[v3] RISC-V: Bugfix for legitimize move when get vec mode in zve32f

From: Pan Li <pan2.li@intel.com>

If we want to extract 64bit value but ELEN < 64, we use RVV
vector mode with EEW = 32 to extract the highpart and lowpart.
However, this approach doesn't honor DFmode when movdf pattern
when ZVE32f and of course results in ICE when zve32f.

This patch would like to reuse the approach with some additional
handing, consider lowpart bits is meaningless for FP mode, we need
one int reg as bridge here. For example:

rtx tmp = gen_rtx_reg (DImode)
reg:DI = reg:DF (fmv.d.x) // Move DF reg to DI
...
perform the extract for high and low parts
...
reg:DF = reg:DI (fmv.x.d) // Move DI reg back to DF after all done

	PR target/112743

gcc/ChangeLog:

	* config/riscv/riscv.cc (riscv_legitimize_move): Take the
	exist (U *mode) and handle DFmode like DImode when EEW is
	32bits for ZVE32F.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/base/pr112743-2.c: New test.

Signed-off-by: Pan Li <pan2.li@intel.com>
---
 gcc/config/riscv/riscv.cc                     | 63 +++++++++++++------
 .../gcc.target/riscv/rvv/base/pr112743-2.c    | 52 +++++++++++++++
 2 files changed, 95 insertions(+), 20 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112743-2.c

One more comment:

+      unsigned int num = (smode == DImode || smode == DFmode)
+ && !TARGET_VECTOR_ELEN_64 ? 2 : 1;

change it into:

unsigned int num = known_eq (GET_MODE_SIZE (smode), 8) && !TARGET_VECTOR_ELEN_64 ? 2 : 1;



juzhe.zhong@rivai.ai
 
From: pan2.li
Date: 2023-12-01 18:11
To: gcc-patches
CC: juzhe.zhong; pan2.li; yanzhang.wang; kito.cheng
Subject: [PATCH v3] RISC-V: Bugfix for legitimize move when get vec mode in zve32f
From: Pan Li <pan2.li@intel.com>
 
If we want to extract 64bit value but ELEN < 64, we use RVV
vector mode with EEW = 32 to extract the highpart and lowpart.
However, this approach doesn't honor DFmode when movdf pattern
when ZVE32f and of course results in ICE when zve32f.
 
This patch would like to reuse the approach with some additional
handing, consider lowpart bits is meaningless for FP mode, we need
one int reg as bridge here. For example:
 
rtx tmp = gen_rtx_reg (DImode)
reg:DI = reg:DF (fmv.d.x) // Move DF reg to DI
...
perform the extract for high and low parts
...
reg:DF = reg:DI (fmv.x.d) // Move DI reg back to DF after all done
 
PR target/112743
 
gcc/ChangeLog:
 
* config/riscv/riscv.cc (riscv_legitimize_move): Take the
exist (U *mode) and handle DFmode like DImode when EEW is
32bits for ZVE32F.
 
gcc/testsuite/ChangeLog:
 
* gcc.target/riscv/rvv/base/pr112743-2.c: New test.
 
Signed-off-by: Pan Li <pan2.li@intel.com>
---
gcc/config/riscv/riscv.cc                     | 63 +++++++++++++------
.../gcc.target/riscv/rvv/base/pr112743-2.c    | 52 +++++++++++++++
2 files changed, 95 insertions(+), 20 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112743-2.c
 
