diff options
Diffstat (limited to 'sysdeps/x86_64/fpu/multiarch')
6 files changed, 862 insertions, 14 deletions
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S b/sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S index d37275d7ab..6dfc61ee93 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S @@ -20,7 +20,7 @@ #include "svml_d_trig_data.h" .text -ENTRY (_ZGVbN2vvv_sincos_sse4) +ENTRY (_ZGVbN2vl8l8_sincos_sse4) /* ALGORITHM DESCRIPTION: @@ -311,4 +311,58 @@ ENTRY (_ZGVbN2vvv_sincos_sse4) movsd %xmm0, 256(%rsp,%r15) jmp .LBL_1_7 +END (_ZGVbN2vl8l8_sincos_sse4) +libmvec_hidden_def(_ZGVbN2vl8l8_sincos_sse4) + +/* vvv version implemented with wrapper to vl8l8 variant. */ +ENTRY (_ZGVbN2vvv_sincos_sse4) +#ifndef __ILP32__ + subq $72, %rsp + .cfi_def_cfa_offset 80 + movdqu %xmm1, 32(%rsp) + lea (%rsp), %rdi + movdqu %xmm2, 48(%rdi) + lea 16(%rsp), %rsi + call HIDDEN_JUMPTARGET(_ZGVbN2vl8l8_sincos_sse4) + movq 32(%rsp), %rdx + movq 48(%rsp), %rsi + movq 40(%rsp), %r8 + movq 56(%rsp), %r10 + movq (%rsp), %rax + movq 16(%rsp), %rcx + movq 8(%rsp), %rdi + movq 24(%rsp), %r9 + movq %rax, (%rdx) + movq %rcx, (%rsi) + movq %rdi, (%r8) + movq %r9, (%r10) + addq $72, %rsp + .cfi_def_cfa_offset 8 + ret +#else + subl $72, %esp + .cfi_def_cfa_offset 80 + leal 48(%rsp), %esi + movaps %xmm1, 16(%esp) + leal 32(%rsp), %edi + movaps %xmm2, (%esp) + call HIDDEN_JUMPTARGET(_ZGVbN2vl8l8_sincos_sse4) + movdqa 16(%esp), %xmm1 + movsd 32(%esp), %xmm0 + movq %xmm1, %rax + movdqa (%esp), %xmm2 + movsd %xmm0, (%eax) + movsd 40(%esp), %xmm0 + pextrd $1, %xmm1, %eax + movsd %xmm0, (%eax) + movsd 48(%esp), %xmm0 + movq %xmm2, %rax + movsd %xmm0, (%eax) + movsd 56(%esp), %xmm0 + pextrd $1, %xmm2, %eax + movsd %xmm0, (%eax) + addl $72, %esp + .cfi_def_cfa_offset 8 + ret +#endif END (_ZGVbN2vvv_sincos_sse4) diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S index 24b57f4e8c..12f60100fa 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S @@ -20,7 +20,7 @@ #include "svml_d_trig_data.h" .text -ENTRY (_ZGVdN4vvv_sincos_avx2) +ENTRY (_ZGVdN4vl8l8_sincos_avx2) /* ALGORITHM DESCRIPTION: @@ -274,4 +274,100 @@ ENTRY (_ZGVdN4vvv_sincos_avx2) vmovsd %xmm0, 384(%rsp,%r15) jmp .LBL_1_7 +END (_ZGVdN4vl8l8_sincos_avx2) +libmvec_hidden_def(_ZGVdN4vl8l8_sincos_avx2) + +/* vvv version implemented with wrapper to vl8l8 variant. */ +ENTRY (_ZGVdN4vvv_sincos_avx2) +#ifndef __ILP32__ + pushq %rbp + cfi_adjust_cfa_offset (8) + cfi_rel_offset (%rbp, 0) + movq %rsp, %rbp + cfi_def_cfa_register (%rbp) + andq $-32, %rsp + subq $128, %rsp + vmovdqu %ymm1, 64(%rsp) + lea (%rsp), %rdi + vmovdqu %ymm2, 96(%rdi) + lea 32(%rsp), %rsi + call HIDDEN_JUMPTARGET(_ZGVdN4vl8l8_sincos_avx2) + movq 64(%rsp), %rdx + movq 96(%rsp), %rsi + movq 72(%rsp), %r8 + movq 104(%rsp), %r10 + movq (%rsp), %rax + movq 32(%rsp), %rcx + movq 8(%rsp), %rdi + movq 40(%rsp), %r9 + movq %rax, (%rdx) + movq %rcx, (%rsi) + movq 