From c166f44e4488af4f4af035645775fe44b12bab13 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Fri, 20 Aug 2021 06:42:24 -0700
Subject: [PATCH] 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.

(cherry picked from commit 78c9ec9000f873abe7a15a91b87080a2e4308260)
---
 .../x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S   |  7 +------
 .../x86_64/fpu/multiarch/svml_d_log8_core_avx512.S   |  7 +------
 .../x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S   |  7 +------
 .../fpu/multiarch/svml_d_sincos8_core_avx512.S       |  7 +------
 .../x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S |  7 +------
 .../x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S |  7 +------
 .../x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S |  7 +------
 .../x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S | 12 ++----------
 .../fpu/multiarch/svml_s_sincosf16_core_avx512.S     |  7 +------
 .../x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S |  7 +------
 10 files changed, 11 insertions(+), 64 deletions(-)

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S
index 24e3b363..07dfed85 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S
@@ -265,7 +265,7 @@ WRAPPER_IMPL_AVX512 _ZGVdN4v_cos
         vmovaps   %zmm0, %zmm8
 
 /* Check for large arguments path */
-        vpbroadcastq .L_2il0floatpacket.16(%rip), %zmm2
+        vpternlogd $0xff, %zmm2, %zmm2, %zmm2
 
 /*
   ARGUMENT RANGE REDUCTION:
@@ -456,8 +456,3 @@ WRAPPER_IMPL_AVX512 _ZGVdN4v_cos
         jmp       .LBL_2_7
 #endif
 END (_ZGVeN8v_cos_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.16:
-	.long	0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.16,@object
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S
index ae8af8d8..ddb60e5b 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S
@@ -274,7 +274,7 @@ WRAPPER_IMPL_AVX512 _ZGVdN4v_log
 
 /* preserve mantissa, set input exponent to 2^(-10) */
         vpternlogq $248, _ExpMask(%rax), %zmm3, %zmm2
-        vpbroadcastq .L_2il0floatpacket.12(%rip), %zmm1
+        vpternlogd $0xff, %zmm1, %zmm1, %zmm1
         vpsrlq    $32, %zmm4, %zmm6
 
 /* reciprocal approximation good to at least 11 bits */
@@ -461,8 +461,3 @@ WRAPPER_IMPL_AVX512 _ZGVdN4v_log
         jmp       .LBL_2_7
 #endif
 END (_ZGVeN8v_log_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.12:
-	.long	0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.12,@object
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S
index 2d4b14fd..529c454a 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S
@@ -261,7 +261,7 @@ WRAPPER_IMPL_AVX512 _ZGVdN4v_sin
         andq      $-64, %rsp
         subq      $1280, %rsp
         movq      __svml_d_trig_data@GOTPCREL(%rip), %rax
-        vpbroadcastq .L_2il0floatpacket.14(%rip), %zmm14
+        vpternlogd $0xff, %zmm1, %zmm1, %zmm14
         vmovups __dAbsMask(%rax), %zmm7
         vmovups __dInvPI(%rax), %zmm2
         vmovups __dRShifter(%rax), %zmm1
@@ -458,8 +458,3 @@ WRAPPER_IMPL_AVX512 _ZGVdN4v_sin
         jmp       .LBL_2_7
 #endif
 END (_ZGVeN8v_sin_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.14:
-	.long	0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.14,@object
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 2df626c0..e501a53a 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
@@ -430,7 +430,7 @@ WRAPPER_IMPL_AVX512_fFF _ZGVdN4vl8l8_sincos
 
 /* SinPoly = SinR*SinPoly */
         vfmadd213pd %zmm5, %zmm5, %zmm4
-        vpbroadcastq .L_2il0floatpacket.15(%rip), %zmm3
+        vpternlogd $0xff, %zmm3, %zmm3, %zmm3
 
 /* Update Cos result's sign */
         vxorpd    %zmm2, %zmm1, %zmm1
@@ -741,8 +741,3 @@ END (_ZGVeN8vvv_sincos_knl)
 ENTRY (_ZGVeN8vvv_sincos_skx)
 WRAPPER_AVX512_vvv_vl8l8 _ZGVeN8vl8l8_sincos_skx
 END (_ZGVeN8vvv_sincos_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.15:
-	.long	0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.15,@object
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S
index 6ea1137b..377af394 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S
@@ -278,7 +278,7 @@ WRAPPER_IMPL_AVX512 _ZGVdN8v_cosf
   X = X - Y*PI1 - Y*PI2 - Y*PI3
  */
         vmovaps   %zmm0, %zmm6
-        vmovups   .L_2il0floatpacket.13(%rip), %zmm12
+        vpternlogd $0xff, %zmm12, %zmm12, %zmm12
         vmovups __sRShifter(%rax), %zmm3
         vmovups __sPI1_FMA(%rax), %zmm5
         vmovups __sA9_FMA(%rax), %zmm9
@@ -453,8 +453,3 @@ WRAPPER_IMPL_AVX512 _ZGVdN8v_cosf
         jmp       .LBL_2_7
 #endif
 END (_ZGVeN16v_cosf_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.13:
-	.long	0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.13,@object
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S
index 89ba0df2..46f33d46 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S
@@ -264,7 +264,7 @@ WRAPPER_IMPL_AVX512 _ZGVdN8v_expf
         vmovaps   %zmm0, %zmm7
 
