Use movss/movsd to implement V4SI/V2DI VEC_PERM on x86.

This patch tweaks the x86 backend to use the movss and movsd instructions
to perform some vector permutations on integer vectors (V4SI and V2DI) in
the same way they are used for floating point vectors (V4SF and V2DF).

As a motivating example, consider:

typedef unsigned int v4si __attribute__((vector_size(16)));
typedef float v4sf __attribute__((vector_size(16)));
v4si foo(v4si x,v4si y) { return (v4si){y[0],x[1],x[2],x[3]}; }
v4sf bar(v4sf x,v4sf y) { return (v4sf){y[0],x[1],x[2],x[3]}; }

which is currently compiled with -O2 to:

foo:	movdqa	%xmm0, %xmm2
	shufps	$80, %xmm0, %xmm1
	movdqa	%xmm1, %xmm0
	shufps	$232, %xmm2, %xmm0
	ret

bar:	movss	%xmm1, %xmm0
	ret

with this patch both functions compile to the same form.
Likewise for the V2DI case:

typedef unsigned long v2di __attribute__((vector_size(16)));
typedef double v2df __attribute__((vector_size(16)));

v2di foo(v2di x,v2di y) { return (v2di){y[0],x[1]}; }
v2df bar(v2df x,v2df y) { return (v2df){y[0],x[1]}; }

which currently generates:

foo:	shufpd	$2, %xmm0, %xmm1
	movdqa	%xmm1, %xmm0
	ret

bar:	movsd	%xmm1, %xmm0
	ret

2022-12-25  Roger Sayle  <roger@nextmovesoftware.com>
	    Uroš Bizjak  <ubizjak@gmail.com>

gcc/ChangeLog
	* config/i386/i386-builtin.def (__builtin_ia32_movss): Update
	CODE_FOR_sse_movss to CODE_FOR_sse_movss_v4sf.
	(__builtin_ia32_movsd): Likewise, update CODE_FOR_sse2_movsd to
	CODE_FOR_sse2_movsd_v2df.
	* config/i386/i386-expand.cc (split_convert_uns_si_sse): Update
	gen_sse_movss call to gen_sse_movss_v4sf, and gen_sse2_movsd call
	to gen_sse2_movsd_v2df.
	(expand_vec_perm_movs): Also allow V4SImode with TARGET_SSE and
	V2DImode with TARGET_SSE2.
	* config/i386/sse.md
	(avx512fp16_fcmaddcsh_v8hf_mask3<round_expand_name>): Update
	gen_sse_movss call to gen_sse_movss_v4sf.
	(avx512fp16_fmaddcsh_v8hf_mask3<round_expand_name>): Likewise.
	(sse_movss_<mode>): Renamed from sse_movss using VI4F_128 mode
	iterator to handle both V4SF and V4SI.
	(sse2_movsd_<mode>): Likewise, renamed from sse2_movsd using
	VI8F_128 mode iterator to handle both V2DF and V2DI.

gcc/testsuite/ChangeLog
	* gcc.target/i386/sse-movss-4.c: New test case.
	* gcc.target/i386/sse2-movsd-3.c: New test case.

5 files changed, 47 insertions, 17 deletions

diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index d85b175..0d1fc34 100644
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -679,7 +679,7 @@ BDESC (OPTION_MASK_ISA_SSE, 0, CODE_FOR_xorv4sf3,  "__builtin_ia32_xorps", IX86_
 
 BDESC (OPTION_MASK_ISA_SSE, 0, CODE_FOR_copysignv4sf3,  "__builtin_ia32_copysignps", IX86_BUILTIN_CPYSGNPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF)
 
