From: Juzhe-Zhong <juzhe.zh...@rivai.ai>
This patch is adding mask logic auto-vectorization.
define the pattern as "define_insn_and_split" to allow
combine PASS easily combine series instructions.
For example:
combine vmxor.mm + vmnot.m into vmxnor.mm
Build success and regression PASS
Ok for trunk ?
gcc/ChangeLog:
* config/riscv/autovec.md (<optab><mode>3): New pattern.
(one_cmpl<mode>2): Ditto.
(*<optab>not<mode>): Ditto.
(*n<optab><mode>): Ditto.
* config/riscv/riscv-v.cc (expand_vec_cmp_float): Change to one_cmpl.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/cmp/vcond-4.c: New test.
* gcc.target/riscv/rvv/autovec/cmp/vcond_run-4.c: New test.
---
gcc/config/riscv/autovec.md | 95 +++++++++++++++++++
gcc/config/riscv/riscv-v.cc | 7 +-
.../riscv/rvv/autovec/cmp/vcond-4.c | 53 +++++++++++
.../riscv/rvv/autovec/cmp/vcond_run-4.c | 35 +++++++
4 files changed, 187 insertions(+), 3 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/cmp/vcond-4.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/cmp/vcond_run-4.c
diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index 4eeeab624a4..cacf27e4e60 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -163,6 +163,101 @@
DONE;
})
+;; -------------------------------------------------------------------------
+;; ---- [BOOL] Binary logical operations
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vmand.mm
+;; - vmxor.mm
+;; - vmor.mm
+;; -------------------------------------------------------------------------
+
+(define_insn_and_rewrite "<optab><mode>3"
+ [(set (match_operand:VB 0 "register_operand" "=vr")
+ (any_bitwise:VB (match_operand:VB 1 "register_operand" " vr")
+ (match_operand:VB 2 "register_operand" " vr")))]
+ "TARGET_VECTOR"
+ "#"
+ "&& can_create_pseudo_p ()"
+ {
+ insn_code icode = code_for_pred (<CODE>, <MODE>mode);
+ riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_BINOP, operands);
+ DONE;
+ }
+ [(set_attr "type" "vmalu")
+ (set_attr "mode" "<MODE>")])
+
+;; -------------------------------------------------------------------------
+;; ---- [BOOL] Inverse
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vmnot.m
+;; -------------------------------------------------------------------------
+
+(define_insn_and_rewrite "one_cmpl<mode>2"
+ [(set (match_operand:VB 0 "register_operand" "=vr")
+ (not:VB (match_operand:VB 1 "register_operand" " vr")))]
+ "TARGET_VECTOR"
+ "#"
+ "&& can_create_pseudo_p ()"
+ {
+ insn_code icode = code_for_pred_not (<MODE>mode);
+ riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_UNOP, operands);
+ DONE;
+ }
+ [(set_attr "type" "vmalu")
+ (set_attr "mode" "<MODE>")])
+
+;; -------------------------------------------------------------------------
+;; ---- [BOOL] Binary logical operations (inverted second input)
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vmandnot.mm
+;; - vmornot.mm
+;; -------------------------------------------------------------------------
+
+(define_insn_and_rewrite "*<optab>not<mode>"
+ [(set (match_operand:VB 0 "register_operand" "=vr")
+ (bitmanip_bitwise:VB
+ (not:VB (match_operand:VB 2 "register_operand" " vr"))
+ (match_operand:VB 1 "register_operand" " vr")))]
+ "TARGET_VECTOR"
+ "#"
+ "&& can_create_pseudo_p ()"
+ {
+ insn_code icode = code_for_pred_not (<CODE>, <MODE>mode);
+ riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_BINOP, operands);
+ DONE;
+ }
+ [(set_attr "type" "vmalu")
+ (set_attr "mode" "<MODE>")])
+
+;; -------------------------------------------------------------------------
+;; ---- [BOOL] Binary logical operations (inverted result)
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vmnand.mm
+;; - vmnor.mm
+;; - vmxnor.mm
+;; -------------------------------------------------------------------------
+
+(define_insn_and_rewrite "*n<optab><mode>"
+ [(set (match_operand:VB 0 "register_operand" "=vr")
+ (not:VB
+ (any_bitwise:VB
+ (match_operand:VB 1 "register_operand" " vr")
+ (match_operand:VB 2 "register_operand" " vr"))))]
+ "TARGET_VECTOR"
+ "#"
+ "&& can_create_pseudo_p ()"