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index a4fc858fb50..2fbaaf01078 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -2605,41 +2605,64 @@ riscv_legitimize_move (machine_mode mode, rtx dest, rtx src)
       unsigned int nunits = vmode_size > mode_size ? vmode_size / mode_size : 1;
       scalar_mode smode = as_a<scalar_mode> (mode);
       unsigned int index = SUBREG_BYTE (src).to_constant () / mode_size;
-      unsigned int num = smode == DImode && !TARGET_VECTOR_ELEN_64 ? 2 : 1;
+      unsigned int num = (smode == DImode || smode == DFmode)
+ && !TARGET_VECTOR_ELEN_64 ? 2 : 1;
+      bool need_int_reg_p = false;
       if (num == 2)
{
  /* If we want to extract 64bit value but ELEN < 64,
     we use RVV vector mode with EEW = 32 to extract
     the highpart and lowpart.  */
+   need_int_reg_p = smode == DFmode;
  smode = SImode;
  nunits = nunits * 2;
}
-      vmode = riscv_vector::get_vector_mode (smode, nunits).require ();
-      rtx v = gen_lowpart (vmode, SUBREG_REG (src));
-      for (unsigned int i = 0; i < num; i++)
+      if (riscv_vector::get_vector_mode (smode, nunits).exists (&vmode))
{
-   rtx result;
-   if (num == 1)
-     result = dest;
-   else if (i == 0)
-     result = gen_lowpart (smode, dest);
-   else
-     result = gen_reg_rtx (smode);
-   riscv_vector::emit_vec_extract (result, v, index + i);
+   rtx v = gen_lowpart (vmode, SUBREG_REG (src));
+   rtx int_reg = dest;
-   if (i == 1)
+   if (need_int_reg_p)
    {
-       rtx tmp
- = expand_binop (Pmode, ashl_optab, gen_lowpart (Pmode, result),
- gen_int_mode (32, Pmode), NULL_RTX, 0,
- OPTAB_DIRECT);
-       rtx tmp2 = expand_binop (Pmode, ior_optab, tmp, dest, NULL_RTX, 0,
-        OPTAB_DIRECT);
-       emit_move_insn (dest, tmp2);
+       int_reg = gen_reg_rtx (DImode);
+       emit_move_insn (int_reg, gen_lowpart (GET_MODE (int_reg), dest));
    }
+
+   for (unsigned int i = 0; i < num; i++)
+     {
+       rtx result;
+       if (num == 1)
+ result = int_reg;
+       else if (i == 0)
+ result = gen_lowpart (smode, int_reg);
+       else
+ result = gen_reg_rtx (smode);
+
+       riscv_vector::emit_vec_extract (result, v, index + i);
+
+       if (i == 1)
+ {
+   rtx tmp = expand_binop (Pmode, ashl_optab,
+   gen_lowpart (Pmode, result),
+   gen_int_mode (32, Pmode), NULL_RTX, 0,
+   OPTAB_DIRECT);
+   rtx tmp2 = expand_binop (Pmode, ior_optab, tmp, int_reg,
+    NULL_RTX, 0,
+    OPTAB_DIRECT);
+   emit_move_insn (int_reg, tmp2);
+ }
+     }
+
+   if (need_int_reg_p)
+     emit_move_insn (dest, gen_lowpart (GET_MODE (dest), int_reg));
+   else
+     emit_move_insn (dest, int_reg);
}
+      else
+ gcc_unreachable ();
+
       return true;
     }
   /* Expand
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112743-2.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112743-2.c
new file mode 100644
index 00000000000..fdb35fd70f2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112743-2.c
@@ -0,0 +1,52 @@
+/* Test that we do not have ice when compile */
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zve32f_zvfh_zfh -mabi=lp64 -O2" } */
+
+#include <sys/types.h>
+
+union double_union
+{
+  double d;
+  __uint32_t i[2];
+};
+
+#define word0(x)  (x.i[1])
+#define word1(x)  (x.i[0])
+
+#define P         53
+#define Exp_shift 20
+#define Exp_msk1  ((__uint32_t)0x100000L)
+#define Exp_mask  ((__uint32_t)0x7ff00000L)
+
+double ulp (double _x)
+{
+  union double_union x, a;
+  register int L;
+
+  x.d = _x;
+  L = (word0 (x) & Exp_mask) - (P - 1) * Exp_msk1;
+
+  if (L > 0)
+    {
+      L |= Exp_msk1 >> 4;
+      word0 (a) = L;
+      word1 (a) = 0;
+    }
+  else
+    {
+      L = -L >> Exp_shift;
+      if (L < Exp_shift)
+ {
+   word0 (a) = 0x80000 >> L;
+   word1 (a) = 0;
+ }
+      else
+ {
+   word0 (a) = 0;
+   L -= Exp_shift;
+   word1 (a) = L >= 31 ? 1 : 1 << (31 - L);
+ }
+    }
+
+  return a.d;
+}