arm: Add movmisalign patterns for MVE (PR target/97875)

This patch adds new movmisalign<mode>_mve_load and store patterns for
MVE to help vectorization. They are very similar to their Neon
counterparts, but use different iterators and instructions.

Indeed MVE supports less vectors modes than Neon, so we use the
MVE_VLD_ST iterator where Neon uses VQX.

Since the supported modes are different from the ones valid for
arithmetic operators, we introduce two new sets of macros:

ARM_HAVE_NEON_<MODE>_LDST
  true if Neon has vector load/store instructions for <MODE>

ARM_HAVE_<MODE>_LDST
  true if any vector extension has vector load/store instructions for <MODE>

We move the movmisalign<mode> expander from neon.md to vec-commond.md, and
replace the TARGET_NEON enabler with ARM_HAVE_<MODE>_LDST.

The patch also updates the mve-vneg.c test to scan for the better code
generation when loading and storing the vectors involved: it checks
that no 'orr' instruction is generated to cope with misalignment at
runtime.
This test was chosen among the other mve tests, but any other should
be OK. Using a plain vector copy loop (dest[i] = a[i]) is not a good
test because the compiler chooses to use memcpy.

For instance we now generate:
test_vneg_s32x4:
	vldrw.32       q3, [r1]
	vneg.s32  q3, q3
	vstrw.32       q3, [r0]
	bx      lr

instead of:
test_vneg_s32x4:
	orr     r3, r1, r0
	lsls    r3, r3, #28
	bne     .L15
	vldrw.32	q3, [r1]
	vneg.s32  q3, q3
	vstrw.32	q3, [r0]
	bx      lr
	.L15:
	push    {r4, r5}
	ldrd    r2, r3, [r1, #8]
	ldrd    r5, r4, [r1]
	rsbs    r2, r2, #0
	rsbs    r5, r5, #0
	rsbs    r4, r4, #0
	rsbs    r3, r3, #0
	strd    r5, r4, [r0]
	pop     {r4, r5}
	strd    r2, r3, [r0, #8]
	bx      lr

2021-01-12  Christophe Lyon  <christophe.lyon@linaro.org>

	PR target/97875
	gcc/
	* config/arm/arm.h (ARM_HAVE_NEON_V8QI_LDST): New macro.
	(ARM_HAVE_NEON_V16QI_LDST, ARM_HAVE_NEON_V4HI_LDST): Likewise.
	(ARM_HAVE_NEON_V8HI_LDST, ARM_HAVE_NEON_V2SI_LDST): Likewise.
	(ARM_HAVE_NEON_V4SI_LDST, ARM_HAVE_NEON_V4HF_LDST): Likewise.
	(ARM_HAVE_NEON_V8HF_LDST, ARM_HAVE_NEON_V4BF_LDST): Likewise.
	(ARM_HAVE_NEON_V8BF_LDST, ARM_HAVE_NEON_V2SF_LDST): Likewise.
	(ARM_HAVE_NEON_V4SF_LDST, ARM_HAVE_NEON_DI_LDST): Likewise.
	(ARM_HAVE_NEON_V2DI_LDST): Likewise.
	(ARM_HAVE_V8QI_LDST, ARM_HAVE_V16QI_LDST): Likewise.
	(ARM_HAVE_V4HI_LDST, ARM_HAVE_V8HI_LDST): Likewise.
	(ARM_HAVE_V2SI_LDST, ARM_HAVE_V4SI_LDST, ARM_HAVE_V4HF_LDST): Likewise.
	(ARM_HAVE_V8HF_LDST, ARM_HAVE_V4BF_LDST, ARM_HAVE_V8BF_LDST): Likewise.
	(ARM_HAVE_V2SF_LDST, ARM_HAVE_V4SF_LDST, ARM_HAVE_DI_LDST): Likewise.
	(ARM_HAVE_V2DI_LDST): Likewise.
	* config/arm/mve.md (*movmisalign<mode>_mve_store): New pattern.
	(*movmisalign<mode>_mve_load): New pattern.
	* config/arm/neon.md (movmisalign<mode>): Move to ...
	* config/arm/vec-common.md: ... here.

	PR target/97875
	gcc/testsuite/
	* gcc.target/arm/simd/mve-vneg.c: Update test.

diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h
index 64a4080185c8f5f43b14a20bd17f427e86049c12..6bc03ada0bffd63f760c35009924c69e86213c62 100644 (file)
--- a/gcc/config/arm/arm.h
+++ b/gcc/config/arm/arm.h
@@ -1151,6 +1151,46 @@ extern const int arm_arch_cde_coproc_bits[];
 #define ARM_HAVE_V8HF_ARITH (ARM_HAVE_NEON_V8HF_ARITH || TARGET_HAVE_MVE_FLOAT)
 #define ARM_HAVE_V4SF_ARITH (ARM_HAVE_NEON_V4SF_ARITH || TARGET_HAVE_MVE_FLOAT)
 
