[nvptx] Handle V2DI/V2SI mode in nvptx_gen_shuffle

With the pr96628-part1.f90 source and -ftree-slp-vectorize, we run into an
ICE due to the fact that V2DI mode is not handled in nvptx_gen_shuffle.

Fix this by adding handling of V2DI as well as V2SI mode in
nvptx_gen_shuffle.

Build and reg-tested on x86_64 with nvptx accelerator.

gcc/ChangeLog:

	PR target/96428
	* config/nvptx/nvptx.c (nvptx_gen_shuffle): Handle V2SI/V2DI.

libgomp/ChangeLog:

	PR target/96428
	* testsuite/libgomp.oacc-fortran/pr96628-part1.f90: New test.
	* testsuite/libgomp.oacc-fortran/pr96628-part2.f90: New test.

diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index d8a8fb2..cf53a92 100644 (file)
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -1796,6 +1796,44 @@ nvptx_gen_shuffle (rtx dst, rtx src, rtx idx, nvptx_shuffle_kind kind)
        end_sequence ();
       }
       break;
+    case E_V2SImode:
+      {
+       rtx src0 = gen_rtx_SUBREG (SImode, src, 0);
+       rtx src1 = gen_rtx_SUBREG (SImode, src, 4);
+       rtx dst0 = gen_rtx_SUBREG (SImode, dst, 0);
+       rtx dst1 = gen_rtx_SUBREG (SImode, dst, 4);
+       rtx tmp0 = gen_reg_rtx (SImode);
+       rtx tmp1 = gen_reg_rtx (SImode);
+       start_sequence ();
+       emit_insn (gen_movsi (tmp0, src0));
+       emit_insn (gen_movsi (tmp1, src1));
+       emit_insn (nvptx_gen_shuffle (tmp0, tmp0, idx, kind));
+       emit_insn (nvptx_gen_shuffle (tmp1, tmp1, idx, kind));
+       emit_insn (gen_movsi (dst0, tmp0));
+       emit_insn (gen_movsi (dst1, tmp1));
+       res = get_insns ();
+       end_sequence ();
+      }
+      break;
+    case E_V2DImode:
+      {
+       rtx src0 = gen_rtx_SUBREG (DImode, src, 0);
+       rtx src1 = gen_rtx_SUBREG (DImode, src, 8);
+       rtx dst0 = gen_rtx_SUBREG (DImode, dst, 0);
+       rtx dst1 = gen_rtx_SUBREG (DImode, dst, 8);
+       rtx tmp0 = gen_reg_rtx (DImode);
+       rtx tmp1 = gen_reg_rtx (DImode);
+       start_sequence ();
+       emit_insn (gen_movdi (tmp0, src0));
+       emit_insn (gen_movdi (tmp1, src1));
+       emit_insn (nvptx_gen_shuffle (tmp0, tmp0, idx, kind));
+       emit_insn (nvptx_gen_shuffle (tmp1, tmp1, idx, kind));
+       emit_insn (gen_movdi (dst0, tmp0));
+       emit_insn (gen_movdi (dst1, tmp1));
+       res = get_insns ();
+       end_sequence ();
+      }
+      break;
     case E_BImode:
       {
        rtx tmp = gen_reg_rtx (SImode);

diff --git a/libgomp/testsuite/libgomp.oacc-fortran/pr96628-part1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/pr96628-part1.f90
new file mode 100644 (file)
index 0000000..71219f9
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/pr96628-part1.f90
@@ -0,0 +1,20 @@
+! { dg-do run }
+! { dg-additional-sources pr96628-part2.f90 }
+! { dg-additional-options "-ftree-slp-vectorize" }
+!
+! This file is compiled first
+module m2
+  real*8 :: mysum
+  !$acc declare device_resident(mysum)
+contains
+    SUBROUTINE one(t)
+      !$acc routine
+      REAL*8,  INTENT(IN)    :: t(:)
+      mysum = sum(t)
+    END SUBROUTINE one
+    SUBROUTINE two(t)
+      !$acc routine seq
+      REAL*8, INTENT(INOUT) :: t(:)
+      t = (100.0_8*t)/sum
+    END SUBROUTINE two
+end module m2

diff --git a/libgomp/testsuite/libgomp.oacc-fortran/pr96628-part2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/pr96628-part2.f90
new file mode 100644 (file)
index 0000000..784dc27
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/pr96628-part2.f90
@@ -0,0 +1,37 @@
+! { dg-do compile  { target skip-all-targets } }
+!
+! Main file is pr96628-part1.f90
+
+MODULE m
+  IMPLICIT NONE
+  REAL*8, ALLOCATABLE :: t(:)
+CONTAINS
+  SUBROUTINE run()
+    use m2
+    IMPLICIT NONE
+
+    INTEGER :: i,j    ! loop indices
+    !$acc data present(t)
+    !$acc parallel
+    !$acc loop gang
+    DO j = 1,2
+      !$acc loop vector
+      DO i = 1,2
+        CALL one(t(:))
+        CALL two(t(:))
+      END DO
+   END DO
+   !$acc end parallel
+   !$acc end data
+  END SUBROUTINE run
+END MODULE m
+
+use m
+implicit none
+integer :: i
+t = [(3.0_8*i, i = 1, 100)]
+!$acc data copy(t)
+call run
+!$acc end data
+if (any (abs(t - [((300.0_8*i)/15150.0_8, i = 1, 100)]) < 10.0_8*epsilon(t))) stop 1
+end