vsx.md (UNSPEC_P9_MEMORY): New unspec to support loading and storing…

vsx.md (UNSPEC_P9_MEMORY): New unspec to support loading and storing byte/half-word values in the vector...

[gcc]
2016-06-27  Michael Meissner  <meissner@linux.vnet.ibm.com>

	* config/rs6000/vsx.md (UNSPEC_P9_MEMORY): New unspec to support
	loading and storing byte/half-word values in the vector registers.
	(vsx_sign_extend_hi_<mode>): Enable the generator function.
	(p9_lxsi<wd>zx): New insns to load zero-extended bytes and
	half-words on ISA 3.0 to the vector registers.
	(p9_stxsi<wd>zx): New insns to store zero-extended bytes and
	half-words on ISA 3.0 from the vector registers.
	* config/rs6000/rs6000.md (FP_ISA3): New iterator to optimize
	converting char/half-word items to floating point on ISA 3.0.
	(float<QHI:mode><FP_ISA3:mode>2): On ISA 3.0 generate the lxsihzx
	and lxsibzx instructions if we are converting an 8-bit or 16-bit
	item from memory to floating point.
	(float<QHI:mode><FP_ISA3:mode>2_internal): Likewise.
	(floatuns<QHI:mode><FP_ISA3:mode>2): Likewise.
	(floatuns<QHI:mode><FP_ISA3:mode>2_internal): Likewise.
	(fix_trunc<SFDF:mode><QHI:mode>2): On ISA 3.0 generate the stxsihx
	and stxsibx instructions to store floating point values converted
	to 8 or 16-bit integers.
	(fixuns_trunc<mode>si2): Likewise.

[gcc/testsuite]
2016-06-27  Michael Meissner  <meissner@linux.vnet.ibm.com>

	* gcc.target/powerpc/p9-fpcvt-1.c: New test to test ISA 3.0 load
	byte/half-word to vector registers and store byte/half-word from
	vector register instructions.
	* gcc.target/powerpc/p9-fpcvt-2.c: Likewise.

From-SVN: r237806

gcc/config/rs6000/rs6000.md

@@ -506,6 +506,12 @@
 				(IF "TARGET_FLOAT128")
 				(TF "TARGET_LONG_DOUBLE_128")])
 
+; Iterator for ISA 3.0 supported floating point types
+(define_mode_iterator FP_ISA3 [SF
+			       DF
+			       (KF "FLOAT128_IEEE_P (KFmode)")
+			       (TF "FLOAT128_IEEE_P (TFmode)")])
+
 ; SF/DF suffix for traditional floating instructions
 (define_mode_attr Ftrad		[(SF "s") (DF "")])
 
@@ -5188,6 +5194,107 @@
   [(set_attr "length" "20")
    (set_attr "type" "fp")])
 
