diff options
| author | Andrew Senkevich <andrew.senkevich@intel.com> | 2016-07-01 14:15:38 +0300 |
|---|---|---|
| committer | Andrew Senkevich <andrew.senkevich@intel.com> | 2016-07-01 14:15:38 +0300 |
| commit | ee2196bb6766ca7e63a1ba22ebb7619a3266776a (patch) | |
| tree | a99accc0d97a405f535249efd7657de270726850 /sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S | |
| parent | fd1cf1dc3b2d90c2a61332363feb1043f6916564 (diff) | |
| download | glibc-ee2196bb6766ca7e63a1ba22ebb7619a3266776a.tar.gz glibc-ee2196bb6766ca7e63a1ba22ebb7619a3266776a.tar.xz glibc-ee2196bb6766ca7e63a1ba22ebb7619a3266776a.zip | |
Fixed wrong vector sincos/sincosf ABI to have it compatible with
current vector function declaration "#pragma omp declare simd notinbranch",
according to which vector sincos should have vector of pointers for second and
third parameters. It is fixed with implementation as wrapper to version
having second and third parameters as pointers.
[BZ #20024]
* sysdeps/x86/fpu/test-math-vector-sincos.h: New.
* sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S: Fixed ABI
of this implementation of vector function.
* sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S:
Likewise.
* sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S: Likewise.
* sysdeps/x86_64/fpu/svml_d_sincos2_core.S: Likewise.
* sysdeps/x86_64/fpu/svml_d_sincos4_core.S: Likewise.
* sysdeps/x86_64/fpu/svml_d_sincos4_core_avx.S: Likewise.
* sysdeps/x86_64/fpu/svml_d_sincos8_core.S: Likewise.
* sysdeps/x86_64/fpu/svml_s_sincosf16_core.S: Likewise.
* sysdeps/x86_64/fpu/svml_s_sincosf4_core.S: Likewise.
* sysdeps/x86_64/fpu/svml_s_sincosf8_core.S: Likewise.
* sysdeps/x86_64/fpu/svml_s_sincosf8_core_avx.S: Likewise.
* sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Use another wrapper
for testing vector sincos with fixed ABI.
* sysdeps/x86_64/fpu/test-double-vlen4-avx2-wrappers.c: Likewise.
* sysdeps/x86_64/fpu/test-double-vlen4-wrappers.c: Likewise.
* sysdeps/x86_64/fpu/test-double-vlen8-wrappers.c: Likewise.
* sysdeps/x86_64/fpu/test-float-vlen16-wrappers.c: Likewise.
* sysdeps/x86_64/fpu/test-float-vlen4-wrappers.c: Likewise.
* sysdeps/x86_64/fpu/test-float-vlen8-avx2-wrappers.c: Likewise.
* sysdeps/x86_64/fpu/test-float-vlen8-wrappers.c: Likewise.
* sysdeps/x86_64/fpu/test-double-libmvec-sincos-avx.c: New test.
* sysdeps/x86_64/fpu/test-double-libmvec-sincos-avx2.c: Likewise.
* sysdeps/x86_64/fpu/test-double-libmvec-sincos-avx512.c: Likewise.
* sysdeps/x86_64/fpu/test-double-libmvec-sincos.c: Likewise.
* sysdeps/x86_64/fpu/test-float-libmvec-sincosf-avx.c: Likewise.
* sysdeps/x86_64/fpu/test-float-libmvec-sincosf-avx2.c: Likewise.
* sysdeps/x86_64/fpu/test-float-libmvec-sincosf-avx512.c: Likewise.
* sysdeps/x86_64/fpu/test-float-libmvec-sincosf.c: Likewise.
* sysdeps/x86_64/fpu/Makefile: Added new tests.
Diffstat (limited to 'sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S')
| -rw-r--r-- | sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S | 98 |
1 files changed, 97 insertions, 1 deletions
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) |