .long 0x5644f12f, 0x56f6f777
- .long 0x563d55cc, 0x56efe513
- .long 0x5635f2a1, 0x56e8e968
- .long 0x562ec6f6, 0x56e20584
- .long 0x5627d207, 0x56db3a64
- .long 0x5621130b, 0x56d488f8
- .long 0x561a8931, 0x56cdf21c
- .long 0x561433a0, 0x56c7769b
- .long 0x560e117c, 0x56c11733
- .long 0x560821e1, 0x56bad48d
- .long 0x560263e5, 0x56b4af46
- .long 0x55f9ad39, 0x56aea7ea
- .long 0x55eef22b, 0x56a8bef3
- .long 0x55e494b6, 0x56a2f4ce
- .long 0x55da92eb, 0x569d49d9
- .long 0x55d0ead3, 0x5697be62
- .long 0x55c79a75, 0x569252aa
- .long 0x55be9fd3, 0x568d06e3
- .long 0x55b5f8ee, 0x5687db31
- .long 0x55ada3c2, 0x5682cfad
- .long 0x55a59e4c, 0x567bc8c2
- .long 0x559de68a, 0x56723298
- .long 0x55967a77, 0x5668dcc1
- .long 0x558f5812, 0x565fc70e
- .long 0x55887d5c, 0x5656f136
- .long 0x5581e856, 0x564e5adf
- .long 0x55772e0c, 0x56460399
- .long 0x556b0eeb, 0x563deae4
- .long 0x555f6f64, 0x5636102b
- .long 0x55544b9e, 0x562e72cb
- .long 0x55499fc8, 0x5627120f
- .long 0x553f681d, 0x561fed36
- .long 0x5535a0e6, 0x5619036e
- .long 0x552c4679, 0x561253dc
- .long 0x55235539, 0x560bdd96
- .long 0x551ac999, 0x56059fa9
- .long 0x5512a01c, 0x55ff3230
- .long 0x550ad554, 0x55f391b9
- .long 0x550365e5, 0x55e85bd0
- .long 0x54f89d02, 0x55dd8e4c
- .long 0x54eb17df, 0x55d326f3
- .long 0x54de360f, 0x55c92385
- .long 0x54d1f166, 0x55bf81b6
- .long 0x54c643dc, 0x55b63f32
- .long 0x54bb2790, 0x55ad59a1
- .long 0x54b096c5, 0x55a4cea4
- .long 0x54a68be5, 0x559c9bd9
- .long 0x549d0180, 0x5594bedd
- .long 0x5493f24c, 0x558d354b
- .long 0x548b5926, 0x5585fcbf
- .long 0x54833111, 0x557e25af
- .long 0x5476ea69, 0x5570ea68
- .long 0x546841c1, 0x556442f0
- .long 0x545a5f10, 0x55582a98
- .long 0x544d398b, 0x554c9cbd
- .long 0x5440c8ae, 0x554194c7
- .long 0x54350440, 0x55370e2c
- .long 0x5429e44f, 0x552d0474
- .long 0x541f612f, 0x55237336
- .long 0x5415737d, 0x551a561b
- .long 0x540c1417, 0x5511a8e1
- .long 0x54033c22, 0x5509675a
- .long 0x53f5ca07, 0x55018d6b
- .long 0x53e610c3, 0x54f42e22
- .long 0x53d74046, 0x54e600c0
- .long 0x53c94cd8, 0x54d88b05
- .long 0x53bc2b3a, 0x54cbc574
- .long 0x53afd0a5, 0x54bfa8c4
- .long 0x53a432c3, 0x54b42ddb
- .long 0x539947af, 0x54a94dcf
- .long 0x538f05f3, 0x549f01ec
- .long 0x5385647e, 0x549543ae
- .long 0x5378b557, 0x548c0cc2
- .long 0x5367c06a, 0x5483570a
- .long 0x5357da71, 0x54763931
- .long 0x5348f45f, 0x5466af65
- .long 0x533affda, 0x5458059c
- .long 0x532def39, 0x544a3127
- .long 0x5321b57a, 0x543d27b5
- .long 0x5316463d, 0x5430df57
- .long 0x530b95bd, 0x54254e7b
- .long 0x530198cc, 0x541a6bee
- .long 0x52f08999, 0x54102ed6
- .long 0x52df1f58, 0x54068eb5
- .long 0x52cedfb9, 0x53fb06c5
- .long 0x52bfb8a0, 0x53ea0a1d
- .long 0x52b198e5, 0x53da1876
- .long 0x52a4704e, 0x53cb237a
- .long 0x52982f7c, 0x53bd1d6f
- .long 0x528cc7eb, 0x53aff93b
- .long 0x52822be3, 0x53a3aa56
- .long 0x52709cde, 0x539824ce
- .long 0x525e46a9, 0x538d5d3c
- .long 0x524d3e18, 0x538348c6
- .long 0x523d6d6f, 0x5373ba24
- .long 0x522ec035, 0x53622096
- .long 0x52212321, 0x5351b22a
- .long 0x52148413, 0x53425d18
- .long 0x5208d1fc, 0x53341080
- .long 0x51fbf9ac, 0x5326bc5e
- .long 0x51e7eb29, 0x531a5183
- .long 0x51d55c2d, 0x530ec18c
- .long 0x51c43238, 0x5303feda
- .long 0x51b45472, 0x52f3f919
- .long 0x51a5ab93, 0x52e15ce8
- .long 0x519821ce, 0x52d0121b
- .long 0x518ba2bc, 0x52c002f8
- .long 0x51801b49, 0x52b11afe
- .long 0x516af33c, 0x52a346d7
- .long 0x51575a21, 0x5296744c
- .long 0x51454c24, 0x528a9237
- .long 0x5134ac3b, 0x527f20e7
- .long 0x51255f51, 0x526abfa9
- .long 0x51174c27, 0x5257e42f
- .long 0x510a5b3b, 0x524673af
- .long 0x50fced50, 0x52365507
- .long 0x50e7141d, 0x522770a1
- .long 0x50d304fc, 0x5219b066
- .long 0x50c09cb5, 0x520cffa3
- .long 0x50afba92, 0x52014af8
- .long 0x50a04037, 0x51ed0088
- .long 0x50921177, 0x51d91d2d
- .long 0x50851430, 0x51c6cc35
- .long 0x50726058, 0x51b5f011
- .long 0x505c9dfa, 0x51a66d2a
- .long 0x5048b7be, 0x519829c8
- .long 0x50368738, 0x518b0df2
- .long 0x5025e8e0, 0x517e06ab
- .long 0x5016bbdf, 0x5167ea53
- .long 0x5008e1df, 0x5153a034
-