+;; ISA 3.0 adds instructions lxsi[bh]zx to directly load QImode and HImode to
+;; vector registers.  At the moment, QI/HImode are not allowed in floating
+;; point or vector registers, so we use UNSPEC's to use the load byte and
+;; half-word instructions.
+
+(define_expand "float<QHI:mode><FP_ISA3:mode>2"
+  [(parallel [(set (match_operand:FP_ISA3 0 "vsx_register_operand")
+		   (float:FP_ISA3
+		    (match_operand:QHI 1 "input_operand")))
+	      (clobber (match_scratch:DI 2))
+	      (clobber (match_scratch:DI 3))])]
+  "TARGET_P9_VECTOR && TARGET_DIRECT_MOVE && TARGET_POWERPC64"
+{
+  if (MEM_P (operands[1]))
+    operands[1] = rs6000_address_for_fpconvert (operands[1]);
+})
+
+(define_insn_and_split "*float<QHI:mode><FP_ISA3:mode>2_internal"
+  [(set (match_operand:FP_ISA3 0 "vsx_register_operand" "=<Fv>,<Fv>")
+	(float:FP_ISA3
+	 (match_operand:QHI 1 "reg_or_indexed_operand" "r,Z")))
+   (clobber (match_scratch:DI 2 "=wi,v"))
+   (clobber (match_scratch:DI 3 "=r,X"))]
+  "TARGET_P9_VECTOR && TARGET_DIRECT_MOVE && TARGET_POWERPC64
+   && TARGET_UPPER_REGS_DI"
+  "#"
+  "&& reload_completed"
+  [(const_int 0)]
+{
+  rtx result = operands[0];
+  rtx input = operands[1];
+  rtx di = operands[2];
+
+  if (!MEM_P (input))
+    {
+      rtx tmp = operands[3];
+      emit_insn (gen_extend<QHI:mode>di2 (tmp, input));
+      emit_move_insn (di, tmp);
+    }
+  else
+    {
+      machine_mode vmode;
+      rtx di_vector;
+
+      emit_insn (gen_p9_lxsi<QHI:wd>zx (di, input));
+
+      if (<MODE>mode == QImode)
+	vmode = V16QImode;
+      else if (<MODE>mode == HImode)
+	vmode = V8HImode;
+      else
+	gcc_unreachable ();
+
+      di_vector = gen_rtx_REG (vmode, REGNO (di));
+      emit_insn (gen_vsx_sign_extend_<QHI:mode>_di (di, di_vector));
+    }
+
+  emit_insn (gen_floatdi<FP_ISA3:mode>2 (result, di));
+  DONE;
+})
+
+(define_expand "floatuns<QHI:mode><FP_ISA3:mode>2"
+  [(parallel [(set (match_operand:FP_ISA3 0 "vsx_register_operand" "")
+		   (unsigned_float:FP_ISA3
+		    (match_operand:QHI 1 "input_operand" "")))
+	      (clobber (match_scratch:DI 2 ""))
+	      (clobber (match_scratch:DI 3 ""))])]
+  "TARGET_P9_VECTOR && TARGET_DIRECT_MOVE && TARGET_POWERPC64"
+{
+  if (MEM_P (operands[1]))
+    operands[1] = rs6000_address_for_fpconvert (operands[1]);
+})
+
+(define_insn_and_split "*floatuns<QHI:mode><FP_ISA3:mode>2_internal"
+  [(set (match_operand:FP_ISA3 0 "vsx_register_operand" "=<Fv>,<Fv>")
+	(unsigned_float:FP_ISA3
+	 (match_operand:QHI 1 "reg_or_indexed_operand" "r,Z")))
+   (clobber (match_scratch:DI 2 "=wi,wi"))
+   (clobber (match_scratch:DI 3 "=r,X"))]
+  "TARGET_P9_VECTOR && TARGET_DIRECT_MOVE && TARGET_POWERPC64"
+  "#"
+  "&& reload_completed"
+  [(const_int 0)]
+{
+  rtx result = operands[0];
+  rtx input = operands[1];
+  rtx di = operands[2];
+  rtx tmp = operands[3];
+
+  if (!MEM_P (input))
+    {
+      emit_insn (gen_zero_extend<QHI:mode>di2 (tmp, input));
+      emit_move_insn (di, tmp);
+    }
+  else
+    emit_insn (gen_p9_lxsi<QHI:wd>zx (di, input));
+
+  emit_insn (gen_floatdi<FP_ISA3:mode>2 (result, di));
+  DONE;
+})
+
 (define_expand "fix_trunc<mode>si2"
   [(set (match_operand:SI 0 "gpc_reg_operand" "")
 	(fix:SI (match_operand:SFDF 1 "gpc_reg_operand" "")))]
@@ -5296,6 +5403,23 @@
    xscvdpsxds %x0,%x1"
   [(set_attr "type" "fp")])
 
+(define_expand "fix_trunc<SFDF:mode><QHI:mode>2"
+  [(use (match_operand:QHI 0 "rs6000_nonimmediate_operand" ""))
+   (use (match_operand:SFDF 1 "vsx_register_operand" ""))]
+  "TARGET_P9_VECTOR && TARGET_DIRECT_MOVE && TARGET_POWERPC64"
+{
+  rtx op0 = operands[0];
+  rtx op1 = operands[1];
+  rtx di_tmp = gen_reg_rtx (DImode);
+
+  if (MEM_P (op0))
+    op0 = rs6000_address_for_fpconvert (op0);
+
+  emit_insn (gen_fctiwz_<SFDF:mode> (di_tmp, op1));
+  emit_insn (gen_p9_stxsi<QHI:wd>x (op0, di_tmp));
+  DONE;
+})
+
 (define_expand "fixuns_trunc<mode>si2"
   [(set (match_operand:SI 0 "gpc_reg_operand" "")
 	(unsigned_fix:SI (match_operand:SFDF 1 "gpc_reg_operand" "")))]
@@ -5368,6 +5492,23 @@
    xscvdpuxds %x0,%x1"
   [(set_attr "type" "fp")])
 
