public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: Jeff Law <jlaw@ventanamicro.com>
To: "gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Cc: Jivan Hakobyan <jivanhakobyan9@gmail.com>
Subject: [committed] [RISC-V] Improve floor, ceil & related operations for RISC-V
Date: Tue, 30 Apr 2024 09:46:34 -0600	[thread overview]
Message-ID: <bc774cba-b55b-417f-b427-860bac76773d@ventanamicro.com> (raw)

[-- Attachment #1: Type: text/plain, Size: 1362 bytes --]

This is almost exclusively Jivan's work.  His original post:


> https://www.mail-archive.com/gcc-patches@gcc.gnu.org/msg336483.html




This patch is primarily meant to improve the code we generate for FP 
rounding such as ceil/floor.  It also addresses some unnecessary sign 
extensions in the same areas.

RISC-V's FP conversions have a bit of undesirable behavior that make 
them non-suitable as-is for ceil/floor and other related functions. 
These deficiencies are addressed in the Zfa extension, but there's no 
reason not to pick up a nice improvement when we can.

Basically we can still use the basic FP conversions for floor/ceil and 
friends when we don't care about inexact exceptions by checking for the 
special cases first, then emitting the conversion when the special cases 
don't apply.  That's still much faster than calling into glibc.

The redundant sign extensions are eliminated using the same trick Jivan 
added last year, just in a few more places ;-)

This eliminates roughly 10% of the dynamic instruction count for 
imagick.  But more importantly it's about a 17% performance improvement 
for that workload within spec.

This has been bootstrapped as well as regression tested in a cross 
environment.  It's also successfully built & run specint/specfp correctly.

Pushing to the trunk and the coordination branch momentarily.


Jeff

[-- Attachment #2: P --]
[-- Type: text/plain, Size: 20512 bytes --]

gcc/
	* config/riscv/iterators.md (fix_ops, fix_uns): New iterators.
	(RINT, rint_pattern, rint_rm): Remove unused iterators.
	* config/riscv/riscv-protos.h (get_fp_rounding_coefficient): Prototype.
	* config/riscvriscv-v.cc (get_fp_rounding_coefficient): Externalize.
	external linkage.
	* config/riscv/riscv.md (UNSPEC_LROUND): Remove.
	(fix_trunc<ANYF:mode><GPR:mode>2): Replace with ...
	(<fix_uns>_trunc<ANYF:mode>si2): New expander & associated insn.
	(<fix_uns>_trunc<ANYF:mode>si2_ext): New insn.
	(<fix_uns>_trunc<ANYF:mode>di2): Likewise.
	(l<rint_pattern><ANYF:mode><GPR:mode>2): Replace with ...
	(lrint<ANYF:mode>si2): New expander and associated insn.
	(lrint<ANYF:mode>si2_ext), lrint<ANYF:mode>di2): New insns.
	(<round_pattern><ANYF:mode>2): Replace with....
	(l<round_pattern><ANYF:mode>si2): New expander and associated insn.
	(l<round_pattern><ANYF:mode>si2_sext): New insn.
	(l<round_pattern><ANYF:mode>di2): Likewise.
	(<round_pattern><ANYF:mode>2): New expander.

gcc/testsuite/
	* gcc.target/riscv/fix.c: New test.
	* gcc.target/riscv/round.c: New test.
	* gcc.target/riscv/round_32.c: New test.
	* gcc.target/riscv/round_64.c: New test.


diff --git a/gcc/config/riscv/iterators.md b/gcc/config/riscv/iterators.md
index a7694137685..75e119e407a 100644
--- a/gcc/config/riscv/iterators.md
+++ b/gcc/config/riscv/iterators.md
@@ -196,6 +196,13 @@ (define_code_iterator clz_ctz_pcnt [clz ctz popcount])
 
 (define_code_iterator bitmanip_rotate [rotate rotatert])
 
+;; These code iterators allow the signed and unsigned fix operations to use
+;; the same template.
+(define_code_iterator fix_ops [fix unsigned_fix])
+
+(define_code_attr fix_uns [(fix "fix") (unsigned_fix "fixuns")])
+
+
 ;; -------------------------------------------------------------------
 ;; Code Attributes
 ;; -------------------------------------------------------------------
@@ -312,11 +319,6 @@ (define_code_attr bitmanip_insn [(smin "min")
 ;; Int Iterators.
 ;; -------------------------------------------------------------------
 