80(%rsp), %rax + movq 112(%rsp), %rcx + movq %rdi, (%r8) + movq %r9, (%r10) + movq 88(%rsp), %rdi + movq 120(%rsp), %r9 + movq 16(%rsp), %r11 + movq 48(%rsp), %rdx + movq 24(%rsp), %rsi + movq 56(%rsp), %r8 + movq %r11, (%rax) + movq %rdx, (%rcx) + movq %rsi, (%rdi) + movq %r8, (%r9) + movq %rbp, %rsp + cfi_def_cfa_register (%rsp) + popq %rbp + cfi_adjust_cfa_offset (-8) + cfi_restore (%rbp) + ret +#else + leal 8(%rsp), %r10d + .cfi_def_cfa 10, 0 + andl $-32, %esp + pushq -8(%r10d) + pushq %rbp + .cfi_escape 0x10,0x6,0x2,0x76,0 + movl %esp, %ebp + pushq %r10 + .cfi_escape 0xf,0x3,0x76,0x78,0x6 + leal -48(%rbp), %esi + leal -80(%rbp), %edi + subl $104, %esp + vmovaps %xmm1, -96(%ebp) + vmovaps %xmm2, -112(%ebp) + call HIDDEN_JUMPTARGET(_ZGVdN4vl8l8_sincos_avx2) + movl -96(%ebp), %eax + vmovsd -80(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movl -92(%ebp), %eax + vmovsd -72(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movl -88(%ebp), %eax + vmovsd -64(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movl -84(%ebp), %eax + vmovsd -56(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movl -112(%ebp), %eax + vmovsd -48(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movl -108(%ebp), %eax + vmovsd -40(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movl -104(%ebp), %eax + vmovsd -32(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movl -100(%ebp), %eax + vmovsd -24(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + addl $104, %esp + popq %r10 + .cfi_def_cfa 10, 0 + popq %rbp + leal -8(%r10), %esp + .cfi_def_cfa 7, 8 + ret +#endif END (_ZGVdN4vvv_sincos_avx2) diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S index 1d9f426d37..12ffb0ce9f 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S @@ -36,9 +36,9 @@ sin(R), sin(R') are approximated by corresponding polynomial. */ .text -ENTRY (_ZGVeN8vvv_sincos_knl) +ENTRY (_ZGVeN8vl8l8_sincos_knl) #ifndef HAVE_AVX512_ASM_SUPPORT -WRAPPER_IMPL_AVX512_fFF _ZGVdN4vvv_sincos +WRAPPER_IMPL_AVX512_fFF _ZGVdN4vl8l8_sincos #else pushq %rbp cfi_adjust_cfa_offset (8) @@ -304,11 +304,12 @@ WRAPPER_IMPL_AVX512_fFF _ZGVdN4vvv_sincos jmp .LBL_1_7 #endif -END (_ZGVeN8vvv_sincos_knl) +END (_ZGVeN8vl8l8_sincos_knl) +libmvec_hidden_def(_ZGVeN8vl8l8_sincos_knl) -ENTRY (_ZGVeN8vvv_sincos_skx) +ENTRY (_ZGVeN8vl8l8_sincos_skx) #ifndef HAVE_AVX512_ASM_SUPPORT -WRAPPER_IMPL_AVX512_fFF _ZGVdN4vvv_sincos +WRAPPER_IMPL_AVX512_fFF _ZGVdN4vl8l8_sincos #else pushq %rbp cfi_adjust_cfa_offset (8) @@ -585,6 +586,175 @@ WRAPPER_IMPL_AVX512_fFF _ZGVdN4vvv_sincos jmp .LBL_2_7 #endif +END (_ZGVeN8vl8l8_sincos_skx) +libmvec_hidden_def(_ZGVeN8vl8l8_sincos_skx) + +/* Wrapper between vvv and vl8l8 vector variants. */ +.macro WRAPPER_AVX512_vvv_vl8l8 callee +#ifndef __ILP32__ + pushq %rbp + cfi_adjust_cfa_offset (8) + cfi_rel_offset (%rbp, 0) + movq %rsp, %rbp + cfi_def_cfa_register (%rbp) + andq $-64, %rsp + subq $256, %rsp + /* Encoding for vmovups %zmm1, 128(%rsp). */ + .byte 0x62 + .byte 0xf1 + .byte 0x7c + .byte 0x48 + .byte 0x11 + .byte 0x4c + .byte 0x24 + .byte 0x02 + lea (%rsp), %rdi + /* Encoding for vmovups %zmm2, 192(%rdi). */ + .byte 0x62 + .byte 0xf1 + .byte 0x7c + .byte 0x48 + .byte 0x11 + .byte 0x57 + .byte 0x03 + lea 64(%rsp), %rsi + call HIDDEN_JUMPTARGET(\callee) + movq 128(%rsp), %rdx + movq 136(%rsp), %rsi + movq 144(%rsp), %r8 + movq 152(%rsp), %r10 + movq (%rsp), %rax + movq 8(%rsp), %rcx + movq 16(%rsp), %rdi + movq 24(%rsp), %r9 + movq %rax, (%rdx) + movq %rcx, (%rsi) + movq 160(%rsp), %rax + movq 168(%rsp), %rcx + movq %rdi, (%r8) + movq %r9, (%r10) + movq 176(%rsp), %rdi + movq 184(%rsp), %r9 + movq 32(%rsp), %r11 + movq 40(%rsp), %rdx + movq 48(%rsp), %rsi + movq 56(%rsp), %r8 + movq %r11, (%rax) + movq %rdx, (%rcx) + movq 192(%rsp), %r11 + movq 200(%rsp), %rdx + movq %rsi, (%rdi) + movq %r8, (%r9) + movq 208(%rsp), %rsi + movq 216(%rsp), %r8 + movq 64(%rsp), %r10 + movq 72(%rsp), %rax + movq 80(%rsp), %rcx + movq 88(%rsp), %rdi + movq %r10, (%r11) + movq %rax, (%rdx) + movq 224(%rsp), %r10 + movq 232(%rsp), %rax + movq %rcx, (%rsi) + movq %rdi, (%r8) + movq 240(%rsp), %rcx + movq 248(%rsp), %rdi + movq 96(%rsp), %r9 + movq 104(%rsp), %r11 + movq 112(%rsp), %rdx + movq 120(%rsp), %rsi + movq %r9, (%r10) + movq %r11, (%rax) + movq %rdx, (%rcx) + movq %rsi, (%rdi) + movq %rbp, %rsp + cfi_def_cfa_register (%rsp) + popq %rbp + cfi_adjust_cfa_offset (-8) + cfi_restore (%rbp) + ret +#else + leal 8(%rsp), %r10d + .cfi_def_cfa 10, 0 + andl $-64, %esp + pushq -8(%r10d) + pushq %rbp + .cfi_escape 0x10,0x6,0x2,0x76,0 + movl %esp, %ebp + pushq %r10 + .cfi_escape 0xf,0x3,0x76,0x78,0x6 + leal -112(%rbp), %esi + leal -176(%rbp), %edi + subl $232, %esp + vmovdqa %ymm1, -208(%ebp) + vmovdqa %ymm2, -240(%ebp) + call HIDDEN_JUMPTARGET(\callee) + vmovdqa -208(%ebp), %xmm0 + vmovq %xmm0, %rax + vmovsd -176(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + shrq $32, %rax + vmovsd -168(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movq -200(%ebp), %rax + vmovsd -160(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + shrq $32, %rax + vmovsd -152(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movq -192(%ebp), %rax + vmovsd -144(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + shrq $32, %rax + vmovsd -136(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movq -184(%ebp), %rax + vmovsd -128(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + shrq $32, %rax + vmovsd -120(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + vmovdqa -240(%ebp), %xmm0 + vmovq %xmm0, %rax + vmovsd -112(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + shrq $32, %rax + vmovsd -104(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movq -232(%ebp), %rax + vmovsd -96(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + shrq $32, %rax + vmovsd -88(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movq -224(%ebp), %rax + vmovsd -80(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + shrq $32, %rax + vmovsd -72(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + movq -216(%ebp), %rax + vmovsd -64(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + shrq $32, %rax + vmovsd -56(%ebp), %xmm0 + vmovsd %xmm0, (%eax) + addl $232, %esp + popq %r10 + .cfi_def_cfa 10, 0 + popq %rbp + leal -8(%r10), %esp + .cfi_def_cfa 7, 8 + ret +#endif +.endm + +ENTRY (_ZGVeN8vvv_sincos_knl) +WRAPPER_AVX512_vvv_vl8l8 _ZGVeN8vl8l8_sincos_knl +END (_ZGVeN8vvv_sincos_knl) + +ENTRY (_ZGVeN8vvv_sincos_skx) +WRAPPER_AVX512_vvv_vl8l8 _ZGVeN8vl8l8_sincos_skx END (_ZGVeN8vvv_sincos_skx) .section .rodata, "a" diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S index e375de8970..7621e87581 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S @@ -49,9 +49,9 @@ R2 = XOR( RC, SC ). */ .text -ENTRY (_ZGVeN16vvv_sincosf_knl) +ENTRY (_ZGVeN16vl4l4_sincosf_knl) #ifndef HAVE_AVX512_ASM_SUPPORT -WRAPPER_IMPL_AVX512_fFF _ZGVdN8vvv_sincosf +WRAPPER_IMPL_AVX512_fFF _ZGVdN8vl4l4_sincosf #else pushq %rbp cfi_adjust_cfa_offset (8) @@ -267,9 +267,10 @@ WRAPPER_IMPL_AVX512_fFF _ZGVdN8vvv_sincosf vmovss %xmm0, 1280(%rsp,%r15,8) jmp .LBL_1_7 #endif -END (_ZGVeN16vvv_sincosf_knl) +END (_ZGVeN16vl4l4_sincosf_knl) +libmvec_hidden_def(_ZGVeN16vl4l4_sincosf_knl) -ENTRY (_ZGVeN16vvv_sincosf_skx) +ENTRY (_ZGVeN16vl4l4_sincosf_skx) #ifndef HAVE_AVX512_ASM_SUPPORT WRAPPER_IMPL_AVX512_fFF _ZGVdN8vvv_sincosf #else @@ -496,6 +497,307 @@ WRAPPER_IMPL_AVX512_fFF _ZGVdN8vvv_sincosf vmovss %xmm0, 1280(%rsp,%r15,8) jmp .LBL_2_7 #endif +END (_ZGVeN16vl4l4_sincosf_skx) +libmvec_hidden_def(_ZGVeN16vl4l4_sincosf_skx) + +/* Wrapper between vvv and vl4l4 vector variants. */ +.macro WRAPPER_AVX512_vvv_vl4l4 callee +#ifndef __ILP32__ + pushq %rbp + cfi_adjust_cfa_offset (8) + cfi_rel_offset (%rbp, 0) + movq %rsp, %rbp + cfi_def_cfa_register (%rbp) + andq $-64, %rsp + subq $384, %rsp + /* Encoding for vmovups %zmm1, 128(%rsp). */ + .byte 0x62 + .byte 0xf1 + .byte 0x7c + .byte 0x48 + .byte 0x11 + .byte 0x4c + .byte 0x24 + .byte 0x02 + lea (%rsp), %rdi + /* Encoding for vmovups %zmm2, 192(%rdi). */ + .byte 0x62 + .byte 0xf1 + .byte 0x7c + .byte 0x48 + .byte 0x11 + .byte 0x57 + .byte 0x03 + /* Encoding for vmovups %zmm3, 256(%rdi). */ + .byte 0x62 + .byte 0xf1 + .byte 0x7c + .byte 0x48 + .byte 0x11 + .byte 0x5f + .byte 0x04 + /* Encoding for vmovups %zmm4, 320(%rdi). */ + .byte 0x62 + .byte 0xf1 + .byte 0x7c + .byte 0x48 + .byte 0x11 + .byte 0x67 + .byte 0x05 + lea 64(%rsp), %rsi + call HIDDEN_JUMPTARGET(\callee) + movq 128(%rsp), %rdx + movq 136(%rsp), %rsi + movq 144(%rsp), %r8 + movq 152(%rsp), %r10 + movl (%rsp), %eax + movl 4(%rsp), %ecx + movl 8(%rsp), %edi + movl 12(%rsp), %r9d + movl %eax, (%rdx) + movl %ecx, (%rsi) + movq 160(%rsp), %rax + movq 168(%rsp), %rcx + movl %edi, (%r8) + movl %r9d, (%r10) + movq 176(%rsp), %rdi + movq 184(%rsp), %r9 + movl 16(%rsp), %r11d + movl 20(%rsp), %edx + movl 24(%rsp), %esi + movl 28(%rsp), %r8d + movl %r11d, (%rax) + movl %edx, (%rcx) + movq 192(%rsp), %r11 + movq 200(%rsp), %rdx + movl %esi, (%rdi) + movl %r8d, (%r9) + movq 208(%rsp), %rsi + movq 216(%rsp), %r8 + movl 32(%rsp), %r10d + movl 36(%rsp), %eax + movl 40(%rsp), %ecx + movl 44(%rsp), %edi + movl %r10d, (%r11) + movl %eax, (%rdx) + movq 224(%rsp), %r10 + movq 232(%rsp), %rax + movl %ecx, (%rsi) + movl %edi, (%r8) + movq 240(%rsp), %rcx + movq 248(%rsp), %rdi + movl 48(%rsp), %r9d + movl 52(%rsp), %r11d + movl 56(%rsp), %edx + movl 60(%rsp), %esi + movl %r9d, (%r10) + movl %r11d, (%rax) + movq 256(%rsp), %r9 + movq 264(%rsp), %r11 + movl %edx, (%rcx) + movl %esi, (%rdi) + movq 272(%rsp), %rdx + movq 280(%rsp), %rsi + movl 64(%rsp), %r8d + movl 68(%rsp), %r10d + movl 72(%rsp), %eax + movl 76(%rsp), %ecx + movl %r8d, (%r9) + movl %r10d, (%r11) + movq 288(%rsp), %r8 + movq 296(%rsp), %r10 + movl %eax, (%rdx) + movl %ecx, (%rsi) + movq 304(%rsp), %rax + movq 312(%rsp), %rcx + movl 80(%rsp), %edi + movl 84(%rsp), %r9d + movl 88(%rsp), %r11d + movl 92(%rsp), %edx + movl %edi, (%r8) + movl %r9d, (%r10) + movq 320(%rsp), %rdi + movq 328(%rsp), %r9 + movl %r11d, (%rax) + movl %edx, (%rcx) + movq 336(%rsp), %r11 + movq 344(%rsp), %rdx + movl 96(%rsp), %esi + movl 100(%rsp), %r8d + movl 104(%rsp), %r10d + movl 108(%rsp), %eax + movl %esi, (%rdi) + movl %r8d, (%r9) + movq 352(%rsp), %rsi + movq 360(%rsp), %r8 + movl %r10d, (%r11) + movl %eax, (%rdx) + movq 368(%rsp), %r10 + movq 376(%rsp), %rax + movl 112(%rsp), %ecx + movl 116(%rsp), %edi + movl 120(%rsp), %r9d + movl 124(%rsp), %r11d + movl %ecx, (%rsi) + movl %edi, (%r8) + movl %r9d, (%r10) + movl %r11d, (%rax) + movq %rbp, %rsp + cfi_def_cfa_register (%rsp) + popq %rbp + cfi_adjust_cfa_offset (-8) + cfi_restore (%rbp) + ret +#else + leal 8(%rsp), %r10d + .cfi_def_cfa 10, 0 + andl $-64, %esp + pushq -8(%r10d) + pushq %rbp + .cfi_escape 0x10,0x6,0x2,0x76,0 + movl %esp, %ebp + pushq %r10 + .cfi_escape 0xf,0x3,0x76,0x78,0x6 + leal -112(%rbp), %esi + leal -176(%rbp), %edi + subl $296, %esp + /* Encoding for vmovdqa64 %zmm1, -240(%ebp). */ + .byte 0x67 + .byte 0x62 + .byte 0xf1 + .byte 0xfd + .byte 0x48 + .byte 0x7f + .byte 0x8d + .byte 0x10 + .byte 0xff + .byte 0xff + .byte 0xff + /* Encoding for vmovdqa64 %zmm2, -304(%ebp). */ + .byte 0x67 + .byte 0x62 + .byte 0xf1 + .byte 0xfd + .byte 0x48 + .byte 0x7f + .byte 0x95 + .byte 0xd0 + .byte 0xfe + .byte 0xff + .byte 0xff + call HIDDEN_JUMPTARGET(\callee) + movl -240(%ebp), %eax + vmovss -176(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -236(%ebp), %eax + vmovss -172(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -232(%ebp), %eax + vmovss -168(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -228(%ebp), %eax + vmovss -164(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -224(%ebp), %eax + vmovss -160(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -220(%ebp), %eax + vmovss -156(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -216(%ebp), %eax + vmovss -152(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -212(%ebp), %eax + vmovss -148(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -208(%ebp), %eax + vmovss -144(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -204(%ebp), %eax + vmovss -140(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -200(%ebp), %eax + vmovss -136(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -196(%ebp), %eax + vmovss -132(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -192(%ebp), %eax + vmovss -128(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -188(%ebp), %eax + vmovss -124(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -184(%ebp), %eax + vmovss -120(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -180(%ebp), %eax + vmovss -116(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -304(%ebp), %eax + vmovss -112(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -300(%ebp), %eax + vmovss -108(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -296(%ebp), %eax + vmovss -104(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -292(%ebp), %eax + vmovss -100(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -288(%ebp), %eax + vmovss -96(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -284(%ebp), %eax + vmovss -92(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -280(%ebp), %eax + vmovss -88(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -276(%ebp), %eax + vmovss -84(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -272(%ebp), %eax + vmovss -80(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -268(%ebp), %eax + vmovss -76(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -264(%ebp), %eax + vmovss -72(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -260(%ebp), %eax + vmovss -68(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -256(%ebp), %eax + vmovss -64(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -252(%ebp), %eax + vmovss -60(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -248(%ebp), %eax + vmovss -56(%ebp), %xmm0 + vmovss %xmm0, (%eax) + movl -244(%ebp), %eax + vmovss -52(%ebp), %xmm0 + vmovss %xmm0, (%eax) + addl $296, %esp + popq %r10 + .cfi_def_cfa 10, 0 + popq %rbp + leal -8(%r10), %esp + .cfi_def_cfa 7, 8 + ret +#endif +.endm + +ENTRY (_ZGVeN16vvv_sincosf_knl) +WRAPPER_AVX512_vvv_vl4l4 _ZGVeN16vl4l4_sincosf_knl +END (_ZGVeN16vvv_sincosf_knl) + +ENTRY (_ZGVeN16vvv_sincosf_skx) +WRAPPER_AVX512_vvv_vl4l4 _ZGVeN16vl4l4_sincosf_skx END (_ZGVeN16vvv_sincosf_skx) .section .rodata, "a" diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S index 562367b136..5e8ea8bf76 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S @@ -20,7 +20,7 @@ #include "svml_s_trig_data.h" .text -ENTRY (_ZGVbN4vvv_sincosf_sse4) +ENTRY (_ZGVbN4vl4l4_sincosf_sse4) /* ALGORITHM DESCRIPTION: @@ -265,4 +265,82 @@ ENTRY (_ZGVbN4vvv_sincosf_sse4) movss %xmm0, 256(%rsp,%r15,8) jmp .LBL_1_7 +END (_ZGVbN4vl4l4_sincosf_sse4) +libmvec_hidden_def(_ZGVbN4vl4l4_sincosf_sse4) + +/* vvv version implemented with wrapper to vl4l4 variant. */ +ENTRY (_ZGVbN4vvv_sincosf_sse4) +#ifndef __ILP32__ + subq $104, %rsp + .cfi_def_cfa_offset 112 + movdqu %xmm1, 32(%rsp) + lea (%rsp), %rdi + movdqu %xmm2, 48(%rdi) + lea 16(%rsp), %rsi + movdqu %xmm3, 48(%rsi) + movdqu %xmm4, 64(%rsi) + call HIDDEN_JUMPTARGET(_ZGVbN4vl4l4_sincosf_sse4) + movq 32(%rsp), %rdx + movq 40(%rsp), %rsi + movq 48(%rsp), %r8 + movq 56(%rsp), %r10 + movl (%rsp), %eax + movl 4(%rsp), %ecx + movl 8(%rsp), %edi + movl 12(%rsp), %r9d + movl %eax, (%rdx) + movl %ecx, (%rsi) + movq 64(%rsp), %rax + movq 72(%rsp), %rcx + movl %edi, (%r8) + movl %r9d, (%r10) + movq 80(%rsp), %rdi + movq 88(%rsp), %r9 + movl 16(%rsp), %r11d + movl 20(%rsp), %edx + movl 24(%rsp), %esi + movl 28(%rsp), %r8d + movl %r11d, (%rax) + movl %edx, (%rcx) + movl %esi, (%rdi) + movl %r8d, (%r9) + addq $104, %rsp + .cfi_def_cfa_offset 8 + ret +#else + subl $72, %esp + .cfi_def_cfa_offset 80 + leal 48(%rsp), %esi + movaps %xmm1, 16(%esp) + leal 32(%rsp), %edi + movaps %xmm2, (%esp) + call HIDDEN_JUMPTARGET(_ZGVbN4vl4l4_sincosf_sse4) + movl 16(%esp), %eax + movss 32(%esp), %xmm0 + movss %xmm0, (%eax) + movl 20(%esp), %eax + movss 36(%esp), %xmm0 + movss %xmm0, (%eax) + movl 24(%esp), %eax + movss 40(%esp), %xmm0 + movss %xmm0, (%eax) + movl 28(%esp), %eax + movss 44(%esp), %xmm0 + movss %xmm0, (%eax) + movl (%esp), %eax + movss 48(%esp), %xmm0 + movss %xmm0, (%eax) + movl 4(%esp), %eax + movss 52(%esp), %xmm0 + movss %xmm0, (%eax) + movl 8(%esp), %eax + movss 56(%esp), %xmm0 + movss %xmm0, (%eax) + movl 12(%esp), %eax + movss 60(%esp), %xmm0 + movss %xmm0, (%eax) + addl $72, %esp + .cfi_def_cfa_offset 8 + ret +#endif END (_ZGVbN4vvv_sincosf_sse4) diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S index baf887dd0a..75c28d1daa 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S @@ -20,7 +20,7 @@ #include "svml_s_trig_data.h" .text -ENTRY(_ZGVdN8vvv_sincosf_avx2) +ENTRY (_ZGVdN8vl4l4_sincosf_avx2) /* ALGORITHM DESCRIPTION: @@ -238,4 +238,152 @@ ENTRY(_ZGVdN8vvv_sincosf_avx2) vmovss %xmm0, 384(%rsp,%r15,8) jmp .LBL_1_7 -END(_ZGVdN8vvv_sincosf_avx2) +END (_ZGVdN8vl4l4_sincosf_avx2) +libmvec_hidden_def(_ZGVdN8vl4l4_sincosf_avx2) + +/* vvv version implemented with wrapper to vl4l4 variant. */ +ENTRY (_ZGVdN8vvv_sincosf_avx2) +#ifndef __ILP32__ + pushq %rbp + cfi_adjust_cfa_offset (8) + cfi_rel_offset (%rbp, 0) + movq %rsp, %rbp + cfi_def_cfa_register (%rbp) + andq $-32, %rsp + subq $192, %rsp + vmovdqu %ymm1, 64(%rsp) + lea (%rsp), %rdi + vmovdqu %ymm2, 96(%rdi) + vmovdqu %ymm3, 128(%rdi) + vmovdqu %ymm4, 