public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc(refs/users/meissner/heads/work064)] PATCH Generate XXSPLTIW on power10.
@ 2021-08-13 1:31 Michael Meissner
0 siblings, 0 replies; 2+ messages in thread
From: Michael Meissner @ 2021-08-13 1:31 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:9a29c2ad859d07101afe4412073fd39431a3f970
commit 9a29c2ad859d07101afe4412073fd39431a3f970
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Thu Aug 12 21:31:25 2021 -0400
PATCH Generate XXSPLTIW on power10.
This patch adds support to automatically generate the ISA 3.1 XXSPLTIW
instruction for V8HImode, V4SImode, and V4SFmode vectors. It does this by
adding support for vector constants that can be used, and adding a
VEC_DUPLICATE pattern to generate the actual XXSPLTIW instruction.
I rewrote the XXSPLTW built-in functions to use VEC_DUPLICATE instead of
UNSPEC.
This patch also updates the insn counts in the vec-splati-runnable.c test to
work with the new option to use XXSPLTIW to load up some vector constants.
I added 3 new tests to test loading up V8HI, V4SI, and V4SF vector
constants.
The pr87631-wrapv.c test needed to be adjusted to account for xxspltiw
code generation on power10.
2021-07-21 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/predicates.md (xxspltiw_operand): New predicate.
(easy_vector_constant): If we can use XXSPLTIW, the vector
constant is easy.
* config/rs6000/rs6000.c (xxspltib_constant_p): If we can generate
XXSPLTIW, don't generate a XXSPLTIB and an extend instruction.
(output_vec_const_move): Add support for loading up vector
constants with XXSPLTIW.
* config/rs6000/rs6000.h (TARGET_XXSPLTIW): New macro.
(SIGN_EXTEND_8BIT): New macro.
(SIGN_EXTEND_16BIT): New macro.
(SIGN_EXTEND_32BIT): New macro.
* config/rs6000/rs6000.opt (-mxxspltiw): New debug switch.
* config/rs6000/vsx.md (UNSPEC_XXSPLTIW): Delete.
(xxspltiw_v8hi): New insn.
(xxspltiw_v4si): Rewrite to generate a vector constant.
(xxspltiw_v4sf): Rewrite to generate a vector constant.
(xxspltiw_v4si_inst): Delete.
(xxspltiw_v4sf_inst): Delete.
(xxspltiw_v8hi_dup): New insn.
(xxspltiw_v4si_dup): New insn.
(xxspltiw_v4sf_dup): New insn.
(XXSPLTIW): New mode iterator.
(XXSPLTIW splitter): New insn splitter for XXSPLTIW.
gcc/testsuite/
* gcc.target/powerpc/pr86731-fwrapv.c: Update insn counts on
power10.
* gcc.target/powerpc/vec-splati-runnable.c: Update insn counts.
* gcc.target/powerpc/vec-splat-constant-v4sf.c: New test.
* gcc.target/powerpc/vec-splat-constant-v4si.c: New test.
* gcc.target/powerpc/vec-splat-constant-v8hi.c: New test.
---
gcc/config/rs6000/predicates.md | 29 ++++
gcc/config/rs6000/rs6000.c | 11 +-
gcc/config/rs6000/rs6000.h | 24 +++
gcc/config/rs6000/rs6000.opt | 4 +
gcc/config/rs6000/vsx.md | 146 ++++++++++++++----
.../gcc.target/powerpc/pr86731-fwrapv.c | 9 +-
.../powerpc/vec-splat-constant-v4sf.c | 66 ++++++++
.../powerpc/vec-splat-constant-v4si.c | 51 ++++++
.../powerpc/vec-splat-constant-v8hi.c | 53 +++++++
.../gcc.target/powerpc/vec-splati-runnable.c | 4 +-
10 files changed, 358 insertions(+), 39 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c
create mode 100644 gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c
create mode 100644 gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c
diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 956e42bc514..203eded7927 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -640,6 +640,32 @@ (define_predicate "xxspltib_constant_nosplit"
return num_insns == 1;
})
+;; Return 1 if the operand is a CONST_VECTOR that can be loaded with the
+;; XXSPLTIW instruction. Do not return 1 if the constant can be generated with
+;; XXSPLTIB or VSPLTIS{H,W}
+(define_predicate "xxspltiw_operand"
+ (match_code "const_vector")
+{
+ if (!TARGET_XXSPLTIW)
+ return false;
+
+ if (mode != V8HImode && mode != V4SImode && mode != V4SFmode)
+ return false;
+
+ rtx element = CONST_VECTOR_ELT (op, 0);
+ for (size_t i = 1; i < GET_MODE_NUNITS (mode); i++)
+ if (!rtx_equal_p (element, CONST_VECTOR_ELT (op, i)))
+ return false;
+
+ if (element == CONST0_RTX (GET_MODE_INNER (mode)))
+ return false;
+
+ if (CONST_INT_P (element) && EASY_VECTOR_15 (INTVAL (element)))
+ return false;
+
+ return true;
+})
+
;; Return 1 if the operand is a CONST_VECTOR and can be loaded into a
;; vector register without using memory.
(define_predicate "easy_vector_constant"
@@ -653,6 +679,9 @@ (define_predicate "easy_vector_constant"
if (zero_constant (op, mode) || all_ones_constant (op, mode))
return true;
+ if (xxspltiw_operand (op, mode))
+ return true;
+
if (TARGET_P9_VECTOR
&& xxspltib_constant_p (op, mode, &num_insns, &value))
return true;
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 6b7baf36c2b..49c58554e7d 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -6506,9 +6506,11 @@ xxspltib_constant_p (rtx op,
/* See if we could generate vspltisw/vspltish directly instead of xxspltib +
sign extend. Special case 0/-1 to allow getting any VSX register instead
- of an Altivec register. */
- if ((mode == V4SImode || mode == V8HImode) && !IN_RANGE (value, -1, 0)
- && EASY_VECTOR_15 (value))
+ of an Altivec register. Also if we can generate a XXSPLTIW instruction,
+ don't emit a XXSPLTIB and an extend instruction. */
+ if ((mode == V4SImode || mode == V8HImode)
+ && !IN_RANGE (value, -1, 0)
+ && (EASY_VECTOR_15 (value) || TARGET_XXSPLTIW))
return false;
/* Return # of instructions and the constant byte for XXSPLTIB. */
@@ -6569,6 +6571,9 @@ output_vec_const_move (rtx *operands)
gcc_unreachable ();
}
+ if (xxspltiw_operand (vec, mode))
+ return "#";
+
if (TARGET_P9_VECTOR
&& xxspltib_constant_p (vec, mode, &num_insns, &xxspltib_value))
{
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index c5f38f26649..b8f4f824af1 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -510,6 +510,11 @@ extern int rs6000_vector_align[];
#define TARGET_IBM128 (TARGET_FLOAT128_TYPE \
|| (!TARGET_IEEEQUAD && TARGET_LONG_DOUBLE_128))
+/* Whether we can generate the XXSPLTI* prefixed instructions. We also need
+ VSX instructions to be generated. */
+#define TARGET_XXSPLTIW (TARGET_XXSPLTIW_DEBUG && TARGET_PREFIXED \
+ && TARGET_VSX)
+
/* In switching from using target_flags to using rs6000_isa_flags, the options
machinery creates OPTION_MASK_<xxx> instead of MASK_<xxx>. For now map
OPTION_MASK_<xxx> back into MASK_<xxx>. */
@@ -2613,3 +2618,22 @@ while (0)
rs6000_asm_output_opcode (STREAM); \
} \
while (0)
+
+/* Provide macros for sign-extending values. */
+#if HOST_BITS_PER_CHAR == 8
+#define SIGN_EXTEND_8BIT(X) ((HOST_WIDE_INT)(signed char)(X))
+#else
+#define SIGN_EXTEND_8BIT(X) ((((X) & 0xff) ^ 0x80) - 0x80)
+#endif
+
+#if HOST_BITS_PER_SHORT == 16
+#define SIGN_EXTEND_16BIT(X) ((HOST_WIDE_INT)(short)(X))
+#else
+#define SIGN_EXTEND_16BIT(X) ((((X) & 0xffff) ^ 0x8000) - 0x8000)
+#endif
+
+#if HOST_BITS_PER_INT == 32
+#define SIGN_EXTEND_32BIT(X) ((HOST_WIDE_INT)(int)(X))
+#else
+#define SIGN_EXTEND_32BIT(X) ((((X) & 0xffffffff) ^ 0x80000000) - 0x80000000)
+#endif
diff --git a/gcc/config/rs6000/rs6000.opt b/gcc/config/rs6000/rs6000.opt
index 0538db387dc..9548334d846 100644
--- a/gcc/config/rs6000/rs6000.opt
+++ b/gcc/config/rs6000/rs6000.opt
@@ -639,3 +639,7 @@ Enable instructions that guard against return-oriented programming attacks.