+/* The conditions under which vector modes are supported by load/store
+   instructions using Neon.  */
+
+#define ARM_HAVE_NEON_V8QI_LDST TARGET_NEON
+#define ARM_HAVE_NEON_V16QI_LDST TARGET_NEON
+#define ARM_HAVE_NEON_V4HI_LDST TARGET_NEON
+#define ARM_HAVE_NEON_V8HI_LDST TARGET_NEON
+#define ARM_HAVE_NEON_V2SI_LDST TARGET_NEON
+#define ARM_HAVE_NEON_V4SI_LDST TARGET_NEON
+#define ARM_HAVE_NEON_V4HF_LDST TARGET_NEON_FP16INST
+#define ARM_HAVE_NEON_V8HF_LDST TARGET_NEON_FP16INST
+#define ARM_HAVE_NEON_V4BF_LDST TARGET_BF16_SIMD
+#define ARM_HAVE_NEON_V8BF_LDST TARGET_BF16_SIMD
+#define ARM_HAVE_NEON_V2SF_LDST TARGET_NEON
+#define ARM_HAVE_NEON_V4SF_LDST TARGET_NEON
+#define ARM_HAVE_NEON_DI_LDST TARGET_NEON
+#define ARM_HAVE_NEON_V2DI_LDST TARGET_NEON
+
+/* The conditions under which vector modes are supported by load/store
+   instructions by any vector extension.  */
+
+#define ARM_HAVE_V8QI_LDST (ARM_HAVE_NEON_V8QI_LDST || TARGET_REALLY_IWMMXT)
+#define ARM_HAVE_V4HI_LDST (ARM_HAVE_NEON_V4HI_LDST || TARGET_REALLY_IWMMXT)
+#define ARM_HAVE_V2SI_LDST (ARM_HAVE_NEON_V2SI_LDST || TARGET_REALLY_IWMMXT)
+
+#define ARM_HAVE_V16QI_LDST (ARM_HAVE_NEON_V16QI_LDST || TARGET_HAVE_MVE)
+#define ARM_HAVE_V8HI_LDST (ARM_HAVE_NEON_V8HI_LDST || TARGET_HAVE_MVE)
+#define ARM_HAVE_V4SI_LDST (ARM_HAVE_NEON_V4SI_LDST || TARGET_HAVE_MVE)
+#define ARM_HAVE_DI_LDST ARM_HAVE_NEON_DI_LDST
+#define ARM_HAVE_V2DI_LDST ARM_HAVE_NEON_V2DI_LDST
+
+#define ARM_HAVE_V4HF_LDST ARM_HAVE_NEON_V4HF_LDST
+#define ARM_HAVE_V2SF_LDST ARM_HAVE_NEON_V2SF_LDST
+
+#define ARM_HAVE_V4BF_LDST ARM_HAVE_NEON_V4BF_LDST
+#define ARM_HAVE_V8BF_LDST ARM_HAVE_NEON_V8BF_LDST
+
+#define ARM_HAVE_V8HF_LDST (ARM_HAVE_NEON_V8HF_LDST || TARGET_HAVE_MVE_FLOAT)
+#define ARM_HAVE_V4SF_LDST (ARM_HAVE_NEON_V4SF_LDST || TARGET_HAVE_MVE_FLOAT)
+
 /* The register numbers in sequence, for passing to arm_gen_load_multiple.  */
 extern int arm_regs_in_sequence[];
 

diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index 622ef8bb1eb30394a7a2c3dc5067f0e46f8b19d6..7fb69aae119853994dd3e5eb1f30d641937b91ff 100644 (file)
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -10825,3 +10825,26 @@
   [(set_attr "type" "coproc")
    (set_attr "length" "8")]
 )
+
+(define_insn "*movmisalign<mode>_mve_store"
+  [(set (match_operand:MVE_VLD_ST 0 "neon_permissive_struct_operand"        "=Um")
+       (unspec:MVE_VLD_ST [(match_operand:MVE_VLD_ST 1 "s_register_operand" " w")]
+        UNSPEC_MISALIGNED_ACCESS))]
+  "((TARGET_HAVE_MVE && VALID_MVE_SI_MODE (<MODE>mode))
+    || (TARGET_HAVE_MVE_FLOAT && VALID_MVE_SF_MODE (<MODE>mode)))
+   && !BYTES_BIG_ENDIAN && unaligned_access"
+  "vstr<V_sz_elem1>.<V_sz_elem>\t%q1, %E0"
+  [(set_attr "type" "mve_store")]
+)
+
+
+(define_insn "*movmisalign<mode>_mve_load"
+  [(set (match_operand:MVE_VLD_ST 0 "s_register_operand"                                "=w")
+       (unspec:MVE_VLD_ST [(match_operand:MVE_VLD_ST 1 "neon_permissive_struct_operand" " Um")]
+        UNSPEC_MISALIGNED_ACCESS))]
+  "((TARGET_HAVE_MVE && VALID_MVE_SI_MODE (<MODE>mode))
+    || (TARGET_HAVE_MVE_FLOAT && VALID_MVE_SF_MODE (<MODE>mode)))
+   && !BYTES_BIG_ENDIAN && unaligned_access"
+  "vldr<V_sz_elem1>.<V_sz_elem>\t%q0, %E1"
+  [(set_attr "type" "mve_load")]
+)

diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index 9d38445e6f9dd09e43c0902723a996eec8cfcdfd..317b98e56200ea23c2c523742b2c627ad737ebe4 100644 (file)
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -280,31 +280,6 @@
   neon_disambiguate_copy (operands, dest, src, 4);
 })
 