+ {
+ insn_code icode = code_for_pred_n (<CODE>, <MODE>mode);
+ riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_BINOP, operands);
+ DONE;
+ }
+ [(set_attr "type" "vmalu")
+ (set_attr "mode" "<MODE>")])
+
;; =========================================================================
;; == Comparisons and selects
;; =========================================================================
diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 10de5a19937..f71ad9e46a1 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -1550,9 +1550,10 @@ expand_vec_cmp_float (rtx target, rtx_code code, rtx
op0, rtx op1,
emit_move_insn (target, eq0);
return true;
}
- insn_code icode = code_for_pred_not (mask_mode);
- rtx ops[] = {target, eq0};
- emit_vlmax_insn (icode, RVV_UNOP, ops);
+
+ /* We use one_cmpl<mode>2 to make Combine PASS to combine mask instructions
+ into: vmand.mm/vmnor.mm/vmnand.mm/vmnor.mm/vmxnor.mm. */
+ emit_insn (gen_rtx_SET (target, gen_rtx_NOT (mask_mode, eq0)));
return false;
}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/cmp/vcond-4.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/cmp/vcond-4.c
new file mode 100644
index 00000000000..435a59c97f2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/cmp/vcond-4.c
@@ -0,0 +1,53 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d
--param=riscv-autovec-preference=scalable" } */
+
+#include <stdint-gcc.h>
+
+#define b_and(A, B) ((A) & (B))
+#define b_orr(A, B) ((A) | (B))
+#define b_xor(A, B) ((A) ^ (B))
+#define b_nand(A, B) (!((A) & (B)))
+#define b_nor(A, B) (!((A) | (B)))
+#define b_xnor(A, B) (!(A) ^ (B))
+#define b_andnot(A, B) ((A) & !(B))
+#define b_ornot(A, B) ((A) | !(B))
+
+#define LOOP(TYPE, BINOP)
\
+ void __attribute__ ((noinline, noclone))
\
+ test_##TYPE##_##BINOP (TYPE *restrict dest, TYPE *restrict src,
\
+ TYPE *restrict a, TYPE *restrict b, TYPE *restrict c, \
+ TYPE *restrict d, TYPE fallback, int count) \
+ {
\
+ for (int i = 0; i < count; ++i)
\
+ {
\
+ TYPE srcv = src[i]; \
+ dest[i] = (BINOP (__builtin_isunordered (a[i], b[i]), \
+ __builtin_isunordered (c[i], d[i])) \
+ ? srcv \
+ : fallback); \
+ }
\
+ }
+
+#define TEST_BINOP(T, BINOP)
\
+ T (float, BINOP)
\
+ T (double, BINOP)
+
+#define TEST_ALL(T)
\
+ TEST_BINOP (T, b_and)
\
+ TEST_BINOP (T, b_orr)
\
+ TEST_BINOP (T, b_xor)
\
+ TEST_BINOP (T, b_nand)
\
+ TEST_BINOP (T, b_nor)
\
+ TEST_BINOP (T, b_xnor)
\
+ TEST_BINOP (T, b_andnot)
\
+ TEST_BINOP (T, b_ornot)
+
+TEST_ALL (LOOP)
+
+/* { dg-final { scan-assembler-times {\tvmand\.mm} 2 } } */
+/* { dg-final { scan-assembler-times {\tvmor\.mm} 2 } } */
+/* { dg-final { scan-assembler-times {\tvmxor\.mm} 2 } } */
+/* { dg-final { scan-assembler-times {\tvmnot\.m} 4 } } */
+/* { dg-final { scan-assembler-times {\tvmxnor\.mm} 2 } } */
+/* { dg-final { scan-assembler-times {\tvmandn\.mm} 4 } } */
+/* { dg-final { scan-assembler-times {\tvmorn\.mm} 4 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/cmp/vcond_run-4.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/cmp/vcond_run-4.c
new file mode 100644
index 00000000000..6c45c274c33
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/cmp/vcond_run-4.c
@@ -0,0 +1,35 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+
+#include "vcond-4.c"
+
+#define N 401
+
+#define RUN_LOOP(TYPE, BINOP) \
+ { \
+ TYPE dest[N], src[N], a[N], b[N], c[N], d[N]; \
+ for (int i = 0; i < N; ++i)
\
+ {
\
+ src[i] = i * i; \
+ a[i] = i % 5 < 3 ? __builtin_nan("") : i; \
+ b[i] = i % 7 < 4 ? __builtin_nan("") : i; \
+ c[i] = i % 9 < 5 ? __builtin_nan("") : i; \
+ d[i] = i % 11 < 6 ? __builtin_nan("") : i; \
+ asm volatile ("" ::: "memory"); \
+ }
\
+ test_##TYPE##_##BINOP (dest, src, a, b, c, d, 100, N); \
+ for (int i = 0; i < N; ++i)
\
+ {
\
+ int res = BINOP (__builtin_isunordered (a[i], b[i]), \
+ __builtin_isunordered (c[i], d[i])); \
+ if (dest[i] != (res ? src[i] : 100.0)) \
+ __builtin_abort (); \
+ }
\
+ }
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ TEST_ALL (RUN_LOOP)
+ return 0;
+}
--
2.36.3