mprivileged
Target Var(rs6000_privileged) Init(0)
Generate code that will run in privileged state.
+
+mxxspltiw
+Target Undocumented Var(TARGET_XXSPLTIW_DEBUG) Init(1) Save
+Generate (do not generate) XXSPLTIW instructions.
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index cacdd0d4cc8..660e74bb991 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -373,7 +373,6 @@ (define_c_enum "unspec"
UNSPEC_VDIVES
UNSPEC_VDIVEU
UNSPEC_XXEVAL
- UNSPEC_XXSPLTIW
UNSPEC_XXSPLTID
UNSPEC_XXSPLTI32DX
UNSPEC_XXBLEND
@@ -6407,36 +6406,6 @@ (define_insn "mulv2di3"
[(set_attr "type" "veccomplex")])
\f
-;; XXSPLTIW built-in function support
-(define_insn "xxspltiw_v4si"
- [(set (match_operand:V4SI 0 "register_operand" "=wa")
- (unspec:V4SI [(match_operand:SI 1 "s32bit_cint_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
- "xxspltiw %x0,%1"
- [(set_attr "type" "vecsimple")
- (set_attr "prefixed" "yes")])
-
-(define_expand "xxspltiw_v4sf"
- [(set (match_operand:V4SF 0 "register_operand" "=wa")
- (unspec:V4SF [(match_operand:SF 1 "const_double_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
-{
- long value = rs6000_const_f32_to_i32 (operands[1]);
- emit_insn (gen_xxspltiw_v4sf_inst (operands[0], GEN_INT (value)));
- DONE;
-})
-
-(define_insn "xxspltiw_v4sf_inst"
- [(set (match_operand:V4SF 0 "register_operand" "=wa")
- (unspec:V4SF [(match_operand:SI 1 "c32bit_cint_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
- "xxspltiw %x0,%1"
- [(set_attr "type" "vecsimple")
- (set_attr "prefixed" "yes")])
-
;; XXSPLTIDP built-in function support
(define_expand "xxspltidp_v2df"
[(set (match_operand:V2DF 0 "register_operand" )
@@ -6589,3 +6558,118 @@ (define_insn "xxeval"
[(set_attr "type" "vecsimple")
(set_attr "prefixed" "yes")])
+;; XXSPLTIW built-in function support. Convert to a vector constant, which
+;; will then be optimized to the XXSPLTIW instruction.
+(define_expand "xxspltiw_v4si"
+ [(use (match_operand:V4SI 0 "register_operand"))
+ (use (match_operand:SI 1 "s32bit_cint_operand"))]
+ "TARGET_POWER10"
+{
+ rtx op1 = operands[1];
+ rtvec rv = gen_rtvec (4, op1, op1, op1, op1);
+ rtx vec_constant = gen_rtx_CONST_VECTOR (V4SImode, rv);
+ emit_move_insn (operands[0], vec_constant);
+})
+
+(define_expand "xxspltiw_v4sf"
+ [(use (match_operand:V4SF 0 "register_operand"))
+ (use (match_operand:SF 1 "const_double_operand"))]
+ "TARGET_POWER10"
+{
+ rtx op1 = operands[1];
+ rtvec rv = gen_rtvec (4, op1, op1, op1, op1);
+ rtx vec_constant = gen_rtx_CONST_VECTOR (V4SFmode, rv);
+ emit_move_insn (operands[0], vec_constant);
+})
+
+;; XXSPLTIW support. Add support for the XXSPLTIW built-in functions, and to
+;; use XXSPLTIW to load up vector V8HImode, V4SImode, and V4SFmode vector
+;; constants where all elements are the the same. We special case loading up
+;; integer -16..15 and floating point 0.0f, since we can use the shorter
+;; XXSPLTIB, VSPLTISH, and VSPLTISW instructions.
+
+(define_insn "*xxspltiw_v8hi_dup"
+ [(set (match_operand:V8HI 0 "vsx_register_operand" "=wa,wa,v,wa")
+ (vec_duplicate:V8HI
+ (match_operand 1 "const_int_operand" "O,wM,wB,n")))]
+ "TARGET_XXSPLTIW"
+{
+ HOST_WIDE_INT sign_value = SIGN_EXTEND_16BIT (INTVAL (operands[1]));
+
+ if (sign_value == 0)
+ return "xxspltib %x0,0";
+
+ if (sign_value == -1)
+ return "xxspltib %x0,255";
+
+ int r = reg_or_subregno (operands[0]);
+ if (ALTIVEC_REGNO_P (r) && EASY_VECTOR_15 (sign_value))
+ {
+ operands[2] = GEN_INT (sign_value);
+ return "vspltish %0,%1";
+ }
+
+ HOST_WIDE_INT uns_value = sign_value & 0xffff;
+ operands[2] = GEN_INT ((uns_value << 16) | uns_value);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecperm")
+ (set_attr "prefixed" "*,*,*,yes")])
+
+(define_insn "*xxspltiw_v4si_dup"
+ [(set (match_operand:V4SI 0 "vsx_register_operand" "=wa,wa,v,wa")
+ (vec_duplicate:V4SI
+ (match_operand 1 "const_int_operand" "O,wM,wB,n")))]
+ "TARGET_XXSPLTIW"
+{
+ HOST_WIDE_INT sign_value = SIGN_EXTEND_32BIT (INTVAL (operands[1]));
+
+ if (sign_value == 0)
+ return "xxspltib %x0,0";
+
+ if (sign_value == -1)
+ return "xxspltib %x0,255";
+
+ int r = reg_or_subregno (operands[0]);
+ if (ALTIVEC_REGNO_P (r) && EASY_VECTOR_15 (sign_value))
+ {
+ operands[2] = GEN_INT (sign_value);
+ return "vspltisw %0,%2";
+ }
+
+ /* The assembler doesn't like negative values. */
+ operands[2] = GEN_INT (sign_value & 0xffffffff);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecperm")
+ (set_attr "prefixed" "*,*,*,yes")])
+
+(define_insn "xxspltiw_v4sf_dup"
+ [(set (match_operand:V4SF 0 "vsx_register_operand" "=wa,wa")
+ (vec_duplicate:V4SF
+ (match_operand:SF 1 "const_double_operand" "O,F")))]
+ "TARGET_XXSPLTIW"
+{
+ if (operands[1] == CONST0_RTX (SFmode))
+ return "xxspltib %x0,0";
+
+ /* The assembler doesn't like negative values. */
+ long value = rs6000_const_f32_to_i32 (operands[1]);
+ operands[2] = GEN_INT (value & 0xffffffff);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecsimple")
+ (set_attr "prefixed" "*,yes")])
+
+;; Convert vector constant to vec_duplicate.
