public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: liuhongt <hongtao.liu@intel.com>
To: gcc-patches@gcc.gnu.org
Cc: crazylht@gmail.com, hjl.tools@gmail.com, ubizjak@gmail.com,
	jakub@redhat.com
Subject: [PATCH 53/62] AVX512FP16: Add expander for sqrthf2.
Date: Thu,  1 Jul 2021 14:16:39 +0800	[thread overview]
Message-ID: <20210701061648.9447-54-hongtao.liu@intel.com> (raw)
In-Reply-To: <20210701061648.9447-1-hongtao.liu@intel.com>

gcc/ChangeLog:

	* config/i386/i386-features.c (i386-features.c): Handle
	E_HFmode.
	* config/i386/i386.md (sqrthf2): New expander.
	(*sqrt<mode>2_sse): Extend to MODEFH.
	* config/i386/sse.md
	(*<sse>_vmsqrt<mode>2<mask_scalar_name><round_scalar_name>):
	Extend to VFH_128.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx512fp16-builtin-sqrt-1.c: New test.
	* gcc.target/i386/avx512fp16vl-builtin-sqrt-1.c: New test.
---
 gcc/config/i386/i386-features.c               | 15 +++++++++++----
 gcc/config/i386/i386.md                       | 12 +++++++++---
 gcc/config/i386/sse.md                        |  8 ++++----
 .../i386/avx512fp16-builtin-sqrt-1.c          | 18 ++++++++++++++++++
 .../i386/avx512fp16vl-builtin-sqrt-1.c        | 19 +++++++++++++++++++
 5 files changed, 61 insertions(+), 11 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-builtin-sqrt-1.c
 create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16vl-builtin-sqrt-1.c

diff --git a/gcc/config/i386/i386-features.c b/gcc/config/i386/i386-features.c
index a25769ae478..0b5a1a3af53 100644
--- a/gcc/config/i386/i386-features.c
+++ b/gcc/config/i386/i386-features.c
@@ -2238,15 +2238,22 @@ remove_partial_avx_dependency (void)
 
 	  rtx zero;
 	  machine_mode dest_vecmode;
-	  if (dest_mode == E_SFmode)
+	  switch (dest_mode)
 	    {
+	    case E_HFmode:
+	      dest_vecmode = V8HFmode;
+	      zero = gen_rtx_SUBREG (V8HFmode, v4sf_const0, 0);
+	      break;
+	    case E_SFmode:
 	      dest_vecmode = V4SFmode;
 	      zero = v4sf_const0;
-	    }
-	  else
-	    {
+	      break;
+	    case E_DFmode:
 	      dest_vecmode = V2DFmode;
 	      zero = gen_rtx_SUBREG (V2DFmode, v4sf_const0, 0);
+	      break;
+	    default:
+	      gcc_unreachable ();
 	    }
 
 	  /* Change source to vector mode.  */
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index a85c23d74f1..81c893c60de 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -16561,9 +16561,9 @@ (define_expand "rsqrtsf2"
 })
 
 (define_insn "*sqrt<mode>2_sse"
-  [(set (match_operand:MODEF 0 "register_operand" "=v,v,v")
-	(sqrt:MODEF
-	  (match_operand:MODEF 1 "nonimmediate_operand" "0,v,m")))]
+  [(set (match_operand:MODEFH 0 "register_operand" "=v,v,v")
+	(sqrt:MODEFH
+	  (match_operand:MODEFH 1 "nonimmediate_operand" "0,v,m")))]
   "SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH"
   "@
    %vsqrt<ssemodesuffix>\t{%d1, %0|%0, %d1}
@@ -16583,6 +16583,12 @@ (define_insn "*sqrt<mode>2_sse"
 	    ]
 	    (symbol_ref "true")))])
 
+(define_expand "sqrthf2"
+  [(set (match_operand:HF 0 "register_operand")
+	(sqrt:HF
+	  (match_operand:HF 1 "nonimmediate_operand")))]
+  "TARGET_AVX512FP16")
+
 (define_expand "sqrt<mode>2"
   [(set (match_operand:MODEF 0 "register_operand")
 	(sqrt:MODEF
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 2c3dba5bdb0..b47e7f0b82a 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -2389,12 +2389,12 @@ (define_insn "<sse>_vmsqrt<mode>2<mask_scalar_name><round_scalar_name>"
    (set_attr "mode" "<ssescalarmode>")])
 