-(define_expand "movmisalign<mode>"
-  [(set (match_operand:VDQX 0 "neon_perm_struct_or_reg_operand")
-       (unspec:VDQX [(match_operand:VDQX 1 "neon_perm_struct_or_reg_operand")]
-                    UNSPEC_MISALIGNED_ACCESS))]
-  "TARGET_NEON && !BYTES_BIG_ENDIAN && unaligned_access"
-{
-  rtx adjust_mem;
-  /* This pattern is not permitted to fail during expansion: if both arguments
-     are non-registers (e.g. memory := constant, which can be created by the
-     auto-vectorizer), force operand 1 into a register.  */
-  if (!s_register_operand (operands[0], <MODE>mode)
-      && !s_register_operand (operands[1], <MODE>mode))
-    operands[1] = force_reg (<MODE>mode, operands[1]);
-
-  if (s_register_operand (operands[0], <MODE>mode))
-    adjust_mem = operands[1];
-  else
-    adjust_mem = operands[0];
-
-  /* Legitimize address.  */
-  if (!neon_vector_mem_operand (adjust_mem, 2, true))
-    XEXP (adjust_mem, 0) = force_reg (Pmode, XEXP (adjust_mem, 0));
-
-})
-
 (define_insn "*movmisalign<mode>_neon_store"
   [(set (match_operand:VDX 0 "neon_permissive_struct_operand"  "=Um")
        (unspec:VDX [(match_operand:VDX 1 "s_register_operand" " w")]

diff --git a/gcc/config/arm/vec-common.md b/gcc/config/arm/vec-common.md
index 6967b845d70a05965d56155f41e98cf224afca6c..32387e11d61b9041d71a176117f370aefef761d0 100644 (file)
--- a/gcc/config/arm/vec-common.md
+++ b/gcc/config/arm/vec-common.md
@@ -215,3 +215,26 @@
                      && ARM_HAVE_<MODE>_ARITH)) && !BYTES_BIG_ENDIAN"
 )
 
+(define_expand "movmisalign<mode>"
+ [(set (match_operand:VDQX 0 "neon_perm_struct_or_reg_operand")
+       (unspec:VDQX [(match_operand:VDQX 1 "neon_perm_struct_or_reg_operand")]
+        UNSPEC_MISALIGNED_ACCESS))]
+ "ARM_HAVE_<MODE>_LDST && !BYTES_BIG_ENDIAN && unaligned_access"
+{
+ rtx adjust_mem;
+ /* This pattern is not permitted to fail during expansion: if both arguments
+    are non-registers (e.g. memory := constant, which can be created by the
+    auto-vectorizer), force operand 1 into a register.  */
+ if (!s_register_operand (operands[0], <MODE>mode)
+     && !s_register_operand (operands[1], <MODE>mode))
+   operands[1] = force_reg (<MODE>mode, operands[1]);
+
+ if (s_register_operand (operands[0], <MODE>mode))
+   adjust_mem = operands[1];
+ else
+   adjust_mem = operands[0];
+
+ /* Legitimize address.  */
+ if (!neon_vector_mem_operand (adjust_mem, 2, true))
+   XEXP (adjust_mem, 0) = force_reg (Pmode, XEXP (adjust_mem, 0));
+})

diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-vneg.c b/gcc/testsuite/gcc.target/arm/simd/mve-vneg.c
index afd0d6087bd50b8d5e7812f0c2bc78ee63be7b0d..7945a060e25feafc9c2e9c2454c77a20fec57d8d 100644 (file)
--- a/gcc/testsuite/gcc.target/arm/simd/mve-vneg.c
+++ b/gcc/testsuite/gcc.target/arm/simd/mve-vneg.c
@@ -47,3 +47,6 @@ FUNC(f, float, 16, 8, -, vneg)
    functions above.  */
 /* { dg-final { scan-assembler-times {vneg.s[0-9]+  q[0-9]+, q[0-9]+} 6 } } */
 /* { dg-final { scan-assembler-times {vneg.f[0-9]+  q[0-9]+, q[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vldr[bhw].[0-9]+\tq[0-9]+} 8 } } */
+/* { dg-final { scan-assembler-times {vstr[bhw].[0-9]+\tq[0-9]+} 8 } } */
+/* { dg-final { scan-assembler-not {orr\tr[0-9]+, r[0-9]+, r[0-9]+} } } */