+(define_mode_iterator XXSPLTIW [V8HI V4SI V4SF])
+
+(define_split
+ [(set (match_operand:XXSPLTIW 0 "vsx_register_operand")
+ (match_operand:XXSPLTIW 1 "xxspltiw_operand"))]
+ "TARGET_XXSPLTIW"
+ [(set (match_dup 0)
+ (vec_duplicate:<MODE> (match_dup 2)))]
+{
+ operands[2] = CONST_VECTOR_ELT (operands[1], 0);
+})
diff --git a/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c b/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
index f312550f04d..22e43d21565 100644
--- a/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
+++ b/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
@@ -57,7 +57,12 @@ vector signed int splats3(void)
If folding is enabled, the vec_sl tests using vector long long type will
generate a lvx instead of a vspltisw+vsld pair. */
-/* { dg-final { scan-assembler-times {\mvspltis[bhw]\M|\mxxspltib\M} 7 } } */
-/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 7 } } */
+/* { dg-final { scan-assembler-times {\mvspltis[bhw]\M|\mxxspltib\M} 7 { target { ! has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 7 { target { ! has_arch_pwr10 } } } } */
+
+/* { dg-final { scan-assembler-times {\mxxspltib\M} 2 { target { has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 5 { target { has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 2 { target { has_arch_pwr10 } } } } */
+
/* { dg-final { scan-assembler-times {\mlvx\M|\mlxvd2x\M} 0 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c
new file mode 100644
index 00000000000..06830b02076
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c
@@ -0,0 +1,66 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V4SF vector constants. */
+
+vector float
+v4sf_const_1 (void)
+{
+ return (vector float) { 1.0f, 1.0f, 1.0f, 1.0f }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_nan (void)
+{
+ return (vector float) { __builtin_nanf (""),
+ __builtin_nanf (""),
+ __builtin_nanf (""),
+ __builtin_nanf ("") }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_inf (void)
+{
+ return (vector float) { __builtin_inff (),
+ __builtin_inff (),
+ __builtin_inff (),
+ __builtin_inff () }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_m0 (void)
+{
+ return (vector float) { -0.0f, -0.0f, -0.0f, -0.0f }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_1 (void)
+{
+ return vec_splats (1.0f); /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_nan (void)
+{
+ return vec_splats (__builtin_nanf ("")); /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_inf (void)
+{
+ return vec_splats (__builtin_inff ()); /* XXSPLTIW. */
+}
+
+vector float
+v8hi_splats_m0 (void)
+{
+ return vec_splats (-0.0f); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 8 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c
new file mode 100644
index 00000000000..02d0c6d66a2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c
@@ -0,0 +1,51 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V4SI vector constants. We make sure
+ the power9 support (XXSPLTIB/VEXTSB2W) is not done. */
+
+vector int
+v4si_const_1 (void)
+{
+ return (vector int) { 1, 1, 1, 1 }; /* VSLTPISW. */
+}
+
+vector int
+v4si_const_126 (void)
+{
+ return (vector int) { 126, 126, 126, 126 }; /* XXSPLTIW. */
+}
+
+vector int
+v4si_const_1023 (void)
+{
+ return (vector int) { 1023, 1023, 1023, 1023 }; /* XXSPLTIW. */
+}
+
+vector int
+v4si_splats_1 (void)
+{
+ return vec_splats (1); /* VSLTPISW. */
+}
+
+vector int
+v4si_splats_126 (void)
+{
+ return vec_splats (126); /* XXSPLTIW. */
+}
+
+vector int
+v8hi_splats_1023 (void)
+{
+ return vec_splats (1023); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mvspltisw\M} 2 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mvextsb2w\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c
new file mode 100644
index 00000000000..e6d0fab6d67
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c
@@ -0,0 +1,53 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V8HI vector constants. We make sure
+ the power9 support (XXSPLTIB/VUPKLSB) is not done. */
+
+vector short
+v8hi_const_1 (void)
+{
+ return (vector short) { 1, 1, 1, 1, 1, 1, 1, 1 }; /* VSLTPISH. */
+}
+
+vector short
+v8hi_const_126 (void)
+{
+ return (vector short) { 126, 126, 126, 126,
+ 126, 126, 126, 126 }; /* XXSPLTIW. */
+}
+
+vector short
+v8hi_const_1023 (void)
+{
+ return (vector short) { 1023, 1023, 1023, 1023,
+ 1023, 1023, 1023, 1023 }; /* XXSPLTIW. */
+}
+
+vector short
+v8hi_splats_1 (void)
+{
+ return vec_splats ((short)1); /* VSLTPISH. */
+}
+
+vector short
+v8hi_splats_126 (void)
+{
+ return vec_splats ((short)126); /* XXSPLTIW. */
+}
+
+vector short
+v8hi_splats_1023 (void)
+{
+ return vec_splats ((short)1023); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mvspltish\M} 2 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mvupklsb\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c b/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
index a135279b1d7..f49ef91422e 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
@@ -149,8 +149,6 @@ main (int argc, char *argv [])
return 0;
}
-/* { dg-final { scan-assembler-times {\mxxspltiw\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 1 } } */
/* { dg-final { scan-assembler-times {\mxxspltidp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxxsplti32dx\M} 3 } } */
-
-
--
2.31.1
Diff:
---
gcc/config/rs6000/predicates.md | 29 ++++
gcc/config/rs6000/rs6000.c | 11 +-
gcc/config/rs6000/rs6000.h | 24 ++++
gcc/config/rs6000/rs6000.opt | 4 +
gcc/config/rs6000/vsx.md | 146 ++++++++++++++++-----
gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c | 9 +-
.../gcc.target/powerpc/vec-splat-constant-v4sf.c | 66 ++++++++++
.../gcc.target/powerpc/vec-splat-constant-v4si.c | 51 +++++++
.../gcc.target/powerpc/vec-splat-constant-v8hi.c | 53 ++++++++
.../gcc.target/powerpc/vec-splati-runnable.c | 4 +-
10 files changed, 358 insertions(+), 39 deletions(-)
diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 956e42bc514..203eded7927 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -640,6 +640,32 @@
return num_insns == 1;
})
+;; Return 1 if the operand is a CONST_VECTOR that can be loaded with the
+;; XXSPLTIW instruction. Do not return 1 if the constant can be generated with
+;; XXSPLTIB or VSPLTIS{H,W}
+(define_predicate "xxspltiw_operand"
+ (match_code "const_vector")
+{
+ if (!TARGET_XXSPLTIW)
+ return false;
+
+ if (mode != V8HImode && mode != V4SImode && mode != V4SFmode)
+ return false;
+
+ rtx element = CONST_VECTOR_ELT (op, 0);
+ for (size_t i = 1; i < GET_MODE_NUNITS (mode); i++)
+ if (!rtx_equal_p (element, CONST_VECTOR_ELT (op, i)))
+ return false;
+
+ if (element == CONST0_RTX (GET_MODE_INNER (mode)))
+ return false;
+
+ if (CONST_INT_P (element) && EASY_VECTOR_15 (INTVAL (element)))
+ return false;
+
+ return true;
+})
+
;; Return 1 if the operand is a CONST_VECTOR and can be loaded into a
;; vector register without using memory.
