Hi!
This patch improves code generation e.g. on the first attached testcase
and allows accepting the second one.
I've noticed we don't allow TFmode or V1TImode in xmm16+ regs at all,
while they are allowed in xmm0-xmm15, so IMHO should be ok even with
AVX512VL.
Wonder if it wouldn't be better to add a new constraint that would act
like v constraint for TARGET_AVX512VL and like x constraint otherwise,
that might greatly simplify the i386.md changes in this patch.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk,
or with some changes? Haven't figured out how to test the *andnot*
and *<logic>* patterns though.
2016-05-03 Jakub Jelinek <ja...@redhat.com>
* config/i386/i386.h (VALID_AVX512VL_128_REG_MODE): Allow
TFmode and V1TImode in xmm16+ registers for TARGET_AVX512VL.
* config/i386/i386.md (avx512fvecmode): New mode attr.
(*pushtf): Use v constraint instead of x.
(*movtf_internal): Likewise. For TARGET_AVX512VL and
xmm16+ registers, use vmovdqu64 or vmovdqa64 instructions.
(*absneg<mode>2): Add avx512vl alternatives.
(*absnegtf2_sse): Likewise.
(copysign<mode>3_const, copysign<mode>3_var): Likewise.
* config/i386/sse.md (*andnot<mode>3): Add avx512vl and
avx512f alternatives.
(*andnottf3, *<code><mode>3, *<code>tf3): Likewise.
--- gcc/config/i386/i386.h.jj 2016-03-30 16:00:17.000000000 +0200
+++ gcc/config/i386/i386.h 2016-05-03 15:55:46.656342870 +0200
@@ -1126,7 +1126,8 @@ extern const char *host_detect_local_cpu
#define VALID_AVX512VL_128_REG_MODE(MODE) \
((MODE) == V2DImode || (MODE) == V2DFmode || (MODE) == V16QImode \
- || (MODE) == V4SImode || (MODE) == V4SFmode || (MODE) == V8HImode)
+ || (MODE) == V4SImode || (MODE) == V4SFmode || (MODE) == V8HImode \
+ || (MODE) == TFmode || (MODE) == V1TImode)
#define VALID_SSE2_REG_MODE(MODE) \
((MODE) == V16QImode || (MODE) == V8HImode || (MODE) == V2DFmode \
--- gcc/config/i386/i386.md.jj 2016-05-03 14:16:14.000000000 +0200
+++ gcc/config/i386/i386.md 2016-05-03 17:13:46.643545826 +0200
@@ -1165,6 +1165,10 @@ (define_mode_attr ssevecmode
(define_mode_attr ssevecmodelower
[(QI "v16qi") (HI "v8hi") (SI "v4si") (DI "v2di") (SF "v4sf") (DF "v2df")])
+;; AVX512F vector mode corresponding to a scalar mode
+(define_mode_attr avx512fvecmode
+ [(QI "V64QI") (HI "V32HI") (SI "V16SI") (DI "V8DI") (SF "V16SF") (DF
"V8DF")])
+
;; Instruction suffix for REX 64bit operators.
(define_mode_attr rex64suffix [(SI "") (DI "{q}")])
@@ -2928,7 +2932,7 @@ (define_insn "*insvqi"
(define_insn "*pushtf"
[(set (match_operand:TF 0 "push_operand" "=<,<")
- (match_operand:TF 1 "general_no_elim_operand" "x,*roF"))]
+ (match_operand:TF 1 "general_no_elim_operand" "v,*roF"))]
"TARGET_64BIT || TARGET_SSE"
{
/* This insn should be already split before reg-stack. */
@@ -3107,8 +3111,8 @@ (define_expand "mov<mode>"
"ix86_expand_move (<MODE>mode, operands); DONE;")
(define_insn "*movtf_internal"
- [(set (match_operand:TF 0 "nonimmediate_operand" "=x,x ,m,?*r ,!o")
- (match_operand:TF 1 "general_operand" "C ,xm,x,*roF,*rC"))]
+ [(set (match_operand:TF 0 "nonimmediate_operand" "=v,v ,m,?*r ,!o")
+ (match_operand:TF 1 "general_operand" "C ,vm,v,*roF,*rC"))]
"(TARGET_64BIT || TARGET_SSE)