-;; Iterator and attributes for floating-point rounding instructions.
-(define_int_iterator RINT [UNSPEC_LRINT UNSPEC_LROUND])
-(define_int_attr rint_pattern [(UNSPEC_LRINT "rint") (UNSPEC_LROUND "round")])
-(define_int_attr rint_rm [(UNSPEC_LRINT "dyn") (UNSPEC_LROUND "rmm")])
-
 ;; Iterator and attributes for quiet comparisons.
 (define_int_iterator QUIET_COMPARISON [UNSPEC_FLT_QUIET UNSPEC_FLE_QUIET])
 (define_int_attr quiet_pattern [(UNSPEC_FLT_QUIET "lt") (UNSPEC_FLE_QUIET "le")])
diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index 5d46a29d8b7..e5aebf3fc3d 100644
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -711,6 +711,7 @@ bool gather_scatter_valid_offset_p (machine_mode);
 HOST_WIDE_INT estimated_poly_value (poly_int64, unsigned int);
 bool whole_reg_to_reg_move_p (rtx *, machine_mode, int);
 bool splat_to_scalar_move_p (rtx *);
+rtx get_fp_rounding_coefficient (machine_mode);
 }
 
 /* We classify builtin types into two classes:
diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 814c5febabe..c9e0feebca6 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -4494,7 +4494,7 @@ vls_mode_valid_p (machine_mode vls_mode)
       All double floating point will be unchanged for ceil if it is
       greater than and equal to 4503599627370496.
  */
-static rtx
+rtx
 get_fp_rounding_coefficient (machine_mode inner_mode)
 {
   REAL_VALUE_TYPE real;
diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index 455715ab2f7..8f518fdbe5a 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -64,7 +64,6 @@ (define_c_enum "unspec" [
   UNSPEC_ROUNDEVEN
   UNSPEC_NEARBYINT
   UNSPEC_LRINT
-  UNSPEC_LROUND
   UNSPEC_FMIN
   UNSPEC_FMAX
   UNSPEC_FMINM
@@ -1919,21 +1918,48 @@ (define_insn "*movhf_softfloat_boxing"
 ;;
 ;;  ....................
 
-(define_insn "fix_trunc<ANYF:mode><GPR:mode>2"
-  [(set (match_operand:GPR      0 "register_operand" "=r")
-	(fix:GPR
+(define_expand "<fix_uns>_trunc<ANYF:mode>si2"
+  [(set (match_operand:SI      0 "register_operand" "=r")
+	(fix_ops:SI
 	    (match_operand:ANYF 1 "register_operand" " f")))]
   "TARGET_HARD_FLOAT || TARGET_ZFINX"
-  "fcvt.<GPR:ifmt>.<ANYF:fmt> %0,%1,rtz"
+{
+  if (TARGET_64BIT)
+    {
+      rtx t = gen_reg_rtx (DImode);
+      emit_insn (gen_<fix_uns>_trunc<ANYF:mode>si2_sext (t, operands[1]));
+      t = gen_lowpart (SImode, t);
+      SUBREG_PROMOTED_VAR_P (t) = 1;
+      SUBREG_PROMOTED_SET (t, SRP_SIGNED);
+      emit_move_insn (operands[0], t);
+      DONE;
+    }
+})
+
+(define_insn "*<fix_uns>_trunc<ANYF:mode>si2"
+  [(set (match_operand:SI      0 "register_operand" "=r")
+	(fix_ops:SI
+	    (match_operand:ANYF 1 "register_operand" " f")))]
+  "TARGET_HARD_FLOAT || TARGET_ZFINX"
+  "fcvt.w<u>.<ANYF:fmt> %0,%1,rtz"
+  [(set_attr "type" "fcvt_f2i")
+   (set_attr "mode" "<ANYF:MODE>")])
+
+(define_insn "<fix_uns>_trunc<ANYF:mode>si2_sext"
+  [(set (match_operand:DI      0 "register_operand" "=r")
+  (sign_extend:DI (fix_ops:SI
+	    (match_operand:ANYF 1 "register_operand" " f"))))]
+  "TARGET_64BIT && (TARGET_HARD_FLOAT || TARGET_ZFINX)"
+  "fcvt.w<u>.<ANYF:fmt> %0,%1,rtz"
   [(set_attr "type" "fcvt_f2i")
    (set_attr "mode" "<ANYF:MODE>")])
 
