about summary refs log tree commit diff
path: root/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2021-08-20 06:42:24 -0700
committerH.J. Lu <hjl.tools@gmail.com>2021-08-22 06:23:37 -0700
commit78c9ec9000f873abe7a15a91b87080a2e4308260 (patch)
tree1fb85aec1d1f6394f650758f5074130e77fea131 /sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S
parentc333dcf8d8f9e6e46475d9eff24bd5394b5d3d9e (diff)
downloadglibc-78c9ec9000f873abe7a15a91b87080a2e4308260.tar.gz
glibc-78c9ec9000f873abe7a15a91b87080a2e4308260.tar.xz
glibc-78c9ec9000f873abe7a15a91b87080a2e4308260.zip
x86-64: Optimize load of all bits set into ZMM register [BZ #28252]
Optimize loads of all bits set into ZMM register in AVX512 SVML codes
by replacing

	vpbroadcastq .L_2il0floatpacket.16(%rip), %zmmX

and

	vmovups   .L_2il0floatpacket.13(%rip), %zmmX

with
	vpternlogd $0xff, %zmmX, %zmmX, %zmmX

This fixes BZ #28252.
Diffstat (limited to 'sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S')
-rw-r--r--sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S7
1 files changed, 1 insertions, 6 deletions
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S
index bd05109a62..c1b352d0ad 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S
@@ -280,7 +280,7 @@ WRAPPER_IMPL_AVX512 _ZGVdN8v_sinf
         movq      __svml_s_trig_data@GOTPCREL(%rip), %rax
 
 /* Check for large and special values */
-        vmovups   .L_2il0floatpacket.11(%rip), %zmm14
+        vpternlogd $0xff, %zmm14, %zmm14, %zmm14
         vmovups __sAbsMask(%rax), %zmm5
         vmovups __sInvPI(%rax), %zmm1
         vmovups __sRShifter(%rax), %zmm2
@@ -472,8 +472,3 @@ WRAPPER_IMPL_AVX512 _ZGVdN8v_sinf
         jmp       .LBL_2_7
 #endif
 END (_ZGVeN16v_sinf_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.11:
-	.long	0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.11,@object