160(%rdi) + lea 32(%rsp), %rsi + call HIDDEN_JUMPTARGET(_ZGVdN8vl4l4_sincosf_avx2) + movq 64(%rsp), %rdx + movq 72(%rsp), %rsi + movq 80(%rsp), %r8 + movq 88(%rsp), %r10 + movl (%rsp), %eax + movl 4(%rsp), %ecx + movl 8(%rsp), %edi + movl 12(%rsp), %r9d + movl %eax, (%rdx) + movl %ecx, (%rsi) + movq 96(%rsp), %rax + movq 104(%rsp), %rcx + movl %edi, (%r8) + movl %r9d, (%r10) + movq 112(%rsp), %rdi + movq 120(%rsp), %r9 + movl 16(%rsp), %r11d + movl 20(%rsp), %edx + movl 24(%rsp), %esi + movl 28(%rsp), %r8d + movl %r11d, (%rax) + movl %edx, (%rcx) + movq 128(%rsp), %r11 + movq 136(%rsp), %rdx + movl %esi, (%rdi) + movl %r8d, (%r9) + movq 144(%rsp), %rsi + movq 152(%rsp), %r8 + movl 32(%rsp), %r10d + movl 36(%rsp), %eax + movl 40(%rsp), %ecx + movl 44(%rsp), %edi + movl %r10d, (%r11) + movl %eax, (%rdx) + movq 160(%rsp), %r10 + movq 168(%rsp), %rax + movl %ecx, (%rsi) + movl %edi, (%r8) + movq 176(%rsp), %rcx + movq 184(%rsp), %rdi + movl 48(%rsp), %r9d + movl 52(%rsp), %r11d + movl 56(%rsp), %edx + movl 60(%rsp), %esi + movl %r9d, (%r10) + movl %r11d, (%rax) + movl %edx, (%rcx) + movl %esi, (%rdi) + movq %rbp, %rsp + cfi_def_cfa_register (%rsp) + popq %rbp + cfi_adjust_cfa_offset (-8) + cfi_restore (%rbp) + ret +#else + leal 8(%rsp), %r10d + .cfi_def_cfa 10, 0 + andl $-32, %esp + pushq -8(%r10d) + pushq %rbp + .cfi_escape 0x10,0x6,0x2,0x76,0 + movl %esp, %ebp + pushq %r10 + .cfi_escape 0xf,0x3,0x76,0x78,0x6 + leal -48(%rbp), %esi + leal -80(%rbp), %edi + subl $136, %esp + vmovdqa %ymm1, -112(%ebp) + vmovdqa %ymm2, -144(%ebp) + call HIDDEN_JUMPTARGET(_ZGVdN8vl4l4_sincosf_avx2) + vmovdqa -112(%ebp), %xmm0 + vmovq %xmm0, %rax + vmovss -80(%ebp), %xmm0 + vmovss %xmm0, (%eax) + vmovss -76(%ebp), %xmm0 + shrq $32, %rax + vmovss %xmm0, (%eax) + movq -104(%ebp), %rax + vmovss -72(%ebp), %xmm0 + vmovss %xmm0, (%eax) + vmovss -68(%ebp), %xmm0 + shrq $32, %rax + vmovss %xmm0, (%eax) + movq -96(%ebp), %rax + vmovss -64(%ebp), %xmm0 + vmovss %xmm0, (%eax) + vmovss -60(%ebp), %xmm0 + shrq $32, %rax + vmovss %xmm0, (%eax) + movq -88(%ebp), %rax + vmovss -56(%ebp), %xmm0 + vmovss %xmm0, (%eax) + vmovss -52(%ebp), %xmm0 + shrq $32, %rax + vmovss %xmm0, (%eax) + vmovdqa -144(%ebp), %xmm0 + vmovq %xmm0, %rax + vmovss -48(%ebp), %xmm0 + vmovss %xmm0, (%eax) + vmovss -44(%ebp), %xmm0 + shrq $32, %rax + vmovss %xmm0, (%eax) + movq -136(%ebp), %rax + vmovss -40(%ebp), %xmm0 + vmovss %xmm0, (%eax) + vmovss -36(%ebp), %xmm0 + shrq $32, %rax + vmovss %xmm0, (%eax) + movq -128(%ebp), %rax + vmovss -32(%ebp), %xmm0 + vmovss %xmm0, (%eax) + vmovss -28(%ebp), %xmm0 + shrq $32, %rax + vmovss %xmm0, (%eax) + movq -120(%ebp), %rax + vmovss -24(%ebp), %xmm0 + vmovss %xmm0, (%eax) + vmovss -20(%ebp), %xmm0 + shrq $32, %rax + vmovss %xmm0, (%eax) + addl $136, %esp + popq %r10 + .cfi_def_cfa 10, 0 + popq %rbp + leal -8(%r10), %esp + .cfi_def_cfa 7, 8 + ret +#endif +END (_ZGVdN8vvv_sincosf_avx2) |