(define_predicate "easy_vector_constant"
@@ -653,6 +679,9 @@
if (zero_constant (op, mode) || all_ones_constant (op, mode))
return true;
+ if (xxspltiw_operand (op, mode))
+ return true;
+
if (TARGET_P9_VECTOR
&& xxspltib_constant_p (op, mode, &num_insns, &value))
return true;
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 60f406a4ff6..50139c803c5 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -6511,9 +6511,11 @@ xxspltib_constant_p (rtx op,
/* See if we could generate vspltisw/vspltish directly instead of xxspltib +
sign extend. Special case 0/-1 to allow getting any VSX register instead
- of an Altivec register. */
- if ((mode == V4SImode || mode == V8HImode) && !IN_RANGE (value, -1, 0)
- && EASY_VECTOR_15 (value))
+ of an Altivec register. Also if we can generate a XXSPLTIW instruction,
+ don't emit a XXSPLTIB and an extend instruction. */
+ if ((mode == V4SImode || mode == V8HImode)
+ && !IN_RANGE (value, -1, 0)
+ && (EASY_VECTOR_15 (value) || TARGET_XXSPLTIW))
return false;
/* Return # of instructions and the constant byte for XXSPLTIB. */
@@ -6574,6 +6576,9 @@ output_vec_const_move (rtx *operands)
gcc_unreachable ();
}
+ if (xxspltiw_operand (vec, mode))
+ return "#";
+
if (TARGET_P9_VECTOR
&& xxspltib_constant_p (vec, mode, &num_insns, &xxspltib_value))
{
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index c5d20d240f2..88c10c55eb5 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -504,6 +504,11 @@ extern int rs6000_vector_align[];
#define TARGET_MINMAX (TARGET_HARD_FLOAT && TARGET_PPC_GFXOPT \
&& (TARGET_P9_MINMAX || !flag_trapping_math))
+/* Whether we can generate the XXSPLTI* prefixed instructions. We also need
+ VSX instructions to be generated. */
+#define TARGET_XXSPLTIW (TARGET_XXSPLTIW_DEBUG && TARGET_PREFIXED \
+ && TARGET_VSX)
+
/* In switching from using target_flags to using rs6000_isa_flags, the options
machinery creates OPTION_MASK_<xxx> instead of MASK_<xxx>. For now map
OPTION_MASK_<xxx> back into MASK_<xxx>. */
@@ -2609,3 +2614,22 @@ while (0)
rs6000_asm_output_opcode (STREAM); \
} \
while (0)
+
+/* Provide macros for sign-extending values. */
+#if HOST_BITS_PER_CHAR == 8
+#define SIGN_EXTEND_8BIT(X) ((HOST_WIDE_INT)(signed char)(X))
+#else
+#define SIGN_EXTEND_8BIT(X) ((((X) & 0xff) ^ 0x80) - 0x80)
+#endif
+
+#if HOST_BITS_PER_SHORT == 16
+#define SIGN_EXTEND_16BIT(X) ((HOST_WIDE_INT)(short)(X))
+#else
+#define SIGN_EXTEND_16BIT(X) ((((X) & 0xffff) ^ 0x8000) - 0x8000)
+#endif
+
+#if HOST_BITS_PER_INT == 32
+#define SIGN_EXTEND_32BIT(X) ((HOST_WIDE_INT)(int)(X))
+#else
+#define SIGN_EXTEND_32BIT(X) ((((X) & 0xffffffff) ^ 0x80000000) - 0x80000000)
+#endif
diff --git a/gcc/config/rs6000/rs6000.opt b/gcc/config/rs6000/rs6000.opt
index 0538db387dc..9548334d846 100644
--- a/gcc/config/rs6000/rs6000.opt
+++ b/gcc/config/rs6000/rs6000.opt
@@ -639,3 +639,7 @@ Enable instructions that guard against return-oriented programming attacks.
mprivileged
Target Var(rs6000_privileged) Init(0)
Generate code that will run in privileged state.
+
+mxxspltiw
+Target Undocumented Var(TARGET_XXSPLTIW_DEBUG) Init(1) Save
+Generate (do not generate) XXSPLTIW instructions.
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index e4ca6e94d49..a2a1571484e 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -373,7 +373,6 @@
UNSPEC_VDIVES
UNSPEC_VDIVEU
UNSPEC_XXEVAL
- UNSPEC_XXSPLTIW
UNSPEC_XXSPLTID
UNSPEC_XXSPLTI32DX
UNSPEC_XXBLEND
@@ -6407,36 +6406,6 @@
[(set_attr "type" "veccomplex")])
\f
-;; XXSPLTIW built-in function support
-(define_insn "xxspltiw_v4si"
- [(set (match_operand:V4SI 0 "register_operand" "=wa")
- (unspec:V4SI [(match_operand:SI 1 "s32bit_cint_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
- "xxspltiw %x0,%1"
- [(set_attr "type" "vecsimple")
- (set_attr "prefixed" "yes")])
-
-(define_expand "xxspltiw_v4sf"
- [(set (match_operand:V4SF 0 "register_operand" "=wa")
- (unspec:V4SF [(match_operand:SF 1 "const_double_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
-{
- long value = rs6000_const_f32_to_i32 (operands[1]);
- emit_insn (gen_xxspltiw_v4sf_inst (operands[0], GEN_INT (value)));
- DONE;
-})
-
-(define_insn "xxspltiw_v4sf_inst"
- [(set (match_operand:V4SF 0 "register_operand" "=wa")
- (unspec:V4SF [(match_operand:SI 1 "c32bit_cint_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
- "xxspltiw %x0,%1"
- [(set_attr "type" "vecsimple")
- (set_attr "prefixed" "yes")])
-
;; XXSPLTIDP built-in function support
(define_expand "xxspltidp_v2df"
[(set (match_operand:V2DF 0 "register_operand" )
@@ -6589,3 +6558,118 @@
[(set_attr "type" "vecsimple")
(set_attr "prefixed" "yes")])
+;; XXSPLTIW built-in function support. Convert to a vector constant, which
+;; will then be optimized to the XXSPLTIW instruction.
+(define_expand "xxspltiw_v4si"
+ [(use (match_operand:V4SI 0 "register_operand"))
+ (use (match_operand:SI 1 "s32bit_cint_operand"))]
+ "TARGET_POWER10"
+{
+ rtx op1 = operands[1];
+ rtvec rv = gen_rtvec (4, op1, op1, op1, op1);
+ rtx vec_constant = gen_rtx_CONST_VECTOR (V4SImode, rv);
+ emit_move_insn (operands[0], vec_constant);
+})
+
+(define_expand "xxspltiw_v4sf"
+ [(use (match_operand:V4SF 0 "register_operand"))
+ (use (match_operand:SF 1 "const_double_operand"))]
+ "TARGET_POWER10"
+{
+ rtx op1 = operands[1];
+ rtvec rv = gen_rtvec (4, op1, op1, op1, op1);
+ rtx vec_constant = gen_rtx_CONST_VECTOR (V4SFmode, rv);
+ emit_move_insn (operands[0], vec_constant);
+})
+
+;; XXSPLTIW support. Add support for the XXSPLTIW built-in functions, and to
+;; use XXSPLTIW to load up vector V8HImode, V4SImode, and V4SFmode vector
+;; constants where all elements are the the same. We special case loading up
+;; integer -16..15 and floating point 0.0f, since we can use the shorter
+;; XXSPLTIB, VSPLTISH, and VSPLTISW instructions.