-(define_insn "fixuns_trunc<ANYF:mode><GPR:mode>2"
-  [(set (match_operand:GPR      0 "register_operand" "=r")
-	(unsigned_fix:GPR
+(define_insn "<fix_uns>_trunc<ANYF:mode>di2"
+  [(set (match_operand:DI      0 "register_operand" "=r")
+	(fix_ops:DI
 	    (match_operand:ANYF 1 "register_operand" " f")))]
-  "TARGET_HARD_FLOAT  || TARGET_ZFINX"
-  "fcvt.<GPR:ifmt>u.<ANYF:fmt> %0,%1,rtz"
+  "TARGET_64BIT && (TARGET_HARD_FLOAT || TARGET_ZFINX)"
+  "fcvt.l<u>.<ANYF:fmt> %0,%1,rtz"
   [(set_attr "type" "fcvt_f2i")
    (set_attr "mode" "<ANYF:MODE>")])
 
@@ -1955,17 +1981,170 @@ (define_insn "floatuns<GPR:mode><ANYF:mode>2"
   [(set_attr "type" "fcvt_i2f")
    (set_attr "mode" "<ANYF:MODE>")])
 
-(define_insn "l<rint_pattern><ANYF:mode><GPR:mode>2"
-  [(set (match_operand:GPR       0 "register_operand" "=r")
-	(unspec:GPR
+(define_expand "lrint<ANYF:mode>si2"
+  [(set (match_operand:SI       0 "register_operand" "=r")
+	(unspec:SI
 	    [(match_operand:ANYF 1 "register_operand" " f")]
-	    RINT))]
+	    UNSPEC_LRINT))]
   "TARGET_HARD_FLOAT || TARGET_ZFINX"
-  "fcvt.<GPR:ifmt>.<ANYF:fmt> %0,%1,<rint_rm>"
+{
+  if (TARGET_64BIT)
+    {
+      rtx t = gen_reg_rtx (DImode);
+      emit_insn (gen_lrint<ANYF:mode>si2_sext (t, operands[1]));
+      t = gen_lowpart (SImode, t);
+      SUBREG_PROMOTED_VAR_P (t) = 1;
+      SUBREG_PROMOTED_SET (t, SRP_SIGNED);
+      emit_move_insn (operands[0], t);
+      DONE;
+    }
+})
+
+(define_insn "*lrint<ANYF:mode>si2"
+  [(set (match_operand:SI       0 "register_operand" "=r")
+	(unspec:SI
+	    [(match_operand:ANYF 1 "register_operand" " f")]
+	    UNSPEC_LRINT))]
+  "TARGET_HARD_FLOAT || TARGET_ZFINX"
+  "fcvt.w.<ANYF:fmt> %0,%1,dyn"
   [(set_attr "type" "fcvt_f2i")
    (set_attr "mode" "<ANYF:MODE>")])
 
