From ad9fcb961c0705f56907a728c3748c011a0a8048 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Sat, 4 Sep 2021 07:48:43 -0700
Subject: [PATCH] x86: Enable FMA in unsigned SI to SF expanders

Enable FMA in scalar/vector unsigned SI to SF expanders.  Don't check
TARGET_AVX512F which has vcvtusi2ss and vcvtudq2ps instructions.

gcc/

	PR target/85819
	* config/i386/i386-expand.c (ix86_expand_convert_uns_sisf_sse):
	Enable FMA.
	(ix86_expand_vector_convert_uns_vsivsf): Likewise.

gcc/testsuite/

	PR target/85819
	* gcc.target/i386/pr85819-1a.c: New test.
	* gcc.target/i386/pr85819-1b.c: Likewise.
	* gcc.target/i386/pr85819-2a.c: Likewise.
	* gcc.target/i386/pr85819-2b.c: Likewise.
	* gcc.target/i386/pr85819-2c.c: Likewise.
	* gcc.target/i386/pr85819-3.c: Likewise.
---
 gcc/config/i386/i386-expand.c              | 41 +++++++++++++++++++++---------
 gcc/testsuite/gcc.target/i386/pr85819-1a.c | 11 ++++++++
 gcc/testsuite/gcc.target/i386/pr85819-1b.c |  6 +++++
 gcc/testsuite/gcc.target/i386/pr85819-2a.c | 17 +++++++++++++
 gcc/testsuite/gcc.target/i386/pr85819-2b.c |  6 +++++
 gcc/testsuite/gcc.target/i386/pr85819-2c.c |  7 +++++
 gcc/testsuite/gcc.target/i386/pr85819-3.c  | 18 +++++++++++++
 7 files changed, 94 insertions(+), 12 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr85819-1a.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr85819-1b.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr85819-2a.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr85819-2b.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr85819-2c.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr85819-3.c

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 273a0ba..3f90f67 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -1851,12 +1851,21 @@ ix86_expand_convert_uns_sisf_sse (rtx target, rtx input)
   fp_lo = gen_reg_rtx (SFmode);
   emit_insn (gen_floatsisf2 (fp_hi, int_hi));
   emit_insn (gen_floatsisf2 (fp_lo, int_lo));
-  fp_hi = expand_simple_binop (SFmode, MULT, fp_hi, x, fp_hi,
-			       0, OPTAB_DIRECT);
-  fp_hi = expand_simple_binop (SFmode, PLUS, fp_hi, fp_lo, target,
-			       0, OPTAB_DIRECT);
-  if (!rtx_equal_p (target, fp_hi))
-    emit_move_insn (target, fp_hi);
+  if (TARGET_FMA)
+    {
+      x = validize_mem (force_const_mem (SFmode, x));
+      fp_hi = gen_rtx_FMA (SFmode, fp_hi, x, fp_lo);
+      emit_move_insn (target, fp_hi);
+    }
+  else
+    {
+      fp_hi = expand_simple_binop (SFmode, MULT, fp_hi, x, fp_hi,
+				   0, OPTAB_DIRECT);
+      fp_hi = expand_simple_binop (SFmode, PLUS, fp_hi, fp_lo, target,
+				   0, OPTAB_DIRECT);
+      if (!rtx_equal_p (target, fp_hi))
+	emit_move_insn (target, fp_hi);
+    }
 }
 