+
+(define_insn "*xxspltiw_v8hi_dup"
+ [(set (match_operand:V8HI 0 "vsx_register_operand" "=wa,wa,v,wa")
+ (vec_duplicate:V8HI
+ (match_operand 1 "const_int_operand" "O,wM,wB,n")))]
+ "TARGET_XXSPLTIW"
+{
+ HOST_WIDE_INT sign_value = SIGN_EXTEND_16BIT (INTVAL (operands[1]));
+
+ if (sign_value == 0)
+ return "xxspltib %x0,0";
+
+ if (sign_value == -1)
+ return "xxspltib %x0,255";
+
+ int r = reg_or_subregno (operands[0]);
+ if (ALTIVEC_REGNO_P (r) && EASY_VECTOR_15 (sign_value))
+ {
+ operands[2] = GEN_INT (sign_value);
+ return "vspltish %0,%1";
+ }
+
+ HOST_WIDE_INT uns_value = sign_value & 0xffff;
+ operands[2] = GEN_INT ((uns_value << 16) | uns_value);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecperm")
+ (set_attr "prefixed" "*,*,*,yes")])
+
+(define_insn "*xxspltiw_v4si_dup"
+ [(set (match_operand:V4SI 0 "vsx_register_operand" "=wa,wa,v,wa")
+ (vec_duplicate:V4SI
+ (match_operand 1 "const_int_operand" "O,wM,wB,n")))]
+ "TARGET_XXSPLTIW"
+{
+ HOST_WIDE_INT sign_value = SIGN_EXTEND_32BIT (INTVAL (operands[1]));
+
+ if (sign_value == 0)
+ return "xxspltib %x0,0";
+
+ if (sign_value == -1)
+ return "xxspltib %x0,255";
+
+ int r = reg_or_subregno (operands[0]);
+ if (ALTIVEC_REGNO_P (r) && EASY_VECTOR_15 (sign_value))
+ {
+ operands[2] = GEN_INT (sign_value);
+ return "vspltisw %0,%2";
+ }
+
+ /* The assembler doesn't like negative values. */
+ operands[2] = GEN_INT (sign_value & 0xffffffff);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecperm")
+ (set_attr "prefixed" "*,*,*,yes")])
+
+(define_insn "xxspltiw_v4sf_dup"
+ [(set (match_operand:V4SF 0 "vsx_register_operand" "=wa,wa")
+ (vec_duplicate:V4SF
+ (match_operand:SF 1 "const_double_operand" "O,F")))]
+ "TARGET_XXSPLTIW"
+{
+ if (operands[1] == CONST0_RTX (SFmode))
+ return "xxspltib %x0,0";
+
+ /* The assembler doesn't like negative values. */
+ long value = rs6000_const_f32_to_i32 (operands[1]);
+ operands[2] = GEN_INT (value & 0xffffffff);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecsimple")
+ (set_attr "prefixed" "*,yes")])
+
+;; Convert vector constant to vec_duplicate.
+(define_mode_iterator XXSPLTIW [V8HI V4SI V4SF])
+
+(define_split
+ [(set (match_operand:XXSPLTIW 0 "vsx_register_operand")
+ (match_operand:XXSPLTIW 1 "xxspltiw_operand"))]
+ "TARGET_XXSPLTIW"
+ [(set (match_dup 0)
+ (vec_duplicate:<MODE> (match_dup 2)))]
+{
+ operands[2] = CONST_VECTOR_ELT (operands[1], 0);
+})
diff --git a/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c b/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
index f312550f04d..22e43d21565 100644
--- a/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
+++ b/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
@@ -57,7 +57,12 @@ vector signed int splats3(void)
If folding is enabled, the vec_sl tests using vector long long type will
generate a lvx instead of a vspltisw+vsld pair. */
-/* { dg-final { scan-assembler-times {\mvspltis[bhw]\M|\mxxspltib\M} 7 } } */
-/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 7 } } */
+/* { dg-final { scan-assembler-times {\mvspltis[bhw]\M|\mxxspltib\M} 7 { target { ! has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 7 { target { ! has_arch_pwr10 } } } } */
+
+/* { dg-final { scan-assembler-times {\mxxspltib\M} 2 { target { has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 5 { target { has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 2 { target { has_arch_pwr10 } } } } */
+
/* { dg-final { scan-assembler-times {\mlvx\M|\mlxvd2x\M} 0 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c
new file mode 100644
index 00000000000..06830b02076
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c
@@ -0,0 +1,66 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V4SF vector constants. */
+
+vector float
+v4sf_const_1 (void)
+{
+ return (vector float) { 1.0f, 1.0f, 1.0f, 1.0f }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_nan (void)
+{
+ return (vector float) { __builtin_nanf (""),
+ __builtin_nanf (""),
+ __builtin_nanf (""),
+ __builtin_nanf ("") }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_inf (void)
+{
+ return (vector float) { __builtin_inff (),
+ __builtin_inff (),
+ __builtin_inff (),
+ __builtin_inff () }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_m0 (void)
+{
+ return (vector float) { -0.0f, -0.0f, -0.0f, -0.0f }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_1 (void)
+{
+ return vec_splats (1.0f); /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_nan (void)
+{
+ return vec_splats (__builtin_nanf ("")); /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_inf (void)
+{
+ return vec_splats (__builtin_inff ()); /* XXSPLTIW. */
+}
+
+vector float
+v8hi_splats_m0 (void)
+{
+ return vec_splats (-0.0f); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 8 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c
new file mode 100644
index 00000000000..02d0c6d66a2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c
@@ -0,0 +1,51 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V4SI vector constants. We make sure
+ the power9 support (XXSPLTIB/VEXTSB2W) is not done. */
+
+vector int
+v4si_const_1 (void)
+{
+ return (vector int) { 1, 1, 1, 1 }; /* VSLTPISW. */
+}
+
+vector int
+v4si_const_126 (void)
+{
+ return (vector int) { 126, 126, 126, 126 }; /* XXSPLTIW. */
+}
+
+vector int
+v4si_const_1023 (void)
+{
+ return (vector int) { 1023, 1023, 1023, 1023 }; /* XXSPLTIW. */
+}
+
+vector int
+v4si_splats_1 (void)
+{
+ return vec_splats (1); /* VSLTPISW. */
+}
+
+vector int
+v4si_splats_126 (void)
+{
+ return vec_splats (126); /* XXSPLTIW. */
+}
+
+vector int
+v8hi_splats_1023 (void)
+{
+ return vec_splats (1023); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mvspltisw\M} 2 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mvextsb2w\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c
new file mode 100644
index 00000000000..e6d0fab6d67
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c
@@ -0,0 +1,53 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V8HI vector constants. We make sure
+ the power9 support (XXSPLTIB/VUPKLSB) is not done. */
+
+vector short
+v8hi_const_1 (void)
+{
+ return (vector short) { 1, 1, 1, 1, 1, 1, 1, 1 }; /* VSLTPISH. */
+}
+
+vector short
+v8hi_const_126 (void)
+{
+ return (vector short) { 126, 126, 126, 126,
+ 126, 126, 126, 126 }; /* XXSPLTIW. */
+}
+
+vector short
+v8hi_const_1023 (void)
+{
+ return (vector short) { 1023, 1023, 1023, 1023,
+ 1023, 1023, 1023, 1023 }; /* XXSPLTIW. */
+}
+
+vector short
+v8hi_splats_1 (void)
+{
+ return vec_splats ((short)1); /* VSLTPISH. */
+}
+
+vector short
+v8hi_splats_126 (void)
+{
+ return vec_splats ((short)126); /* XXSPLTIW. */
+}
+
+vector short
+v8hi_splats_1023 (void)
+{
+ return vec_splats ((short)1023); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mvspltish\M} 2 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mvupklsb\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c b/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
index a135279b1d7..f49ef91422e 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
@@ -149,8 +149,6 @@ main (int argc, char *argv [])
return 0;
}
-/* { dg-final { scan-assembler-times {\mxxspltiw\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 1 } } */
/* { dg-final { scan-assembler-times {\mxxspltidp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxxsplti32dx\M} 3 } } */
-
-
^ permalink raw reply [flat|nested] 2+ messages in thread
* [gcc(refs/users/meissner/heads/work064)] PATCH Generate XXSPLTIW on power10.