-(define_insn "<round_pattern><ANYF:mode>2"
+(define_insn "lrint<ANYF:mode>si2_sext"
+  [(set (match_operand:DI       0 "register_operand" "=r")
+  (sign_extend:DI (unspec:SI
+	    [(match_operand:ANYF 1 "register_operand" " f")]
+	    UNSPEC_LRINT)))]
+  "TARGET_64BIT && (TARGET_HARD_FLOAT || TARGET_ZFINX)"
+  "fcvt.w.<ANYF:fmt> %0,%1,dyn"
+  [(set_attr "type" "fcvt_f2i")
+   (set_attr "mode" "<ANYF:MODE>")])
+
+(define_insn "lrint<ANYF:mode>di2"
+  [(set (match_operand:DI       0 "register_operand" "=r")
+	(unspec:DI
+	    [(match_operand:ANYF 1 "register_operand" " f")]
+	    UNSPEC_LRINT))]
+  "TARGET_64BIT && (TARGET_HARD_FLOAT || TARGET_ZFINX)"
+  "fcvt.l.<ANYF:fmt> %0,%1,dyn"
+  [(set_attr "type" "fcvt_f2i")
+   (set_attr "mode" "<ANYF:MODE>")])
+
+(define_expand "l<round_pattern><ANYF:mode>si2"
+  [(set (match_operand:SI       0 "register_operand" "=r")
+	(unspec:SI
+	    [(match_operand:ANYF 1 "register_operand" " f")]
+    ROUND))]
+  "TARGET_HARD_FLOAT || TARGET_ZFINX"
+{
+  if (TARGET_64BIT)
+    {
+      rtx t = gen_reg_rtx (DImode);
+      emit_insn (gen_l<round_pattern><ANYF:mode>si2_sext (t, operands[1]));
+      t = gen_lowpart (SImode, t);
+      SUBREG_PROMOTED_VAR_P (t) = 1;
+      SUBREG_PROMOTED_SET (t, SRP_SIGNED);
+      emit_move_insn (operands[0], t);
+      DONE;
+    }
+})
+
+(define_insn "*l<round_pattern><ANYF:mode>si2"
+  [(set (match_operand:SI       0 "register_operand" "=r")
+	(unspec:SI
+	    [(match_operand:ANYF 1 "register_operand" " f")]
+    ROUND))]
+  "TARGET_HARD_FLOAT || TARGET_ZFINX"
+  "fcvt.w.<ANYF:fmt> %0,%1,<round_rm>"
+  [(set_attr "type" "fcvt_f2i")
+   (set_attr "mode" "<ANYF:MODE>")])
+
+(define_insn "l<round_pattern><ANYF:mode>si2_sext"
+  [(set (match_operand:DI       0 "register_operand" "=r")
+	 (sign_extend:DI (unspec:SI
+	                     [(match_operand:ANYF 1 "register_operand" " f")]
+                      ROUND)))]
+  "TARGET_64BIT && (TARGET_HARD_FLOAT || TARGET_ZFINX)"
+  "fcvt.w.<ANYF:fmt> %0,%1,<round_rm>"
+  [(set_attr "type" "fcvt_f2i")
+   (set_attr "mode" "<ANYF:MODE>")])
+
+(define_insn "l<round_pattern><ANYF:mode>di2"
+  [(set (match_operand:DI       0 "register_operand" "=r")
+	(unspec:DI
+	    [(match_operand:ANYF 1 "register_operand" " f")]
+    ROUND))]
+  "TARGET_64BIT && (TARGET_HARD_FLOAT || TARGET_ZFINX)"
+  "fcvt.l.<ANYF:fmt> %0,%1,<round_rm>"
+  [(set_attr "type" "fcvt_f2i")
+   (set_attr "mode" "<ANYF:MODE>")])
+
+(define_expand "<round_pattern><ANYF:mode>2"
+  [(set (match_operand:ANYF     0 "register_operand" "=f")
+        (unspec:ANYF
+            [(match_operand:ANYF 1 "register_operand" " f")]
+        ROUND))]
+  "TARGET_HARD_FLOAT && (TARGET_ZFA
+                         || flag_fp_int_builtin_inexact || !flag_trapping_math)"
+{
+  if (TARGET_ZFA)
+    emit_insn (gen_<round_pattern><ANYF:mode>_zfa2 (operands[0],
+                                                    operands[1]));
+  else
+    {
+      rtx reg;
+      rtx label = gen_label_rtx ();
+      rtx end_label = gen_label_rtx ();
+      rtx abs_reg = gen_reg_rtx (<ANYF:MODE>mode);
+      rtx coeff_reg = gen_reg_rtx (<ANYF:MODE>mode);
+      rtx tmp_reg = gen_reg_rtx (<ANYF:MODE>mode);
+
+      riscv_emit_move (tmp_reg, operands[1]);
+      riscv_emit_move (coeff_reg,
+                       riscv_vector::get_fp_rounding_coefficient (<ANYF:MODE>mode));
+      emit_insn (gen_abs<ANYF:mode>2 (abs_reg, operands[1]));
+
+      riscv_expand_conditional_branch (label, LT, abs_reg, coeff_reg);
+
