nvptx: Add support for 64-bit mul.hi (and other) instructions

Now that the middle-end MULT_HIGHPART_EXPR pieces are in place, this
patch adds support for nvptx's mul.hi.s64 and mul.hi.u64 instructions,
as previously reviewed (provisionally pre-approved) back in August 2020:
https://gcc.gnu.org/pipermail/gcc-patches/2020-August/551373.html
Since then a few things have changed, so this patch uses the new
SMUL_HIGHPART and UMUL_HIGHPART RTX expressions, but the test cases
remain the same.  Like the x86_64 backend, this patch retains the
"trunc" forms of these instructions (while the RTL optimizers/combine
may still generate them).

Given that we're rapidly approaching stage 4, I also took the liberty
of including support in nvptx.md for a few other instructions.  With
the new 64-bit highpart multiplication instructions added above, we
can now provide a define_expand for efficient 64-bit (to 128-bit)
widening multiplications.  This patch also adds support for nvptx's
testp.infinite instruction (for implementing __builtin_isinf) and
the not.pred instruction.

As an example of the code generation improvements, the function
int foo(double x) { return __builtin_isinf(x); }
previously generated with -O2:

                mov.f64 %r26, %ar0;
                abs.f64 %r28, %r26;
                setp.leu.f64    %r31, %r28, 0d7fefffffffffffff;
                selp.u32        %r30, 1, 0, %r31;
                mov.u32 %r29, %r30;
                cvt.u16.u8      %r35, %r29;
                mov.u16 %r33, %r35;
                xor.b16 %r32, %r33, 1;
                cvt.u32.u16     %r34, %r32;
                cvt.u32.u8      %value, %r34;

and with this patch now generates:

                mov.f64 %r23, %ar0;
                testp.infinite.f64      %r24, %r23;
                selp.u32        %value, 1, 0, %r24;

This patch has been tested on nvptx-none hosted on x86_64-pc-linux-gnu
(including newlib) with a make and make -k check with no new failures.

gcc/ChangeLog:

	* config/nvptx/nvptx.md (UNSPEC_ISINF): New UNSPEC.
	(one_cmplbi2): New define_insn for not.pred.
	(mulditi3): New define_expand for signed widening multiply.
	(umulditi3): New define_expand for unsigned widening multiply.
	(smul<mode>3_highpart): New define_insn for signed highpart mult.
	(umul<mode>3_highpart): New define_insn for unsigned highpart mult.
	(*smulhi3_highpart_2): Renamed from smulhi3_highpart.
	(*smulsi3_highpart_2): Renamed from smulsi3_highpart.
	(*umulhi3_highpart_2): Renamed from umulhi3_highpart.
	(*umulsi3_highpart_2): Renamed from umulsi3_highpart.
	(*setcc<mode>_from_not_bi): New define_insn.
	(*setcc_isinf<mode>): New define_insn for testp.infinite.
	(isinf<mode>2): New define_expand.

gcc/testsuite/ChangeLog:

	* gcc.target/nvptx/mul-hi64.c: New test case.
	* gcc.target/nvptx/umul-hi64.c: New test case.
	* gcc.target/nvptx/mul-wide64.c: New test case.
	* gcc.target/nvptx/umul-wide64.c: New test case.
	* gcc.target/nvptx/isinf.c: New test case.

1 files changed, 87 insertions, 4 deletions

diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md
index f53809ea..d19a687 100644
--- a/gcc/config/nvptx/nvptx.md
+++ b/gcc/config/nvptx/nvptx.md
@@ -27,6 +27,7 @@
    UNSPEC_SIN
    UNSPEC_COS
    UNSPEC_TANH
+   UNSPEC_ISINF
 
    UNSPEC_FPINT_FLOOR
    UNSPEC_FPINT_BTRUNC
@@ -596,6 +597,12 @@
   ""
   "%.\\tnot.b%T0\\t%0, %1;")
 
+(define_insn "one_cmplbi2"
+  [(set (match_operand:BI 0 "nvptx_register_operand" "=R")
+	(not:BI (match_operand:BI 1 "nvptx_register_operand" "R")))]
+  ""
+  "%.\\tnot.pred\\t%0, %1;")
+
 (define_insn "*cnot<mode>2"
   [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
 	(eq:HSDIM (match_operand:HSDIM 1 "nvptx_register_operand" "R")
@@ -671,7 +678,57 @@
   ""
   "%.\\tmul.wide.u32\\t%0, %1, %2;")
 