 (define_insn "*<sse>_vmsqrt<mode>2<mask_scalar_name><round_scalar_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=x,v")
-	(vec_merge:VF_128
-	  (vec_duplicate:VF_128
+  [(set (match_operand:VFH_128 0 "register_operand" "=x,v")
+	(vec_merge:VFH_128
+	  (vec_duplicate:VFH_128
 	    (sqrt:<ssescalarmode>
 	      (match_operand:<ssescalarmode> 1 "nonimmediate_operand" "xm,<round_scalar_constraint>")))
-	  (match_operand:VF_128 2 "register_operand" "0,v")
+	  (match_operand:VFH_128 2 "register_operand" "0,v")
 	  (const_int 1)))]
   "TARGET_SSE"
   "@
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-builtin-sqrt-1.c b/gcc/testsuite/gcc.target/i386/avx512fp16-builtin-sqrt-1.c
new file mode 100644
index 00000000000..38cdf23fef7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-builtin-sqrt-1.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -mavx512fp16" } */
+
+_Float16
+f1 (_Float16 x)
+{
+  return __builtin_sqrtf16 (x);
+}
+
+void
+f2 (_Float16* __restrict psrc, _Float16* __restrict pdst)
+{
+  for (int i = 0; i != 32; i++)
+    pdst[i] = __builtin_sqrtf16 (psrc[i]);
+}
+
+/* { dg-final { scan-assembler-times "vsqrtsh\[^\n\r\]*xmm\[0-9\]" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtph\[^\n\r\]*zmm\[0-9\]" 1 } } */
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16vl-builtin-sqrt-1.c b/gcc/testsuite/gcc.target/i386/avx512fp16vl-builtin-sqrt-1.c
new file mode 100644
index 00000000000..08deb3ea470
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16vl-builtin-sqrt-1.c
@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -mavx512fp16 -mavx512vl" } */
+
+void
+f1 (_Float16* __restrict psrc, _Float16* __restrict pdst)
+{
+  for (int i = 0; i != 8; i++)
+    pdst[i] = __builtin_sqrtf16 (psrc[i]);
+}
+
+void
+f2 (_Float16* __restrict psrc, _Float16* __restrict pdst)
+{
+  for (int i = 0; i != 16; i++)
+    pdst[i] = __builtin_sqrtf16 (psrc[i]);
+}
+
+/* { dg-final { scan-assembler-times "vsqrtph\[^\n\r\]*xmm\[0-9\]" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtph\[^\n\r\]*ymm\[0-9\]" 1 } } */
-- 
2.18.1


