RISC-V: Fix regression of -fzero-call-used-regs=all [PR109104]

This patch registers a riscv specific function to
TARGET_ZERO_CALL_USED_REGS instead of default in targhooks.cc. It will
clean gpr and vector relevant registers.

gcc/ChangeLog:

	PR target/109104
	* config/riscv/riscv-protos.h (emit_hard_vlmax_vsetvl): New.
	* config/riscv/riscv-v.cc (emit_hard_vlmax_vsetvl): New.
	(emit_vlmax_vsetvl): Use emit_hard_vlmax_vsetvl.
	* config/riscv/riscv.cc (vector_zero_call_used_regs): New.
	(riscv_zero_call_used_regs): New.
	(TARGET_ZERO_CALL_USED_REGS): New.

gcc/testsuite/ChangeLog:

	PR target/109104
	* gcc.target/riscv/zero-scratch-regs-1.c: New test.
	* gcc.target/riscv/zero-scratch-regs-2.c: New test.
	* gcc.target/riscv/zero-scratch-regs-3.c: New test.

Signed-off-by: Yanzhang Wang <yanzhang.wang@intel.com>
Co-authored-by: Pan Li <pan2.li@intel.com>
Co-authored-by: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>
Co-authored-by: Kito Cheng <kito.cheng@sifive.com>

diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index 4611447dddeb0f7f160678eb5228459f12e5d4d0..5244e8dcbf0a69f1e6c5ed3d4f81c62b7ffe0cd6 100644 (file)
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -159,6 +159,7 @@ bool check_builtin_call (location_t, vec<location_t>, unsigned int,
 bool const_vec_all_same_in_range_p (rtx, HOST_WIDE_INT, HOST_WIDE_INT);
 bool legitimize_move (rtx, rtx, machine_mode);
 void emit_vlmax_vsetvl (machine_mode, rtx);
+void emit_hard_vlmax_vsetvl (machine_mode, rtx);
 void emit_vlmax_op (unsigned, rtx, rtx, machine_mode);
 void emit_vlmax_op (unsigned, rtx, rtx, rtx, machine_mode);
 void emit_nonvlmax_op (unsigned, rtx, rtx, rtx, machine_mode);

diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 2e91d019f6cd8b7619d3e73bf15b7592d609934c..392f5d02e17c0ce6c5d76a2248343f70ba41a4c6 100644 (file)
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -118,6 +118,17 @@ const_vec_all_same_in_range_p (rtx x, HOST_WIDE_INT minval,
          && IN_RANGE (INTVAL (elt), minval, maxval));
 }
 
+/* Emit a vlmax vsetvl instruction.  This should only be used when
+   optimization is disabled or after vsetvl insertion pass.  */
+void
+emit_hard_vlmax_vsetvl (machine_mode vmode, rtx vl)
+{
+  unsigned int sew = get_sew (vmode);
+  emit_insn (gen_vsetvl (Pmode, vl, RVV_VLMAX, gen_int_mode (sew, Pmode),
+                        gen_int_mode (get_vlmul (vmode), Pmode), const0_rtx,
+                        const0_rtx));
+}
+
 void
 emit_vlmax_vsetvl (machine_mode vmode, rtx vl)
 {
@@ -126,9 +137,7 @@ emit_vlmax_vsetvl (machine_mode vmode, rtx vl)
   unsigned int ratio = calculate_ratio (sew, vlmul);
 
   if (!optimize)
-    emit_insn (gen_vsetvl (Pmode, vl, RVV_VLMAX, gen_int_mode (sew, Pmode),
-                          gen_int_mode (get_vlmul (vmode), Pmode), const0_rtx,
-                          const0_rtx));
+    emit_hard_vlmax_vsetvl (vmode, vl);
   else
     emit_insn (gen_vlmax_avl (Pmode, vl, gen_int_mode (ratio, Pmode)));
 }

diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index 5f542932d13ce69aae2fb088087cfc1e2533769e..dc47434fac424b7a2c08b203e9a837923b4b0e92 100644 (file)
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -7066,6 +7066,77 @@ riscv_shamt_matches_mask_p (int shamt, HOST_WIDE_INT mask)
   return shamt == ctz_hwi (mask);
 }
 