-(define_insn "smulhi3_highpart"
+(define_expand "mulditi3"
+  [(set (match_operand:TI 0 "nvptx_register_operand")
+	(mult:TI (sign_extend:TI
+		  (match_operand:DI 1 "nvptx_register_operand"))
+		 (sign_extend:DI
+		  (match_operand:DI 2 "nvptx_nonmemory_operand"))))]
+  ""
+{
+  rtx hi = gen_reg_rtx (DImode);
+  rtx lo = gen_reg_rtx (DImode);
+  emit_insn (gen_smuldi3_highpart (hi, operands[1], operands[2]));
+  emit_insn (gen_muldi3 (lo, operands[1], operands[2]));
+  emit_move_insn (gen_highpart (DImode, operands[0]), hi);
+  emit_move_insn (gen_lowpart (DImode, operands[0]), lo);
+  DONE;
+})
+
+(define_expand "umulditi3"
+  [(set (match_operand:TI 0 "nvptx_register_operand")
+	(mult:TI (zero_extend:TI
+		  (match_operand:DI 1 "nvptx_register_operand"))
+		 (zero_extend:DI
+		  (match_operand:DI 2 "nvptx_nonmemory_operand"))))]
+  ""
+{
+  rtx hi = gen_reg_rtx (DImode);
+  rtx lo = gen_reg_rtx (DImode);
+  emit_insn (gen_umuldi3_highpart (hi, operands[1], operands[2]));
+  emit_insn (gen_muldi3 (lo, operands[1], operands[2]));
+  emit_move_insn (gen_highpart (DImode, operands[0]), hi);
+  emit_move_insn (gen_lowpart (DImode, operands[0]), lo);
+  DONE;
+})
+
+(define_insn "smul<mode>3_highpart"
+  [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
+	(smul_highpart:HSDIM
+	  (match_operand:HSDIM 1 "nvptx_register_operand" "R")
+	  (match_operand:HSDIM 2 "nvptx_nonmemory_operand" "Ri")))]
+  ""
+  "%.\\tmul.hi.s%T0\\t%0, %1, %2;")
+
+(define_insn "umul<mode>3_highpart"
+  [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
+	(umul_highpart:HSDIM
+	  (match_operand:HSDIM 1 "nvptx_register_operand" "R")
+	  (match_operand:HSDIM 2 "nvptx_nonmemory_operand" "Ri")))]
+  ""
+  "%.\\tmul.hi.u%T0\\t%0, %1, %2;")
+
+(define_insn "*smulhi3_highpart_2"
   [(set (match_operand:HI 0 "nvptx_register_operand" "=R")
 	(truncate:HI
 	 (lshiftrt:SI
@@ -683,7 +740,7 @@
   ""
   "%.\\tmul.hi.s16\\t%0, %1, %2;")
 
-(define_insn "smulsi3_highpart"
+(define_insn "*smulsi3_highpart_2"
   [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
 	(truncate:SI
 	 (lshiftrt:DI
@@ -695,7 +752,7 @@
   ""
   "%.\\tmul.hi.s32\\t%0, %1, %2;")
 
-(define_insn "umulhi3_highpart"
+(define_insn "*umulhi3_highpart_2"
   [(set (match_operand:HI 0 "nvptx_register_operand" "=R")
 	(truncate:HI
 	 (lshiftrt:SI
@@ -707,7 +764,7 @@
   ""
   "%.\\tmul.hi.u16\\t%0, %1, %2;")
 
-(define_insn "umulsi3_highpart"
+(define_insn "*umulsi3_highpart_2"
   [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
 	(truncate:SI
 	 (lshiftrt:DI
@@ -885,6 +942,13 @@
   ""
   "%.\\tselp%t0\\t%0, 1, 0, %1;")
 
+(define_insn "*setcc<mode>_from_not_bi"
+  [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
+	(eq:HSDIM (match_operand:BI 1 "nvptx_register_operand" "R")
+		   (const_int 0)))]
+  ""
+  "%.\\tselp%t0\\t%0, 0, 1, %1;")
+
 (define_insn "extendbi<mode>2"
   [(set (match_operand:QHSDIM 0 "nvptx_register_operand" "=R")
 	(sign_extend:QHSDIM
@@ -1160,6 +1224,25 @@
   "flag_unsafe_math_optimizations"
   "%.\\tex2.approx%t0\\t%0, %1;")
 
+(define_insn "setcc_isinf<mode>"
+  [(set (match_operand:BI 0 "nvptx_register_operand" "=R")
+	(unspec:BI [(match_operand:SDFM 1 "nvptx_register_operand" "R")]
+		   UNSPEC_ISINF))]
+  ""
+  "%.\\ttestp.infinite%t1\\t%0, %1;")
+
+(define_expand "isinf<mode>2"
+  [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
+	(unspec:SI [(match_operand:SDFM 1 "nvptx_register_operand" "R")]
+		   UNSPEC_ISINF))]
+  ""
+{
+  rtx pred = gen_reg_rtx (BImode);
+  emit_insn (gen_setcc_isinf<mode> (pred, operands[1]));
+  emit_insn (gen_setccsi_from_bi (operands[0], pred));
+  DONE;
+})
+
 ;; HFmode floating point arithmetic.
 
 (define_insn "addhf3"