+(define_expand "fixuns_trunc<SFDF:mode><QHI:mode>2"
+  [(use (match_operand:QHI 0 "rs6000_nonimmediate_operand" ""))
+   (use (match_operand:SFDF 1 "vsx_register_operand" ""))]
+  "TARGET_P9_VECTOR && TARGET_DIRECT_MOVE && TARGET_POWERPC64"
+{
+  rtx op0 = operands[0];
+  rtx op1 = operands[1];
+  rtx di_tmp = gen_reg_rtx (DImode);
+
+  if (MEM_P (op0))
+    op0 = rs6000_address_for_fpconvert (op0);
+
+  emit_insn (gen_fctiwuz_<SFDF:mode> (di_tmp, op1));
+  emit_insn (gen_p9_stxsi<QHI:wd>x (op0, di_tmp));
+  DONE;
+})
+
 ; Here, we use (set (reg) (unspec:DI [(fix:SI ...)] UNSPEC_FCTIWZ))
 ; rather than (set (subreg:SI (reg)) (fix:SI ...))
 ; because the first makes it clear that operand 0 is not live

gcc/config/rs6000/vsx.md

@@ -293,6 +293,7 @@
    UNSPEC_VSX_XVCVDPSXDS
    UNSPEC_VSX_XVCVDPUXDS
    UNSPEC_VSX_SIGN_EXTEND
+   UNSPEC_P9_MEMORY
   ])
 
 ;; VSX moves
@@ -2705,7 +2706,7 @@
   "vextsb2<wd> %0,%1"
   [(set_attr "type" "vecsimple")])
 
-(define_insn "*vsx_sign_extend_hi_<mode>"
+(define_insn "vsx_sign_extend_hi_<mode>"
   [(set (match_operand:VSINT_84 0 "vsx_register_operand" "=v")
 	(unspec:VSINT_84
 	 [(match_operand:V8HI 1 "vsx_register_operand" "v")]
@@ -2721,3 +2722,24 @@
   "TARGET_P9_VECTOR"
   "vextsw2d %0,%1"
   [(set_attr "type" "vecsimple")])
+
+
+;; ISA 3.0 memory operations
+(define_insn "p9_lxsi<wd>zx"
+  [(set (match_operand:DI 0 "vsx_register_operand" "=wi")
+	(unspec:DI [(zero_extend:DI
+		     (match_operand:QHI 1 "indexed_or_indirect_operand" "Z"))]
+		   UNSPEC_P9_MEMORY))]
+  "TARGET_P9_VECTOR"
+  "lxsi<wd>zx %x0,%y1"
+  [(set_attr "type" "fpload")])
+
+(define_insn "p9_stxsi<wd>x"
+  [(set (match_operand:QHI 0 "reg_or_indexed_operand" "=r,Z")
+	(unspec:QHI [(match_operand:DI 1 "vsx_register_operand" "wi,wi")]
+		    UNSPEC_P9_MEMORY))]
+  "TARGET_P9_VECTOR"
+  "@
+   mfvsrd %0,%x1
+   stxsi<wd>x %x1,%y0"
+  [(set_attr "type" "mffgpr,fpstore")])

gcc/testsuite/gcc.target/powerpc/p9-fpcvt-1.c

+/* { dg-do compile { target { powerpc64*-*-* && lp64 } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-mcpu=power9 -O2" } */
+
+void sc (signed char    *p, double x) { *p = x; }
+void uc (unsigned char  *p, double x) { *p = x; }
+void ss (signed short   *p, double x) { *p = x; }
+void us (unsigned short *p, double x) { *p = x; }
+
+/* { dg-final { scan-assembler     "stxsibx" } } */
+/* { dg-final { scan-assembler     "stxsihx" } } */
+/* { dg-final { scan-assembler-not "mfvsrd"  } } */
+/* { dg-final { scan-assembler-not "mfvsrwz" } } */
+/* { dg-final { scan-assembler-not "mtvsrd"  } } */
+/* { dg-final { scan-assembler-not "mtvsrwa" } } */
+/* { dg-final { scan-assembler-not "mtvsrwz" } } */

gcc/testsuite/gcc.target/powerpc/p9-fpcvt-2.c

+/* { dg-do compile { target { powerpc64*-*-* && lp64 } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-mcpu=power9 -O2" } */
+
+double sc (signed char    *p) { return (double)*p; }
+double uc (unsigned char  *p) { return (double)*p; }
+double ss (signed short   *p) { return (double)*p; }
+double us (unsigned short *p) { return (double)*p; }
+
+/* { dg-final { scan-assembler     "lxsibzx"  } } */
+/* { dg-final { scan-assembler     "lxsihzx"  } } */
+/* { dg-final { scan-assembler     "vextsb2d" } } */
+/* { dg-final { scan-assembler     "vextsh2d" } } */
+/* { dg-final { scan-assembler-not "mfvsrd"   } } */
+/* { dg-final { scan-assembler-not "mfvsrwz"  } } */
+/* { dg-final { scan-assembler-not "mtvsrd"   } } */
+/* { dg-final { scan-assembler-not "mtvsrwa"  } } */
+/* { dg-final { scan-assembler-not "mtvsrwz"  } } */