+      emit_jump_insn (gen_jump (end_label));
+      emit_barrier ();
+
+      emit_label (label);
+      switch (<ANYF:MODE>mode)
+        {
+        case SFmode:
+          reg = gen_reg_rtx (SImode);
+          emit_insn (gen_l<round_pattern>sfsi2 (reg, operands[1]));
+          emit_insn (gen_floatsisf2 (abs_reg, reg));
+          break;
+        case DFmode:
+          if (TARGET_64BIT)
+            {
+              reg = gen_reg_rtx (DImode);
+              emit_insn (gen_l<round_pattern>dfdi2 (reg, operands[1]));
+              emit_insn (gen_floatdidf2 (abs_reg, reg));
+            }
+          else
+            {
+              reg = gen_reg_rtx (SImode);
+              emit_insn (gen_l<round_pattern>dfsi2 (reg, operands[1]));
+              emit_insn (gen_floatsidf2 (abs_reg, reg));
+            }
+          break;
+        default:
+          gcc_unreachable ();
+        }
+
+      emit_insn (gen_copysign<ANYF:mode>3 (tmp_reg, abs_reg, operands[1]));
+
+      emit_label (end_label);
+      riscv_emit_move (operands[0], tmp_reg);
+    }
+
+  DONE;
+})
+
+(define_insn "<round_pattern><ANYF:mode>_zfa2"
   [(set (match_operand:ANYF     0 "register_operand" "=f")
 	(unspec:ANYF
 	    [(match_operand:ANYF 1 "register_operand" " f")]
diff --git a/gcc/testsuite/gcc.target/riscv/fix.c b/gcc/testsuite/gcc.target/riscv/fix.c
new file mode 100644
index 00000000000..265a7da1fc5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/fix.c
@@ -0,0 +1,34 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc -mabi=lp64d" } */
+/* { dg-skip-if "" { *-*-* }  { "-O0" } } */
+
+int
+foo (double n)
+{
+  return n;
+}
+
+int
+foo_1 (float n)
+{
+  return n;
+}
+
+unsigned int
+foo_2 (double n)
+{
+  return n;
+}
+
+unsigned int
+foo_3 (float n)
+{
+  return n;
+}
+
+/* { dg-final { scan-assembler-times {\mfcvt.w.d} 1 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.w.s} 1 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.wu.d} 1 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.wu.s} 1 } } */
+/* { dg-final { scan-assembler-not "\\ssext.w\\s" } } */
+
diff --git a/gcc/testsuite/gcc.target/riscv/round.c b/gcc/testsuite/gcc.target/riscv/round.c
new file mode 100644
index 00000000000..decfc82a390
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/round.c
@@ -0,0 +1,144 @@
+#include <math.h>
+
+extern void abort (void);
+extern void exit (int);
+
+#define NEQ(a, b) (fabs((a) - (b)) > 0.000001)
+
+#define DECL_FUNC(TYPE1, TYPE2, ROUND)              \
+   __attribute__ ((noinline, noclone)) TYPE2        \
+   convert_##TYPE1##_to_##TYPE2##_##ROUND (TYPE1 N) \
+    {                                               \
+      return ROUND (N);                             \
+    }
+
+#define DECL_ALL_ROUNDS_FOR(ROUND_FUNC) \
+  DECL_FUNC(float, float, ROUND_FUNC)   \
+  DECL_FUNC(double, double, ROUND_FUNC) \
+  DECL_FUNC(double, int, ROUND_FUNC)    \
+  DECL_FUNC(double, long, ROUND_FUNC)   \
+  DECL_FUNC(float, int, ROUND_FUNC)     \
+  DECL_FUNC(float, long, ROUND_FUNC)
+
+
+DECL_ALL_ROUNDS_FOR(round)
+DECL_ALL_ROUNDS_FOR(ceil)
+DECL_ALL_ROUNDS_FOR(floor)
+DECL_ALL_ROUNDS_FOR(trunc)
+DECL_ALL_ROUNDS_FOR(nearbyint)
+
+#define TEST_ROUND(TYPE1, TYPE2, N, N_R, ROUND)      \
+  if (NEQ (convert_##TYPE1##_to_##TYPE2##_##ROUND (N), N_R)) \
+    abort ();
+
+
+int main () {
+
+  /* Round */
+  TEST_ROUND(double, double, -4.8, -5.0, round);
+  TEST_ROUND(double, double, -4.2, -4.0, round);
+  TEST_ROUND(double, double, 4.8, 5.0, round);