  parent reply	other threads:[~2021-07-01  6:18 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-01  6:15 [PATCH 00/62] Support all AVX512FP16 intrinsics liuhongt
2021-07-01  6:15 ` [PATCH 01/62] AVX512FP16: Support vector init/broadcast for FP16 liuhongt
2021-07-01  6:15 ` [PATCH 02/62] AVX512FP16: Add testcase for vector init and broadcast intrinsics liuhongt
2021-07-01  6:15 ` [PATCH 03/62] AVX512FP16: Fix HF vector passing in variable arguments liuhongt
2021-07-01  6:15 ` [PATCH 04/62] AVX512FP16: Add ABI tests for xmm liuhongt
2021-07-01  6:15 ` [PATCH 05/62] AVX512FP16: Add ABI test for ymm liuhongt
2021-07-01  6:15 ` [PATCH 06/62] AVX512FP16: Add abi test for zmm liuhongt
2021-07-01  6:15 ` [PATCH 07/62] AVX512FP16: Add vaddph/vsubph/vdivph/vmulph liuhongt
2021-09-09  7:48   ` Hongtao Liu
2021-07-01  6:15 ` [PATCH 08/62] AVX512FP16: Add testcase for vaddph/vsubph/vmulph/vdivph liuhongt
2021-07-01  6:15 ` [PATCH 09/62] AVX512FP16: Enable _Float16 autovectorization liuhongt
2021-09-10  7:03   ` Hongtao Liu
2021-07-01  6:15 ` [PATCH 10/62] AVX512FP16: Add vaddsh/vsubsh/vmulsh/vdivsh liuhongt
2021-07-01  6:15 ` [PATCH 11/62] AVX512FP16: Add testcase for vaddsh/vsubsh/vmulsh/vdivsh liuhongt
2021-07-01  6:15 ` [PATCH 12/62] AVX512FP16: Add vmaxph/vminph/vmaxsh/vminsh liuhongt
2021-07-01  6:15 ` [PATCH 13/62] AVX512FP16: Add testcase for vmaxph/vmaxsh/vminph/vminsh liuhongt
2021-07-01  6:16 ` [PATCH 14/62] AVX512FP16: Add vcmpph/vcmpsh/vcomish/vucomish liuhongt
2021-07-01  6:16 ` [PATCH 15/62] AVX512FP16: Add testcase for vcmpph/vcmpsh/vcomish/vucomish liuhongt
2021-07-01  6:16 ` [PATCH 16/62] AVX512FP16: Add vsqrtph/vrsqrtph/vsqrtsh/vrsqrtsh liuhongt
2021-09-14  3:50   ` Hongtao Liu
2021-07-01  6:16 ` [PATCH 17/62] AVX512FP16: Add testcase for vsqrtph/vsqrtsh/vrsqrtph/vrsqrtsh liuhongt
2021-07-01  6:16 ` [PATCH 18/62] AVX512FP16: Add vrcpph/vrcpsh/vscalefph/vscalefsh liuhongt
2021-07-01  6:16 ` [PATCH 19/62] AVX512FP16: Add testcase for vrcpph/vrcpsh/vscalefph/vscalefsh liuhongt
2021-07-01  6:16 ` [PATCH 20/62] AVX512FP16: Add vreduceph/vreducesh/vrndscaleph/vrndscalesh liuhongt
2021-07-01  6:16 ` [PATCH 21/62] AVX512FP16: Add testcase for vreduceph/vreducesh/vrndscaleph/vrndscalesh liuhongt
2021-07-01  6:16 ` [PATCH 22/62] AVX512FP16: Add fpclass/getexp/getmant instructions liuhongt
2021-07-01  6:16 ` [PATCH 23/62] AVX512FP16: Add testcase for fpclass/getmant/getexp instructions liuhongt
2021-07-01  6:16 ` [PATCH 24/62] AVX512FP16: Add vmovw/vmovsh liuhongt
2021-09-16  5:08   ` Hongtao Liu
2021-07-01  6:16 ` [PATCH 25/62] AVX512FP16: Add testcase for vmovsh/vmovw liuhongt
2021-07-01  6:16 ` [PATCH 26/62] AVX512FP16: Add vcvtph2dq/vcvtph2qq/vcvtph2w/vcvtph2uw/vcvtph2uqq/vcvtph2udq liuhongt
2021-07-01  6:16 ` [PATCH 27/62] AVX512FP16: Add testcase for vcvtph2w/vcvtph2uw/vcvtph2dq/vcvtph2udq/vcvtph2qq/vcvtph2uqq liuhongt
2021-07-01  6:16 ` [PATCH 28/62] AVX512FP16: Add vcvtuw2ph/vcvtw2ph/vcvtdq2ph/vcvtudq2ph/vcvtqq2ph/vcvtuqq2ph liuhongt
2021-07-01  6:16 ` [PATCH 29/62] AVX512FP16: Add testcase for vcvtw2ph/vcvtuw2ph/vcvtdq2ph/vcvtudq2ph/vcvtqq2ph/vcvtuqq2ph liuhongt
2021-07-01  6:16 ` [PATCH 30/62] AVX512FP16: Add vcvtsh2si/vcvtsh2usi/vcvtsi2sh/vcvtusi2sh liuhongt
2021-09-17  8:07   ` Hongtao Liu
2021-07-01  6:16 ` [PATCH 31/62] AVX512FP16: Add testcase for vcvtsh2si/vcvtsh2usi/vcvtsi2sh/vcvtusi2sh liuhongt
2021-07-01  6:16 ` [PATCH 32/62] AVX512FP16: Add vcvttph2w/vcvttph2uw/vcvttph2dq/vcvttph2qq/vcvttph2udq/vcvttph2uqq liuhongt
2021-07-01  6:16 ` [PATCH 33/62] AVX512FP16: Add testcase for vcvttph2w/vcvttph2uw/vcvttph2dq/vcvttph2udq/vcvttph2qq/vcvttph2uqq liuhongt
2021-07-01  6:16 ` [PATCH 34/62] AVX512FP16: Add vcvttsh2si/vcvttsh2usi liuhongt