-BDESC (OPTION_MASK_ISA_SSE, 0, CODE_FOR_sse_movss,  "__builtin_ia32_movss", IX86_BUILTIN_MOVSS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF)
+BDESC (OPTION_MASK_ISA_SSE, 0, CODE_FOR_sse_movss_v4sf,  "__builtin_ia32_movss", IX86_BUILTIN_MOVSS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF)
 BDESC (OPTION_MASK_ISA_SSE, 0, CODE_FOR_sse_movhlps_exp,  "__builtin_ia32_movhlps", IX86_BUILTIN_MOVHLPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF)
 BDESC (OPTION_MASK_ISA_SSE, 0, CODE_FOR_sse_movlhps_exp,  "__builtin_ia32_movlhps", IX86_BUILTIN_MOVLHPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF)
 BDESC (OPTION_MASK_ISA_SSE, 0, CODE_FOR_vec_interleave_highv4sf, "__builtin_ia32_unpckhps", IX86_BUILTIN_UNPCKHPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF)
@@ -781,7 +781,7 @@ BDESC (OPTION_MASK_ISA_SSE2, 0, CODE_FOR_xorv2df3,  "__builtin_ia32_xorpd", IX86
 
 BDESC (OPTION_MASK_ISA_SSE2, 0, CODE_FOR_copysignv2df3,  "__builtin_ia32_copysignpd", IX86_BUILTIN_CPYSGNPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF)
 
-BDESC (OPTION_MASK_ISA_SSE2, 0, CODE_FOR_sse2_movsd,  "__builtin_ia32_movsd", IX86_BUILTIN_MOVSD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF)
+BDESC (OPTION_MASK_ISA_SSE2, 0, CODE_FOR_sse2_movsd_v2df,  "__builtin_ia32_movsd", IX86_BUILTIN_MOVSD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF)
 BDESC (OPTION_MASK_ISA_SSE2, 0, CODE_FOR_vec_interleave_highv2df, "__builtin_ia32_unpckhpd", IX86_BUILTIN_UNPCKHPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF)
 BDESC (OPTION_MASK_ISA_SSE2, 0, CODE_FOR_vec_interleave_lowv2df, "__builtin_ia32_unpcklpd", IX86_BUILTIN_UNPCKLPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF)
 
diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index 0b887e7..b6cc76d 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -1774,9 +1774,9 @@ ix86_split_convert_uns_si_sse (rtx operands[])
       input = gen_rtx_REG (vecmode, REGNO (input));
       emit_move_insn (value, CONST0_RTX (vecmode));
       if (vecmode == V4SFmode)
-	emit_insn (gen_sse_movss (value, value, input));
+	emit_insn (gen_sse_movss_v4sf (value, value, input));
       else
-	emit_insn (gen_sse2_movsd (value, value, input));
+	emit_insn (gen_sse2_movsd_v2df (value, value, input));
     }
 
   emit_move_insn (large, two31);
@@ -18905,8 +18905,10 @@ expand_vec_perm_movs (struct expand_vec_perm_d *d)
     return false;
 
   if (!(TARGET_SSE && vmode == V4SFmode)
+      && !(TARGET_SSE && vmode == V4SImode)
       && !(TARGET_MMX_WITH_SSE && vmode == V2SFmode)
-      && !(TARGET_SSE2 && vmode == V2DFmode))
+      && !(TARGET_SSE2 && vmode == V2DFmode)
+      && !(TARGET_SSE2 && vmode == V2DImode))
     return false;
 
   /* Only the first element is changed.  */
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index de632b2..d50627a 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -6825,7 +6825,7 @@
   if (!MEM_P (operands[3]))
     operands[3] = force_reg (V8HFmode, operands[3]);
   op1 = lowpart_subreg (V4SFmode, operands[3], V8HFmode);
-  emit_insn (gen_sse_movss (dest, op1, op0));
+  emit_insn (gen_sse_movss_v4sf (dest, op1, op0));
   emit_move_insn (operands[0], lowpart_subreg (V8HFmode, dest, V4SFmode));
   DONE;
 })
@@ -6855,7 +6855,7 @@
   if (!MEM_P (operands[3]))
     operands[3] = force_reg (V8HFmode, operands[3]);
   op1 = lowpart_subreg (V4SFmode, operands[3], V8HFmode);
-  emit_insn (gen_sse_movss (dest, op1, op0));
+  emit_insn (gen_sse_movss_v4sf (dest, op1, op0));
   emit_move_insn (operands[0], lowpart_subreg (V8HFmode, dest, V4SFmode));
   DONE;
 })
@@ -10498,11 +10498,11 @@
    (set_attr "prefix" "orig,maybe_evex,orig,maybe_evex,maybe_vex")
    (set_attr "mode" "V4SF,V4SF,V2SF,V2SF,V2SF")])
 