+  TEST_ROUND(double, double, 4.2, 4.0, round);
+
+  TEST_ROUND(double, int, -4.8, -5, round);
+  TEST_ROUND(double, int, -4.2, -4, round);
+  TEST_ROUND(double, int, 4.8, 5, round);
+  TEST_ROUND(double, int, 4.2, 4, round);
+
+  TEST_ROUND(double, long, -4.8, -5, round);
+  TEST_ROUND(double, long, -4.2, -4, round);
+  TEST_ROUND(double, long, 4.8, 5, round);
+  TEST_ROUND(double, long, 4.2, 4, round);
+
+  TEST_ROUND(float, long, -4.8, -5, round);
+  TEST_ROUND(float, long, -4.2, -4, round);
+  TEST_ROUND(float, long, 4.8, 5, round);
+  TEST_ROUND(float, long, 4.2, 4, round);
+
+  /* Ceil */
+  TEST_ROUND(double, double, -4.8, -4.0, ceil);
+  TEST_ROUND(double, double, -4.2, -4.0, ceil);
+  TEST_ROUND(double, double, 4.8, 5.0, ceil);
+  TEST_ROUND(double, double, 4.2, 5.0, ceil);
+
+  TEST_ROUND(double, int, -4.8, -4, ceil);
+  TEST_ROUND(double, int, -4.2, -4, ceil);
+  TEST_ROUND(double, int, 4.8, 5, ceil);
+  TEST_ROUND(double, int, 4.2, 5, ceil);
+
+  TEST_ROUND(double, long, -4.8, -4, ceil);
+  TEST_ROUND(double, long, -4.2, -4, ceil);
+  TEST_ROUND(double, long, 4.8, 5, ceil);
+  TEST_ROUND(double, long, 4.2, 5, ceil);
+
+  TEST_ROUND(float, long, -4.8, -4, ceil);
+  TEST_ROUND(float, long, -4.2, -4, ceil);
+  TEST_ROUND(float, long, 4.8, 5, ceil);
+  TEST_ROUND(float, long, 4.2, 5, ceil);
+
+  /* Floor */
+  TEST_ROUND(double, double, -4.8, -5.0, floor);
+  TEST_ROUND(double, double, -4.2, -5.0, floor);
+  TEST_ROUND(double, double, 4.8, 4.0, floor);
+  TEST_ROUND(double, double, 4.2, 4.0, floor);
+
+  TEST_ROUND(double, int, -4.8, -5, floor);
+  TEST_ROUND(double, int, -4.2, -5, floor);
+  TEST_ROUND(double, int, 4.8, 4, floor);
+  TEST_ROUND(double, int, 4.2, 4, floor);
+
+  TEST_ROUND(double, long, -4.8, -5, floor);
+  TEST_ROUND(double, long, -4.2, -5, floor);
+  TEST_ROUND(double, long, 4.8, 4, floor);
+  TEST_ROUND(double, long, 4.2, 4, floor);
+
+  TEST_ROUND(float, long, -4.8, -5, floor);
+  TEST_ROUND(float, long, -4.2, -5, floor);
+  TEST_ROUND(float, long, 4.8, 4, floor);
+  TEST_ROUND(float, long, 4.2, 4, floor);
+
+  /* Trunc */
+  TEST_ROUND(double, double, -4.8, -4.0, trunc);
+  TEST_ROUND(double, double, -4.2, -4.0, trunc);
+  TEST_ROUND(double, double, 4.8, 4.0, trunc);
+  TEST_ROUND(double, double, 4.2, 4.0, trunc);
+
+  TEST_ROUND(double, int, -4.8, -4, trunc);
+  TEST_ROUND(double, int, -4.2, -4, trunc);
+  TEST_ROUND(double, int, 4.8, 4, trunc);
+  TEST_ROUND(double, int, 4.2, 4, trunc);
+
+  TEST_ROUND(double, long, -4.8, -4, trunc);
+  TEST_ROUND(double, long, -4.2, -4, trunc);
+  TEST_ROUND(double, long, 4.8, 4, trunc);
+  TEST_ROUND(double, long, 4.2, 4, trunc);
+
+  TEST_ROUND(float, long, -4.8, -4, trunc);
+  TEST_ROUND(float, long, -4.2, -4, trunc);
+  TEST_ROUND(float, long, 4.8, 4, trunc);
+  TEST_ROUND(float, long, 4.2, 4, trunc);
+
+  /* Nearbyint */
+  TEST_ROUND(double, double, -4.8, -5.0, nearbyint);
+  TEST_ROUND(double, double, -4.2, -4.0, nearbyint);
+  TEST_ROUND(double, double, 4.8, 5.0, nearbyint);
+  TEST_ROUND(double, double, 4.2, 4.0, nearbyint);
+
+  TEST_ROUND(double, int, -4.8, -5, nearbyint);
+  TEST_ROUND(double, int, -4.2, -4, nearbyint);
+  TEST_ROUND(double, int, 4.8, 5, nearbyint);
+  TEST_ROUND(double, int, 4.2, 4, nearbyint);
+
+  TEST_ROUND(double, long, -4.8, -5, nearbyint);
+  TEST_ROUND(double, long, -4.2, -4, nearbyint);
+  TEST_ROUND(double, long, 4.8, 5, nearbyint);
+  TEST_ROUND(double, long, 4.2, 4, nearbyint);
+
+  TEST_ROUND(float, long, -4.8, -5, nearbyint);
+  TEST_ROUND(float, long, -4.2, -4, nearbyint);