@ 2021-08-13 2:00 Michael Meissner
0 siblings, 0 replies; 2+ messages in thread
From: Michael Meissner @ 2021-08-13 2:00 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:f0030c7727bebfd43dbe62396b9d55bdea2ebfcd
commit f0030c7727bebfd43dbe62396b9d55bdea2ebfcd
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Thu Aug 12 22:00:11 2021 -0400
PATCH Generate XXSPLTIW on power10.
This patch adds support to automatically generate the ISA 3.1 XXSPLTIW
instruction for V8HImode, V4SImode, and V4SFmode vectors. It does this by
adding support for vector constants that can be used, and adding a
VEC_DUPLICATE pattern to generate the actual XXSPLTIW instruction.
I rewrote the XXSPLTW built-in functions to use VEC_DUPLICATE instead of
UNSPEC.
This patch also updates the insn counts in the vec-splati-runnable.c test to
work with the new option to use XXSPLTIW to load up some vector constants.
I added 3 new tests to test loading up V8HI, V4SI, and V4SF vector
constants.
The pr87631-wrapv.c test needed to be adjusted to account for xxspltiw
code generation on power10.
2021-07-21 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/predicates.md (xxspltiw_operand): New predicate.
(easy_vector_constant): If we can use XXSPLTIW, the vector
constant is easy.
* config/rs6000/rs6000.c (xxspltib_constant_p): If we can generate
XXSPLTIW, don't generate a XXSPLTIB and an extend instruction.
(output_vec_const_move): Add support for loading up vector
constants with XXSPLTIW.
* config/rs6000/rs6000.h (TARGET_XXSPLTIW): New macro.
(SIGN_EXTEND_8BIT): New macro.
(SIGN_EXTEND_16BIT): New macro.
(SIGN_EXTEND_32BIT): New macro.
* config/rs6000/rs6000.opt (-mxxspltiw): New debug switch.
* config/rs6000/vsx.md (UNSPEC_XXSPLTIW): Delete.
(xxspltiw_v8hi): New insn.
(xxspltiw_v4si): Rewrite to generate a vector constant.
(xxspltiw_v4sf): Rewrite to generate a vector constant.
(xxspltiw_v4si_inst): Delete.
(xxspltiw_v4sf_inst): Delete.
(xxspltiw_v8hi_dup): New insn.
(xxspltiw_v4si_dup): New insn.
(xxspltiw_v4sf_dup): New insn.
(XXSPLTIW): New mode iterator.
(XXSPLTIW splitter): New insn splitter for XXSPLTIW.
gcc/testsuite/
* gcc.target/powerpc/pr86731-fwrapv.c: Update insn counts on
power10.
* gcc.target/powerpc/vec-splati-runnable.c: Update insn counts.
* gcc.target/powerpc/vec-splat-constant-v4sf.c: New test.
* gcc.target/powerpc/vec-splat-constant-v4si.c: New test.
* gcc.target/powerpc/vec-splat-constant-v8hi.c: New test.
Diff:
---
gcc/config/rs6000/predicates.md | 29 ++++
gcc/config/rs6000/rs6000.c | 11 +-
gcc/config/rs6000/rs6000.h | 24 ++++
gcc/config/rs6000/rs6000.opt | 4 +
gcc/config/rs6000/vsx.md | 146 ++++++++++++++++-----
gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c | 9 +-
.../gcc.target/powerpc/vec-splat-constant-v4sf.c | 66 ++++++++++
.../gcc.target/powerpc/vec-splat-constant-v4si.c | 51 +++++++
.../gcc.target/powerpc/vec-splat-constant-v8hi.c | 53 ++++++++
.../gcc.target/powerpc/vec-splati-runnable.c | 4 +-
10 files changed, 358 insertions(+), 39 deletions(-)
diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 956e42bc514..203eded7927 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -640,6 +640,32 @@
return num_insns == 1;
})
+;; Return 1 if the operand is a CONST_VECTOR that can be loaded with the
+;; XXSPLTIW instruction. Do not return 1 if the constant can be generated with
+;; XXSPLTIB or VSPLTIS{H,W}
+(define_predicate "xxspltiw_operand"
+ (match_code "const_vector")
+{
+ if (!TARGET_XXSPLTIW)
+ return false;
+
+ if (mode != V8HImode && mode != V4SImode && mode != V4SFmode)
+ return false;
+
+ rtx element = CONST_VECTOR_ELT (op, 0);
+ for (size_t i = 1; i < GET_MODE_NUNITS (mode); i++)
+ if (!rtx_equal_p (element, CONST_VECTOR_ELT (op, i)))
+ return false;
+
+ if (element == CONST0_RTX (GET_MODE_INNER (mode)))
+ return false;
+
+ if (CONST_INT_P (element) && EASY_VECTOR_15 (INTVAL (element)))
+ return false;
+
+ return true;
+})
+
;; Return 1 if the operand is a CONST_VECTOR and can be loaded into a
;; vector register without using memory.