+static HARD_REG_SET
+vector_zero_call_used_regs (HARD_REG_SET need_zeroed_hardregs)
+{
+  HARD_REG_SET zeroed_hardregs;
+  CLEAR_HARD_REG_SET (zeroed_hardregs);
+
+  /* Find a register to hold vl.  */
+  unsigned vl_regno = INVALID_REGNUM;
+  /* Skip the first GPR, otherwise the existing vl is kept due to the same
+     between vl and avl.  */
+  for (unsigned regno = GP_REG_FIRST + 1; regno <= GP_REG_LAST; regno++)
+    {
+      if (TEST_HARD_REG_BIT (need_zeroed_hardregs, regno))
+       {
+         vl_regno = regno;
+         break;
+       }
+    }
+
+  if (vl_regno > GP_REG_LAST)
+    sorry ("cannot allocate vl register for %qs on this target",
+          "-fzero-call-used-regs");
+
+  /* Vector configurations need not be saved and restored here.  The
+     -fzero-call-used-regs=* option will zero all vector registers and
+     return.  So there's no vector operations between them.  */
+
+  bool emitted_vlmax_vsetvl = false;
+  rtx vl = gen_rtx_REG (Pmode, vl_regno); /* vl is VLMAX.  */
+  for (unsigned regno = V_REG_FIRST; regno <= V_REG_LAST; ++regno)
+    {
+      if (TEST_HARD_REG_BIT (need_zeroed_hardregs, regno))
+       {
+         rtx target = regno_reg_rtx[regno];
+         machine_mode mode = GET_MODE (target);
+         poly_uint16 nunits = GET_MODE_NUNITS (mode);
+         machine_mode mask_mode
+           = riscv_vector::get_vector_mode (BImode, nunits).require ();
+
+         if (!emitted_vlmax_vsetvl)
+           {
+             riscv_vector::emit_hard_vlmax_vsetvl (mode, vl);
+             emitted_vlmax_vsetvl = true;
+           }
+
+         riscv_vector::emit_vlmax_op (code_for_pred_mov (mode), target,
+                                      CONST0_RTX (mode), vl, mask_mode);
+
+         SET_HARD_REG_BIT (zeroed_hardregs, regno);
+       }
+    }
+
+  return zeroed_hardregs;
+}
+
+/* Generate a sequence of instructions that zero registers specified by
+   NEED_ZEROED_HARDREGS.  Return the ZEROED_HARDREGS that are actually
+   zeroed.  */
+HARD_REG_SET
+riscv_zero_call_used_regs (HARD_REG_SET need_zeroed_hardregs)
+{
+  HARD_REG_SET zeroed_hardregs;
+  CLEAR_HARD_REG_SET (zeroed_hardregs);
+
+  if (TARGET_VECTOR)
+    zeroed_hardregs |= vector_zero_call_used_regs (need_zeroed_hardregs);
+
+  return zeroed_hardregs | default_zero_call_used_regs (need_zeroed_hardregs
+                                                       & ~zeroed_hardregs);
+}
+
 /* Initialize the GCC target structure.  */
 #undef TARGET_ASM_ALIGNED_HI_OP
 #define TARGET_ASM_ALIGNED_HI_OP "\t.half\t"
@@ -7317,6 +7388,9 @@ riscv_shamt_matches_mask_p (int shamt, HOST_WIDE_INT mask)
 #undef TARGET_DWARF_POLY_INDETERMINATE_VALUE
 #define TARGET_DWARF_POLY_INDETERMINATE_VALUE riscv_dwarf_poly_indeterminate_value
 
+#undef TARGET_ZERO_CALL_USED_REGS
+#define TARGET_ZERO_CALL_USED_REGS riscv_zero_call_used_regs
+
 struct gcc_target targetm = TARGET_INITIALIZER;
 
 #include "gt-riscv.h"

diff --git a/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-1.c b/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-1.c
new file mode 100644 (file)
index 0000000..41d94ab
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-1.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc -mabi=lp64 -O2 -fzero-call-used-regs=used -fno-stack-protector -fno-PIC" } */
+
+void
+foo (void)
+{
+}
+
+/* { dg-final { scan-assembler-not "li\t" } } */

diff --git a/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-2.c b/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-2.c
new file mode 100644 (file)
index 0000000..9161dd3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-2.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc -mabi=lp64 -O2 -fzero-call-used-regs=all-gpr" } */
+
+void
+foo (void)
+{
+}
+
+/* { dg-final { scan-assembler-not "vsetvli" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t0,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t1,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t2,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a0,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a1,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a2,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a3,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a4,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a5,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a6,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a7,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t3,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t4,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t5,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t6,0" } } */

diff --git a/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-3.c b/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-3.c
new file mode 100644 (file)
index 0000000..824fe9e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zero-scratch-regs-3.c
@@ -0,0 +1,57 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O2 -fzero-call-used-regs=all" } */
+
+void
+foo (void)
+{
+}
+
+/* { dg-final { scan-assembler "vsetvli\[ \t\]*t0,zero,e32,m1,tu,mu" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v0,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v1,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v2,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v3,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v4,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v5,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v6,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v7,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v8,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v9,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v10,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v11,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v12,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v13,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v14,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v15,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v16,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v17,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v18,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v19,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v20,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v21,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v22,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v23,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v24,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v25,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v26,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v27,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v28,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v29,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v30,0" } } */
+/* { dg-final { scan-assembler "vmv.v.i\[ \t\]*v31,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t0,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t1,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t2,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a0,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a1,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a2,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a3,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a4,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a5,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a6,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*a7,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t3,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t4,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t5,0" } } */
+/* { dg-final { scan-assembler "li\[ \t\]*t6,0" } } */
+/* { dg-final { scan-assembler "fmv.d.x\[ \t\]*ft0,zero" } } */