 /* compare against threshold */
-        vmovups   .L_2il0floatpacket.13(%rip), %zmm3
+        vpternlogd $0xff, %zmm3, %zmm3, %zmm3
         vmovups __sInvLn2(%rax), %zmm4
         vmovups __sShifter(%rax), %zmm1
         vmovups __sLn2hi(%rax), %zmm6
@@ -440,8 +440,3 @@ WRAPPER_IMPL_AVX512 _ZGVdN8v_expf
 
 #endif
 END (_ZGVeN16v_expf_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.13:
-	.long	0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.13,@object
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S
index 4cf0a96f..9e254956 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S
@@ -235,7 +235,7 @@ WRAPPER_IMPL_AVX512 _ZGVdN8v_logf
         andq      $-64, %rsp
         subq      $1280, %rsp
         movq      __svml_slog_data@GOTPCREL(%rip), %rax
-        vmovups   .L_2il0floatpacket.7(%rip), %zmm6
+        vpternlogd $0xff, %zmm6, %zmm6, %zmm6
         vmovups _iBrkValue(%rax), %zmm4
         vmovups _sPoly_7(%rax), %zmm8
 
@@ -409,8 +409,3 @@ WRAPPER_IMPL_AVX512 _ZGVdN8v_logf
 
 #endif
 END (_ZGVeN16v_logf_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.7:
-	.long	0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.7,@object
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S
index bdcd50af..e8331ba1 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S
@@ -385,7 +385,7 @@ WRAPPER_IMPL_AVX512_ff _ZGVdN8vv_powf
         vpsrlq    $32, %zmm3, %zmm2
         vpmovqd   %zmm2, %ymm11
         vcvtps2pd %ymm14, %zmm13
-        vmovups   .L_2il0floatpacket.23(%rip), %zmm14
+        vpternlogd $0xff, %zmm14, %zmm14, %zmm14
         vmovaps   %zmm14, %zmm26
         vpandd _ABSMASK(%rax), %zmm1, %zmm8
         vpcmpd    $1, _INF(%rax), %zmm8, %k2
@@ -427,7 +427,7 @@ WRAPPER_IMPL_AVX512_ff _ZGVdN8vv_powf
         vpmovqd   %zmm11, %ymm5
         vpxord    %zmm10, %zmm10, %zmm10
         vgatherdpd _Log2Rcp_lookup(%rax,%ymm4), %zmm10{%k3}
-        vpbroadcastq .L_2il0floatpacket.24(%rip), %zmm4
+        vpternlogd $0xff, %zmm4, %zmm4, %zmm4
         vpxord    %zmm11, %zmm11, %zmm11
         vcvtdq2pd %ymm7, %zmm7
         vgatherdpd _Log2Rcp_lookup(%rax,%ymm5), %zmm11{%k1}
@@ -643,11 +643,3 @@ WRAPPER_IMPL_AVX512_ff _ZGVdN8vv_powf
         jmp       .LBL_2_7
 #endif
 END (_ZGVeN16vv_powf_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.23:
-	.long	0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.23,@object
-.L_2il0floatpacket.24:
-	.long	0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.24,@object
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 5fa4bc41..1f46f334 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
@@ -317,7 +317,7 @@ WRAPPER_IMPL_AVX512_fFF _ZGVdN8vvv_sincosf
 
 /* Result sign calculations */
         vpternlogd $150, %zmm0, %zmm14, %zmm1
-        vmovups   .L_2il0floatpacket.13(%rip), %zmm14
+        vpternlogd $0xff, %zmm14, %zmm14, %zmm14
 
 /* Add correction term 0.5 for cos() part */
         vaddps    %zmm8, %zmm5, %zmm15
@@ -748,8 +748,3 @@ END (_ZGVeN16vvv_sincosf_knl)
 ENTRY (_ZGVeN16vvv_sincosf_skx)
 WRAPPER_AVX512_vvv_vl4l4 _ZGVeN16vl4l4_sincosf_skx
 END (_ZGVeN16vvv_sincosf_skx)
-
-	.section .rodata, "a"
-.L_2il0floatpacket.13:
-	.long	0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff
-	.type	.L_2il0floatpacket.13,@object
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 141f747e..1fc9308a 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
-- 
GitLab