(define_predicate "easy_vector_constant"
@@ -653,6 +679,9 @@
if (zero_constant (op, mode) || all_ones_constant (op, mode))
return true;
+ if (xxspltiw_operand (op, mode))
+ return true;
+
if (TARGET_P9_VECTOR
&& xxspltib_constant_p (op, mode, &num_insns, &value))
return true;
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 60f406a4ff6..50139c803c5 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -6511,9 +6511,11 @@ xxspltib_constant_p (rtx op,
/* See if we could generate vspltisw/vspltish directly instead of xxspltib +
sign extend. Special case 0/-1 to allow getting any VSX register instead
- of an Altivec register. */
- if ((mode == V4SImode || mode == V8HImode) && !IN_RANGE (value, -1, 0)
- && EASY_VECTOR_15 (value))
+ of an Altivec register. Also if we can generate a XXSPLTIW instruction,
+ don't emit a XXSPLTIB and an extend instruction. */
+ if ((mode == V4SImode || mode == V8HImode)
+ && !IN_RANGE (value, -1, 0)
+ && (EASY_VECTOR_15 (value) || TARGET_XXSPLTIW))
return false;
/* Return # of instructions and the constant byte for XXSPLTIB. */
@@ -6574,6 +6576,9 @@ output_vec_const_move (rtx *operands)
gcc_unreachable ();
}
+ if (xxspltiw_operand (vec, mode))
+ return "#";
+
if (TARGET_P9_VECTOR
&& xxspltib_constant_p (vec, mode, &num_insns, &xxspltib_value))
{
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index c5d20d240f2..88c10c55eb5 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -504,6 +504,11 @@ extern int rs6000_vector_align[];
#define TARGET_MINMAX (TARGET_HARD_FLOAT && TARGET_PPC_GFXOPT \
&& (TARGET_P9_MINMAX || !flag_trapping_math))
+/* Whether we can generate the XXSPLTI* prefixed instructions. We also need
+ VSX instructions to be generated. */
+#define TARGET_XXSPLTIW (TARGET_XXSPLTIW_DEBUG && TARGET_PREFIXED \
+ && TARGET_VSX)
+
/* In switching from using target_flags to using rs6000_isa_flags, the options
machinery creates OPTION_MASK_<xxx> instead of MASK_<xxx>. For now map
OPTION_MASK_<xxx> back into MASK_<xxx>. */
@@ -2609,3 +2614,22 @@ while (0)
rs6000_asm_output_opcode (STREAM); \
} \
while (0)
+
+/* Provide macros for sign-extending values. */
+#if HOST_BITS_PER_CHAR == 8
+#define SIGN_EXTEND_8BIT(X) ((HOST_WIDE_INT)(signed char)(X))
+#else
+#define SIGN_EXTEND_8BIT(X) ((((X) & 0xff) ^ 0x80) - 0x80)
+#endif
+
+#if HOST_BITS_PER_SHORT == 16
+#define SIGN_EXTEND_16BIT(X) ((HOST_WIDE_INT)(short)(X))
+#else
+#define SIGN_EXTEND_16BIT(X) ((((X) & 0xffff) ^ 0x8000) - 0x8000)
+#endif
+
+#if HOST_BITS_PER_INT == 32
+#define SIGN_EXTEND_32BIT(X) ((HOST_WIDE_INT)(int)(X))
+#else
+#define SIGN_EXTEND_32BIT(X) ((((X) & 0xffffffff) ^ 0x80000000) - 0x80000000)
+#endif
diff --git a/gcc/config/rs6000/rs6000.opt b/gcc/config/rs6000/rs6000.opt
index 0538db387dc..9548334d846 100644
--- a/gcc/config/rs6000/rs6000.opt
+++ b/gcc/config/rs6000/rs6000.opt
@@ -639,3 +639,7 @@ Enable instructions that guard against return-oriented programming attacks.
mprivileged
Target Var(rs6000_privileged) Init(0)
Generate code that will run in privileged state.
+
+mxxspltiw
+Target Undocumented Var(TARGET_XXSPLTIW_DEBUG) Init(1) Save
+Generate (do not generate) XXSPLTIW instructions.
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index e4ca6e94d49..a2a1571484e 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -373,7 +373,6 @@
UNSPEC_VDIVES
UNSPEC_VDIVEU
UNSPEC_XXEVAL
- UNSPEC_XXSPLTIW
UNSPEC_XXSPLTID
UNSPEC_XXSPLTI32DX
UNSPEC_XXBLEND
@@ -6407,36 +6406,6 @@
[(set_attr "type" "veccomplex")])
\f
-;; XXSPLTIW built-in function support
-(define_insn "xxspltiw_v4si"
- [(set (match_operand:V4SI 0 "register_operand" "=wa")
- (unspec:V4SI [(match_operand:SI 1 "s32bit_cint_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
- "xxspltiw %x0,%1"
- [(set_attr "type" "vecsimple")
- (set_attr "prefixed" "yes")])
-
-(define_expand "xxspltiw_v4sf"
- [(set (match_operand:V4SF 0 "register_operand" "=wa")
- (unspec:V4SF [(match_operand:SF 1 "const_double_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
-{
- long value = rs6000_const_f32_to_i32 (operands[1]);
- emit_insn (gen_xxspltiw_v4sf_inst (operands[0], GEN_INT (value)));
- DONE;
-})
-
-(define_insn "xxspltiw_v4sf_inst"
- [(set (match_operand:V4SF 0 "register_operand" "=wa")
- (unspec:V4SF [(match_operand:SI 1 "c32bit_cint_operand" "n")]
- UNSPEC_XXSPLTIW))]
- "TARGET_POWER10"
- "xxspltiw %x0,%1"
- [(set_attr "type" "vecsimple")
- (set_attr "prefixed" "yes")])
-
;; XXSPLTIDP built-in function support
(define_expand "xxspltidp_v2df"
[(set (match_operand:V2DF 0 "register_operand" )
@@ -6589,3 +6558,118 @@
[(set_attr "type" "vecsimple")
(set_attr "prefixed" "yes")])
+;; XXSPLTIW built-in function support. Convert to a vector constant, which
+;; will then be optimized to the XXSPLTIW instruction.
+(define_expand "xxspltiw_v4si"
+ [(use (match_operand:V4SI 0 "register_operand"))
+ (use (match_operand:SI 1 "s32bit_cint_operand"))]
+ "TARGET_POWER10"
+{
+ rtx op1 = operands[1];
+ rtvec rv = gen_rtvec (4, op1, op1, op1, op1);
+ rtx vec_constant = gen_rtx_CONST_VECTOR (V4SImode, rv);
+ emit_move_insn (operands[0], vec_constant);
+})
+
+(define_expand "xxspltiw_v4sf"
+ [(use (match_operand:V4SF 0 "register_operand"))
+ (use (match_operand:SF 1 "const_double_operand"))]
+ "TARGET_POWER10"
+{
+ rtx op1 = operands[1];
+ rtvec rv = gen_rtvec (4, op1, op1, op1, op1);
+ rtx vec_constant = gen_rtx_CONST_VECTOR (V4SFmode, rv);
+ emit_move_insn (operands[0], vec_constant);
+})
+
+;; XXSPLTIW support. Add support for the XXSPLTIW built-in functions, and to
+;; use XXSPLTIW to load up vector V8HImode, V4SImode, and V4SFmode vector
+;; constants where all elements are the the same. We special case loading up
+;; integer -16..15 and floating point 0.0f, since we can use the shorter
+;; XXSPLTIB, VSPLTISH, and VSPLTISW instructions.
+
+(define_insn "*xxspltiw_v8hi_dup"
+ [(set (match_operand:V8HI 0 "vsx_register_operand" "=wa,wa,v,wa")
+ (vec_duplicate:V8HI
+ (match_operand 1 "const_int_operand" "O,wM,wB,n")))]
+ "TARGET_XXSPLTIW"
+{
+ HOST_WIDE_INT sign_value = SIGN_EXTEND_16BIT (INTVAL (operands[1]));
+
+ if (sign_value == 0)
+ return "xxspltib %x0,0";
+
+ if (sign_value == -1)
+ return "xxspltib %x0,255";
+
+ int r = reg_or_subregno (operands[0]);
+ if (ALTIVEC_REGNO_P (r) && EASY_VECTOR_15 (sign_value))
+ {
+ operands[2] = GEN_INT (sign_value);
+ return "vspltish %0,%1";
+ }
+
+ HOST_WIDE_INT uns_value = sign_value & 0xffff;
+ operands[2] = GEN_INT ((uns_value << 16) | uns_value);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecperm")
+ (set_attr "prefixed" "*,*,*,yes")])
+
+(define_insn "*xxspltiw_v4si_dup"
+ [(set (match_operand:V4SI 0 "vsx_register_operand" "=wa,wa,v,wa")
+ (vec_duplicate:V4SI
+ (match_operand 1 "const_int_operand" "O,wM,wB,n")))]
+ "TARGET_XXSPLTIW"
+{
+ HOST_WIDE_INT sign_value = SIGN_EXTEND_32BIT (INTVAL (operands[1]));
+
+ if (sign_value == 0)
+ return "xxspltib %x0,0";
+
+ if (sign_value == -1)
+ return "xxspltib %x0,255";
+
+ int r = reg_or_subregno (operands[0]);
+ if (ALTIVEC_REGNO_P (r) && EASY_VECTOR_15 (sign_value))
+ {
+ operands[2] = GEN_INT (sign_value);
+ return "vspltisw %0,%2";
+ }
+
+ /* The assembler doesn't like negative values. */
+ operands[2] = GEN_INT (sign_value & 0xffffffff);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecperm")
+ (set_attr "prefixed" "*,*,*,yes")])
+
+(define_insn "xxspltiw_v4sf_dup"
+ [(set (match_operand:V4SF 0 "vsx_register_operand" "=wa,wa")
+ (vec_duplicate:V4SF
+ (match_operand:SF 1 "const_double_operand" "O,F")))]
+ "TARGET_XXSPLTIW"
+{
+ if (operands[1] == CONST0_RTX (SFmode))
+ return "xxspltib %x0,0";
+
+ /* The assembler doesn't like negative values. */
+ long value = rs6000_const_f32_to_i32 (operands[1]);
+ operands[2] = GEN_INT (value & 0xffffffff);
+ return "xxspltiw %x0,%2";
+}
+ [(set_attr "type" "vecsimple")
+ (set_attr "prefixed" "*,yes")])
+
+;; Convert vector constant to vec_duplicate.
