RISC-V: Bugfix for merging undefined tmp register in math

For math function autovec, there will be one step like

rtx tmp = gen_reg_rtx (vec_int_mode);
emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_DYN, vec_fp_mode);

The MU will leave the tmp (aka dest register) register unmasked elements
unchanged and it is undefined here. This patch would like to adjust the
MU to MA.

gcc/ChangeLog:

	* config/riscv/riscv-protos.h (enum insn_type): Add new type
	values.
	* config/riscv/riscv-v.cc (emit_vec_cvt_x_f): Add undef merge
	operand handling.
	(expand_vec_ceil): Take MA instead of MU for tmp register.
	(expand_vec_floor): Ditto.
	(expand_vec_nearbyint): Ditto.
	(expand_vec_rint): Ditto.
	(expand_vec_round): Ditto.
	(expand_vec_roundeven): Ditto.

Signed-off-by: Pan Li <pan2.li@intel.com>

diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index f7a9a02f1f9b7346a6147a8ae589ec2a7ed3ddaf..5dc97c2adc08959fe85ed4972f8d0eee29b7de16 100644 (file)
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -306,6 +306,11 @@ enum insn_type : unsigned int
   UNARY_OP_FRM_RMM = UNARY_OP | FRM_RMM_P,
   UNARY_OP_FRM_RUP = UNARY_OP | FRM_RUP_P,
   UNARY_OP_FRM_RDN = UNARY_OP | FRM_RDN_P,
+  UNARY_OP_TAMA_FRM_DYN = UNARY_OP_TAMA | FRM_DYN_P,
+  UNARY_OP_TAMA_FRM_RUP = UNARY_OP_TAMA | FRM_RUP_P,
+  UNARY_OP_TAMA_FRM_RDN = UNARY_OP_TAMA | FRM_RDN_P,
+  UNARY_OP_TAMA_FRM_RMM = UNARY_OP_TAMA | FRM_RMM_P,
+  UNARY_OP_TAMA_FRM_RNE = UNARY_OP_TAMA | FRM_RNE_P,
   UNARY_OP_TAMU_FRM_DYN = UNARY_OP_TAMU | FRM_DYN_P,
   UNARY_OP_TAMU_FRM_RUP = UNARY_OP_TAMU | FRM_RUP_P,
   UNARY_OP_TAMU_FRM_RDN = UNARY_OP_TAMU | FRM_RDN_P,

diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 383af55fe3a5afd278b7ec518e7b6e3648f34ee6..91ad6a61fa893d76d8136c3d6a53839a44b0a4f5 100644 (file)
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -4108,10 +4108,18 @@ static void
 emit_vec_cvt_x_f (rtx op_dest, rtx op_src, rtx mask,
                  insn_type type, machine_mode vec_mode)
 {
-  rtx cvt_x_ops[] = {op_dest, mask, op_dest, op_src};
   insn_code icode = code_for_pred_fcvt_x_f (UNSPEC_VFCVT, vec_mode);
 
-  emit_vlmax_insn (icode, type, cvt_x_ops);
+  if (type & USE_VUNDEF_MERGE_P)
+    {
+      rtx cvt_x_ops[] = {op_dest, mask, op_src};
+      emit_vlmax_insn (icode, type, cvt_x_ops);
+    }
+  else
+    {
+      rtx cvt_x_ops[] = {op_dest, mask, op_dest, op_src};
+      emit_vlmax_insn (icode, type, cvt_x_ops);
+    }
 }
 
 static void
@@ -4157,7 +4165,7 @@ expand_vec_ceil (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
 
   /* Step-3: Convert to integer on mask, with rounding up (aka ceil).  */
   rtx tmp = gen_reg_rtx (vec_int_mode);
-  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_RUP, vec_fp_mode);
+  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMA_FRM_RUP, vec_fp_mode);
 
   /* Step-4: Convert to floating-point on mask for the final result.
      To avoid unnecessary frm register access, we use RUP here and it will
@@ -4182,7 +4190,7 @@ expand_vec_floor (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
 
   /* Step-3: Convert to integer on mask, with rounding down (aka floor).  */
   rtx tmp = gen_reg_rtx (vec_int_mode);
-  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_RDN, vec_fp_mode);
+  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMA_FRM_RDN, vec_fp_mode);
 
   /* Step-4: Convert to floating-point on mask for the floor result.  */
   emit_vec_cvt_f_x (op_0, tmp, mask, UNARY_OP_TAMU_FRM_RDN, vec_fp_mode);
@@ -4208,7 +4216,7 @@ expand_vec_nearbyint (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
 
   /* Step-4: Convert to integer on mask, with rounding down (aka nearbyint).  */
   rtx tmp = gen_reg_rtx (vec_int_mode);
-  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_DYN, vec_fp_mode);
+  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMA_FRM_DYN, vec_fp_mode);
 
   /* Step-5: Convert to floating-point on mask for the nearbyint result.  */
   emit_vec_cvt_f_x (op_0, tmp, mask, UNARY_OP_TAMU_FRM_DYN, vec_fp_mode);
@@ -4233,7 +4241,7 @@ expand_vec_rint (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
 
   /* Step-3: Convert to integer on mask, with dyn rounding (aka rint).  */
   rtx tmp = gen_reg_rtx (vec_int_mode);
-  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_DYN, vec_fp_mode);
+  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMA_FRM_DYN, vec_fp_mode);
 
   /* Step-4: Convert to floating-point on mask for the rint result.  */
   emit_vec_cvt_f_x (op_0, tmp, mask, UNARY_OP_TAMU_FRM_DYN, vec_fp_mode);
@@ -4255,7 +4263,7 @@ expand_vec_round (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
 
   /* Step-3: Convert to integer on mask, rounding to nearest (aka round).  */
   rtx tmp = gen_reg_rtx (vec_int_mode);
-  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_RMM, vec_fp_mode);
+  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMA_FRM_RMM, vec_fp_mode);
 
   /* Step-4: Convert to floating-point on mask for the round result.  */
   emit_vec_cvt_f_x (op_0, tmp, mask, UNARY_OP_TAMU_FRM_RMM, vec_fp_mode);
@@ -4299,7 +4307,7 @@ expand_vec_roundeven (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
 
   /* Step-3: Convert to integer on mask, rounding to nearest, ties to even.  */
   rtx tmp = gen_reg_rtx (vec_int_mode);
-  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_RNE, vec_fp_mode);
+  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMA_FRM_RNE, vec_fp_mode);
 
   /* Step-4: Convert to floating-point on mask for the rint result.  */
   emit_vec_cvt_f_x (op_0, tmp, mask, UNARY_OP_TAMU_FRM_RNE, vec_fp_mode);