-(define_insn "sse_movss"
-  [(set (match_operand:V4SF 0 "register_operand"   "=x,v")
-	(vec_merge:V4SF
-	  (match_operand:V4SF 2 "register_operand" " x,v")
-	  (match_operand:V4SF 1 "register_operand" " 0,v")
+(define_insn "sse_movss_<mode>"
+  [(set (match_operand:VI4F_128 0 "register_operand"   "=x,v")
+	(vec_merge:VI4F_128
+	  (match_operand:VI4F_128 2 "register_operand" " x,v")
+	  (match_operand:VI4F_128 1 "register_operand" " 0,v")
 	  (const_int 1)))]
   "TARGET_SSE"
   "@
@@ -13481,11 +13481,11 @@
   [(set (match_dup 0) (match_dup 1))]
   "operands[0] = adjust_address (operands[0], DFmode, 0);")
 
-(define_insn "sse2_movsd"
-  [(set (match_operand:V2DF 0 "nonimmediate_operand"   "=x,v,x,v,m,x,x,v,o")
-	(vec_merge:V2DF
-	  (match_operand:V2DF 2 "nonimmediate_operand" " x,v,m,m,v,0,0,v,0")
-	  (match_operand:V2DF 1 "nonimmediate_operand" " 0,v,0,v,0,x,o,o,v")
+(define_insn "sse2_movsd_<mode>"
+  [(set (match_operand:VI8F_128 0 "nonimmediate_operand"   "=x,v,x,v,m,x,x,v,o")
+	(vec_merge:VI8F_128
+	  (match_operand:VI8F_128 2 "nonimmediate_operand" " x,v,m,m,v,0,0,v,0")
+	  (match_operand:VI8F_128 1 "nonimmediate_operand" " 0,v,0,v,0,x,o,o,v")
 	  (const_int 1)))]
   "TARGET_SSE2"
   "@
diff --git a/gcc/testsuite/gcc.target/i386/sse-movss-4.c b/gcc/testsuite/gcc.target/i386/sse-movss-4.c
new file mode 100644
index 0000000..ec3019c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/sse-movss-4.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse" } */
+
+typedef unsigned int v4si __attribute__((vector_size(16)));
+typedef float v4sf __attribute__((vector_size(16)));
+
+v4si foo(v4si x,v4si y) { return (v4si){y[0],x[1],x[2],x[3]}; }
+v4sf bar(v4sf x,v4sf y) { return (v4sf){y[0],x[1],x[2],x[3]}; }
+
+/* { dg-final { scan-assembler-times "\tv?movss\t" 2 } } */
+/* { dg-final { scan-assembler-not "movaps" } } */
+/* { dg-final { scan-assembler-not "shufps" } } */
+/* { dg-final { scan-assembler-not "vpblendw" } } */
diff --git a/gcc/testsuite/gcc.target/i386/sse2-movsd-3.c b/gcc/testsuite/gcc.target/i386/sse2-movsd-3.c
new file mode 100644
index 0000000..fadbe2b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/sse2-movsd-3.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2" } */
+
+typedef unsigned long long v2di __attribute__((vector_size(16)));
+typedef double v2df __attribute__((vector_size(16)));
+
+v2di foo(v2di x,v2di y) { return (v2di){y[0],x[1]}; }
+v2df bar(v2df x,v2df y) { return (v2df){y[0],x[1]}; }
+
+/* { dg-final { scan-assembler-times "\tv?movsd\t" 2 } } */
+/* { dg-final { scan-assembler-not "v?shufpd" } } */
+/* { dg-final { scan-assembler-not "movdqa" } } */
+/* { dg-final { scan-assembler-not "pshufd" } } */
+/* { dg-final { scan-assembler-not "v?punpckldq" } } */
+/* { dg-final { scan-assembler-not "v?movq" } } */