+  TEST_ROUND(float, long, 4.8, 5, nearbyint);
+  TEST_ROUND(float, long, 4.2, 4, nearbyint);
+
+  exit(0);
+}
+
diff --git a/gcc/testsuite/gcc.target/riscv/round_32.c b/gcc/testsuite/gcc.target/riscv/round_32.c
new file mode 100644
index 00000000000..f9fea70ad55
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/round_32.c
@@ -0,0 +1,22 @@
+/* { dg-do compile { target { riscv32*-*-* } } } */
+/* { dg-options "-march=rv32gc -mabi=ilp32d -fno-math-errno -funsafe-math-optimizations -fno-inline" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" } } */
+
+#include "round.c"
+
+/* { dg-final { scan-assembler-times {\mfcvt.w.s} 15 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.s.w} 5 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.d.w} 65 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.w.d} 15 } } */
+/* { dg-final { scan-assembler-times {,rup} 6 } } */
+/* { dg-final { scan-assembler-times {,rmm} 6 } } */
+/* { dg-final { scan-assembler-times {,rdn} 6 } } */
+/* { dg-final { scan-assembler-times {,rtz} 6 } } */
+/* { dg-final { scan-assembler-not {\mfcvt.l.d} } } */
+/* { dg-final { scan-assembler-not {\mfcvt.d.l} } } */
+/* { dg-final { scan-assembler-not "\\sceil\\s" } } */
+/* { dg-final { scan-assembler-not "\\sfloor\\s" } } */
+/* { dg-final { scan-assembler-not "\\sround\\s" } } */
+/* { dg-final { scan-assembler-not "\\snearbyint\\s" } } */
+/* { dg-final { scan-assembler-not "\\srint\\s" } } */
+/* { dg-final { scan-assembler-not "\\stail\\s" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/round_64.c b/gcc/testsuite/gcc.target/riscv/round_64.c
new file mode 100644
index 00000000000..e79690979a5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/round_64.c
@@ -0,0 +1,23 @@
+/* { dg-do compile { target { riscv64*-*-* } } } */
+/* { dg-options "-march=rv64gc -mabi=lp64d -fno-math-errno -funsafe-math-optimizations -fno-inline" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" } } */
+
+#include "round.c"
+
+/* { dg-final { scan-assembler-times {\mfcvt.w.s} 10 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.s.w} 5 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.l.d} 10 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.d.l} 45 } } */
+/* { dg-final { scan-assembler-times {\mfcvt.w.d} 5 } } */
+/* { dg-final { scan-assembler-times {,rup} 6 } } */
+/* { dg-final { scan-assembler-times {,rmm} 6 } } */
+/* { dg-final { scan-assembler-times {,rdn} 6 } } */
+/* { dg-final { scan-assembler-times {,rtz} 6 } } */
+/* { dg-final { scan-assembler-not "\\sceil\\s" } } */
+/* { dg-final { scan-assembler-not "\\sfloor\\s" } } */
+/* { dg-final { scan-assembler-not "\\sround\\s" } } */
+/* { dg-final { scan-assembler-not "\\snearbyint\\s" } } */
+/* { dg-final { scan-assembler-not "\\srint\\s" } } */
+/* { dg-final { scan-assembler-not "\\stail\\s" } } */
+/* { dg-final { scan-assembler-not "\\ssext.w\\s" } } */
+

             reply	other threads:[~2024-04-30 15:46 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-04-30 15:46 Jeff Law [this message]
2024-05-01 18:44 ` Patrick O'Neill
2024-05-01 19:07   ` Jeff Law
2024-05-01 19:56   ` Jeff Law
2024-05-01 21:54   ` Jeff Law
2024-05-02  2:49   ` Jeff Law
2024-05-02 22:10   ` Jeff Law

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=bc774cba-b55b-417f-b427-860bac76773d@ventanamicro.com \
    --to=jlaw@ventanamicro.com \
    --cc=gcc-patches@gcc.gnu.org \
    --cc=jivanhakobyan9@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).