 /* floatunsv{4,8}siv{4,8}sf2 expander.  Expand code to convert
@@ -1888,12 +1897,20 @@ ix86_expand_vector_convert_uns_vsivsf (rtx target, rtx val)
   real_ldexp (&TWO16r, &dconst1, 16);
   tmp[5] = const_double_from_real_value (TWO16r, SFmode);
   tmp[5] = force_reg (fltmode, ix86_build_const_vector (fltmode, 1, tmp[5]));
-  tmp[6] = expand_simple_binop (fltmode, MULT, tmp[4], tmp[5], NULL_RTX, 1,
-				OPTAB_DIRECT);
-  tmp[7] = expand_simple_binop (fltmode, PLUS, tmp[3], tmp[6], target, 1,
-				OPTAB_DIRECT);
-  if (tmp[7] != target)
-    emit_move_insn (target, tmp[7]);
+  if (TARGET_FMA)
+    {
+      tmp[6] = gen_rtx_FMA (fltmode, tmp[4], tmp[5], tmp[3]);
+      emit_move_insn (target, tmp[6]);
+    }
+  else
+    {
+      tmp[6] = expand_simple_binop (fltmode, MULT, tmp[4], tmp[5],
+				    NULL_RTX, 1, OPTAB_DIRECT);
+      tmp[7] = expand_simple_binop (fltmode, PLUS, tmp[3], tmp[6],
+				    target, 1, OPTAB_DIRECT);
+      if (tmp[7] != target)
+	emit_move_insn (target, tmp[7]);
+    }
 }
 
 /* Adjust a V*SFmode/V*DFmode value VAL so that *sfix_trunc* resp. fix_trunc*
diff --git a/gcc/testsuite/gcc.target/i386/pr85819-1a.c b/gcc/testsuite/gcc.target/i386/pr85819-1a.c
new file mode 100644
index 0000000..db02282
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr85819-1a.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512f -mfma -mfpmath=sse" } */
+
+float
+foo (unsigned int x)
+{
+  return x;
+}
+
+/* { dg-final { scan-assembler "vfmadd132ss" { target ia32 } } } */
+/* { dg-final { scan-assembler "vcvtsi2ssq" { target { ! ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr85819-1b.c b/gcc/testsuite/gcc.target/i386/pr85819-1b.c
new file mode 100644
index 0000000..f1408c4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr85819-1b.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512f -mfpmath=sse" } */
+
+#include "pr85819-1a.c"
+
+/* { dg-final { scan-assembler "vcvtusi2ss" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr85819-2a.c b/gcc/testsuite/gcc.target/i386/pr85819-2a.c
new file mode 100644
index 0000000..cea599f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr85819-2a.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mfma -mfpmath=sse" } */
+
+typedef float To __attribute__ ((__vector_size__ (32)));
+typedef unsigned int From __attribute__ ((__vector_size__ (32)));
+
+#define A2(I) (float)a[I], (float)a[1+I]
+#define A4(I) A2(I), A2(2+I)
+#define A8(I) A4(I), A4(4+I)
+
+To
+f(From a)
+{
+  return __extension__ (To) {A8(0)};
+}
+
+/* { dg-final { scan-assembler "vfmadd132ps" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr85819-2b.c b/gcc/testsuite/gcc.target/i386/pr85819-2b.c
new file mode 100644
index 0000000..0750e56
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr85819-2b.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512vl -mfpmath=sse" } */
+
+#include "pr85819-2a.c"
+
+/* { dg-final { scan-assembler "vcvtudq2ps" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr85819-2c.c b/gcc/testsuite/gcc.target/i386/pr85819-2c.c
new file mode 100644
index 0000000..8211669
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr85819-2c.c
@@ -0,0 +1,7 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-fma -mno-avx2 -mno-avx512vl -mavx512f -mfpmath=sse" } */
+
+#include "pr85819-2a.c"
+
+/* { dg-final { scan-assembler-not "vcvtudq2ps" } } */
+/* { dg-final { scan-assembler-not "vfmadd132ps" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr85819-3.c b/gcc/testsuite/gcc.target/i386/pr85819-3.c
new file mode 100644
index 0000000..cd3bf9b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr85819-3.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512f -mfpmath=sse" } */
+
+typedef float To __attribute__ ((__vector_size__ (64)));
+typedef unsigned int From __attribute__ ((__vector_size__ (64)));
+
+#define A2(I) (float)a[I], (float)a[1+I]
+#define A4(I) A2(I), A2(2+I)
+#define A8(I) A4(I), A4(4+I)
+#define A16(I) A8(I), A8(8+I)
+
+To
+f(From a)
+{
+  return __extension__ (To) {A16(0)};
+}
+
+/* { dg-final { scan-assembler "vcvtudq2ps" } } */
-- 
2.7.4