+(define_mode_iterator XXSPLTIW [V8HI V4SI V4SF])
+
+(define_split
+ [(set (match_operand:XXSPLTIW 0 "vsx_register_operand")
+ (match_operand:XXSPLTIW 1 "xxspltiw_operand"))]
+ "TARGET_XXSPLTIW"
+ [(set (match_dup 0)
+ (vec_duplicate:<MODE> (match_dup 2)))]
+{
+ operands[2] = CONST_VECTOR_ELT (operands[1], 0);
+})
diff --git a/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c b/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
index f312550f04d..22e43d21565 100644
--- a/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
+++ b/gcc/testsuite/gcc.target/powerpc/pr86731-fwrapv.c
@@ -57,7 +57,12 @@ vector signed int splats3(void)
If folding is enabled, the vec_sl tests using vector long long type will
generate a lvx instead of a vspltisw+vsld pair. */
-/* { dg-final { scan-assembler-times {\mvspltis[bhw]\M|\mxxspltib\M} 7 } } */
-/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 7 } } */
+/* { dg-final { scan-assembler-times {\mvspltis[bhw]\M|\mxxspltib\M} 7 { target { ! has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 7 { target { ! has_arch_pwr10 } } } } */
+
+/* { dg-final { scan-assembler-times {\mxxspltib\M} 2 { target { has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 5 { target { has_arch_pwr10 } } } } */
+/* { dg-final { scan-assembler-times {\mvsl[bhwd]\M} 2 { target { has_arch_pwr10 } } } } */
+
/* { dg-final { scan-assembler-times {\mlvx\M|\mlxvd2x\M} 0 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c
new file mode 100644
index 00000000000..06830b02076
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4sf.c
@@ -0,0 +1,66 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V4SF vector constants. */
+
+vector float
+v4sf_const_1 (void)
+{
+ return (vector float) { 1.0f, 1.0f, 1.0f, 1.0f }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_nan (void)
+{
+ return (vector float) { __builtin_nanf (""),
+ __builtin_nanf (""),
+ __builtin_nanf (""),
+ __builtin_nanf ("") }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_inf (void)
+{
+ return (vector float) { __builtin_inff (),
+ __builtin_inff (),
+ __builtin_inff (),
+ __builtin_inff () }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_const_m0 (void)
+{
+ return (vector float) { -0.0f, -0.0f, -0.0f, -0.0f }; /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_1 (void)
+{
+ return vec_splats (1.0f); /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_nan (void)
+{
+ return vec_splats (__builtin_nanf ("")); /* XXSPLTIW. */
+}
+
+vector float
+v4sf_splats_inf (void)
+{
+ return vec_splats (__builtin_inff ()); /* XXSPLTIW. */
+}
+
+vector float
+v8hi_splats_m0 (void)
+{
+ return vec_splats (-0.0f); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 8 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c
new file mode 100644
index 00000000000..02d0c6d66a2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v4si.c
@@ -0,0 +1,51 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V4SI vector constants. We make sure
+ the power9 support (XXSPLTIB/VEXTSB2W) is not done. */
+
+vector int
+v4si_const_1 (void)
+{
+ return (vector int) { 1, 1, 1, 1 }; /* VSLTPISW. */
+}
+
+vector int
+v4si_const_126 (void)
+{
+ return (vector int) { 126, 126, 126, 126 }; /* XXSPLTIW. */
+}
+
+vector int
+v4si_const_1023 (void)
+{
+ return (vector int) { 1023, 1023, 1023, 1023 }; /* XXSPLTIW. */
+}
+
+vector int
+v4si_splats_1 (void)
+{
+ return vec_splats (1); /* VSLTPISW. */
+}
+
+vector int
+v4si_splats_126 (void)
+{
+ return vec_splats (126); /* XXSPLTIW. */
+}
+
+vector int
+v8hi_splats_1023 (void)
+{
+ return vec_splats (1023); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mvspltisw\M} 2 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mvextsb2w\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c
new file mode 100644
index 00000000000..e6d0fab6d67
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splat-constant-v8hi.c
@@ -0,0 +1,53 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+/* Test whether XXSPLTIW is generated for V8HI vector constants. We make sure
+ the power9 support (XXSPLTIB/VUPKLSB) is not done. */
+
+vector short
+v8hi_const_1 (void)
+{
+ return (vector short) { 1, 1, 1, 1, 1, 1, 1, 1 }; /* VSLTPISH. */
+}
+
+vector short
+v8hi_const_126 (void)
+{
+ return (vector short) { 126, 126, 126, 126,
+ 126, 126, 126, 126 }; /* XXSPLTIW. */
+}
+
+vector short
+v8hi_const_1023 (void)
+{
+ return (vector short) { 1023, 1023, 1023, 1023,
+ 1023, 1023, 1023, 1023 }; /* XXSPLTIW. */
+}
+
+vector short
+v8hi_splats_1 (void)
+{
+ return vec_splats ((short)1); /* VSLTPISH. */
+}
+
+vector short
+v8hi_splats_126 (void)
+{
+ return vec_splats ((short)126); /* XXSPLTIW. */
+}
+
+vector short
+v8hi_splats_1023 (void)
+{
+ return vec_splats ((short)1023); /* XXSPLTIW. */
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mvspltish\M} 2 } } */
+/* { dg-final { scan-assembler-not {\mxxspltib\M} } } */
+/* { dg-final { scan-assembler-not {\mvupklsb\M} } } */
+/* { dg-final { scan-assembler-not {\mlxvx?\M} } } */
+/* { dg-final { scan-assembler-not {\mplxv\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c b/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
index a135279b1d7..f49ef91422e 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
@@ -149,8 +149,6 @@ main (int argc, char *argv [])
return 0;
}
-/* { dg-final { scan-assembler-times {\mxxspltiw\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 1 } } */
/* { dg-final { scan-assembler-times {\mxxspltidp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxxsplti32dx\M} 3 } } */
-
-
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2021-08-13 2:00 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-08-13 1:31 [gcc(refs/users/meissner/heads/work064)] PATCH Generate XXSPLTIW on power10 Michael Meissner
2021-08-13 2:00 Michael Meissner
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).