2021-07-01  6:16 ` [PATCH 35/62] AVX512FP16: Add vcvtph2pd/vcvtph2psx/vcvtpd2ph/vcvtps2phx liuhongt
2021-07-01  6:16 ` [PATCH 36/62] AVX512FP16: Add testcase for vcvtph2pd/vcvtph2psx/vcvtpd2ph/vcvtps2phx liuhongt
2021-07-01  6:16 ` [PATCH 37/62] AVX512FP16: Add vcvtsh2ss/vcvtsh2sd/vcvtss2sh/vcvtsd2sh liuhongt
2021-07-01  6:16 ` [PATCH 38/62] AVX512FP16: Add testcase for vcvtsh2sd/vcvtsh2ss/vcvtsd2sh/vcvtss2sh liuhongt
2021-07-01  6:16 ` [PATCH 39/62] AVX512FP16: Add intrinsics for casting between vector float16 and vector float32/float64/integer liuhongt
2021-07-01  6:16 ` [PATCH 40/62] AVX512FP16: Add vfmaddsub[132, 213, 231]ph/vfmsubadd[132, 213, 231]ph liuhongt
2021-09-18  7:04   ` Hongtao Liu
2021-07-01  6:16 ` [PATCH 41/62] AVX512FP16: Add testcase for " liuhongt
2021-07-01  6:16 ` [PATCH 42/62] AVX512FP16: Add FP16 fma instructions liuhongt
2021-07-01  6:16 ` [PATCH 43/62] AVX512FP16: Add testcase for " liuhongt
2021-07-01  6:16 ` [PATCH 44/62] AVX512FP16: Add scalar/vector bitwise operations, including liuhongt
2021-07-23  5:13   ` Hongtao Liu
2021-07-26  2:25     ` Hongtao Liu
2021-07-01  6:16 ` [PATCH 45/62] AVX512FP16: Add testcase for fp16 bitwise operations liuhongt
2021-07-01  6:16 ` [PATCH 46/62] AVX512FP16: Enable FP16 mask load/store liuhongt
2021-07-01  6:16 ` [PATCH 47/62] AVX512FP16: Add scalar fma instructions liuhongt
2021-07-01  6:16 ` [PATCH 48/62] AVX512FP16: Add testcase for scalar FMA instructions liuhongt
2021-07-01  6:16 ` [PATCH 49/62] AVX512FP16: Add vfcmaddcph/vfmaddcph/vfcmulcph/vfmulcph liuhongt
2021-09-22  4:38   ` Hongtao Liu
2021-07-01  6:16 ` [PATCH 50/62] AVX512FP16: Add testcases for vfcmaddcph/vfmaddcph/vfcmulcph/vfmulcph liuhongt
2021-07-01  6:16 ` [PATCH 51/62] AVX512FP16: Add vfcmaddcsh/vfmaddcsh/vfcmulcsh/vfmulcsh liuhongt
2021-07-01  6:16 ` [PATCH 52/62] AVX512FP16: Add testcases for vfcmaddcsh/vfmaddcsh/vfcmulcsh/vfmulcsh liuhongt
2021-07-01  6:16 ` liuhongt [this message]
2021-07-23  5:12   ` [PATCH 53/62] AVX512FP16: Add expander for sqrthf2 Hongtao Liu
2021-07-01  6:16 ` [PATCH 54/62] AVX512FP16: Add expander for ceil/floor/trunc/roundeven liuhongt
2021-07-01  6:16 ` [PATCH 55/62] AVX512FP16: Add expander for cstorehf4 liuhongt
2021-07-01  6:16 ` [PATCH 56/62] AVX512FP16: Optimize (_Float16) sqrtf ((float) f16) to sqrtf16 (f16) liuhongt
2021-07-01  9:50   ` Richard Biener
2021-07-01 10:23     ` Hongtao Liu
2021-07-01 12:43       ` Richard Biener
2021-07-01 21:48         ` Joseph Myers
2021-07-02  7:38           ` Richard Biener
2021-07-01 21:17   ` Joseph Myers
2021-07-01  6:16 ` [PATCH 57/62] AVX512FP16: Add expander for fmahf4 liuhongt
2021-07-01  6:16 ` [PATCH 58/62] AVX512FP16: Optimize for code like (_Float16) __builtin_ceif ((float) f16) liuhongt
2021-07-01  9:52   ` Richard Biener
2021-07-01 21:26   ` Joseph Myers
2021-07-02  7:36     ` Richard Biener
2021-07-02 11:46       ` Bernhard Reutner-Fischer
2021-07-04  5:17         ` Hongtao Liu
2021-07-01  6:16 ` [PATCH 59/62] AVX512FP16: Support load/store/abs intrinsics liuhongt
2021-09-22 10:30   ` Hongtao Liu
2021-07-01  6:16 ` [PATCH 60/62] AVX512FP16: Add reduce operators(add/mul/min/max) liuhongt
2021-07-01  6:16 ` [PATCH 61/62] AVX512FP16: Add complex conjugation intrinsic instructions liuhongt
2021-07-01  6:16 ` [PATCH 62/62] AVX512FP16: Add permutation and mask blend intrinsics liuhongt

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210701061648.9447-54-hongtao.liu@intel.com \
    --to=hongtao.liu@intel.com \
    --cc=crazylht@gmail.com \
    --cc=gcc-patches@gcc.gnu.org \
    --cc=hjl.tools@gmail.com \
    --cc=jakub@redhat.com \
    --cc=ubizjak@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).