&& !(MEM_P (operands[0]) && MEM_P (operands[1]))
&& (!can_create_pseudo_p ()
@@ -3133,6 +3137,10 @@ (define_insn "*movtf_internal"
{
if (get_attr_mode (insn) == MODE_V4SF)
return "%vmovups\t{%1, %0|%0, %1}";
+ else if (TARGET_AVX512VL
+ && (EXT_REX_SSE_REG_P (operands[0])
+ || EXT_REX_SSE_REG_P (operands[1])))
+ return "vmovdqu64\t{%1, %0|%0, %1}";
else
return "%vmovdqu\t{%1, %0|%0, %1}";
}
@@ -3140,6 +3148,10 @@ (define_insn "*movtf_internal"
{
if (get_attr_mode (insn) == MODE_V4SF)
return "%vmovaps\t{%1, %0|%0, %1}";
+ else if (TARGET_AVX512VL
+ && (EXT_REX_SSE_REG_P (operands[0])
+ || EXT_REX_SSE_REG_P (operands[1])))
+ return "vmovdqa64\t{%1, %0|%0, %1}";
else
return "%vmovdqa\t{%1, %0|%0, %1}";
}
@@ -9253,10 +9265,10 @@ (define_expand "<code><mode>2"
"ix86_expand_fp_absneg_operator (<CODE>, <MODE>mode, operands); DONE;")
(define_insn "*absneg<mode>2"
- [(set (match_operand:MODEF 0 "register_operand" "=x,x,f,!r")
+ [(set (match_operand:MODEF 0 "register_operand" "=x,x,v,v,f,!r")
(match_operator:MODEF 3 "absneg_operator"
- [(match_operand:MODEF 1 "register_operand" "0,x,0,0")]))
- (use (match_operand:<ssevecmode> 2 "nonimmediate_operand" "xm,0,X,X"))
+ [(match_operand:MODEF 1 "register_operand" "0,x,0,v,0,0")]))
+ (use (match_operand:<ssevecmode> 2 "nonimmediate_operand" "xm,0,vm,0,X,X"))
(clobber (reg:CC FLAGS_REG))]
"(SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH)
|| TARGET_80387"
@@ -9265,11 +9277,14 @@ (define_insn "*absneg<mode>2"
(if_then_else
(match_test ("SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH"))
(if_then_else
- (eq_attr "alternative" "2")
+ (eq_attr "alternative" "4")
(symbol_ref "TARGET_MIX_SSE_I387")
- (symbol_ref "true"))
+ (if_then_else
+ (eq_attr "alternative" "2,3")
+ (symbol_ref "TARGET_AVX512VL != 0")
+ (symbol_ref "true")))
(if_then_else
- (eq_attr "alternative" "2,3")
+ (eq_attr "alternative" "4,5")
(symbol_ref "true")
(symbol_ref "false"))))])
@@ -9289,13 +9304,14 @@ (define_expand "<code>tf2"
"ix86_expand_fp_absneg_operator (<CODE>, TFmode, operands); DONE;")
(define_insn "*absnegtf2_sse"
- [(set (match_operand:TF 0 "register_operand" "=x,x")
+ [(set (match_operand:TF 0 "register_operand" "=x,x,v,v")
(match_operator:TF 3 "absneg_operator"
- [(match_operand:TF 1 "register_operand" "0,x")]))
- (use (match_operand:TF 2 "nonimmediate_operand" "xm,0"))
+ [(match_operand:TF 1 "register_operand" "0,x,0,v")]))
+ (use (match_operand:TF 2 "nonimmediate_operand" "xm,0,vm,0"))
(clobber (reg:CC FLAGS_REG))]
"TARGET_SSE"
- "#")
+ "#"
+ [(set_attr "isa" "*,*,avx512vl,avx512vl")])
;; Splitters for fp abs and neg.
@@ -9473,31 +9489,35 @@ (define_expand "copysign<mode>3"
"ix86_expand_copysign (operands); DONE;")
(define_insn_and_split "copysign<mode>3_const"
- [(set (match_operand:CSGNMODE 0 "register_operand" "=x")
+ [(set (match_operand:CSGNMODE 0 "register_operand" "=x,v")
(unspec:CSGNMODE
- [(match_operand:<CSGNVMODE> 1 "vector_move_operand" "xmC")
- (match_operand:CSGNMODE 2 "register_operand" "0")
- (match_operand:<CSGNVMODE> 3 "nonimmediate_operand" "xm")]
+ [(match_operand:<CSGNVMODE> 1 "vector_move_operand" "xmC,vmC")
+ (match_operand:CSGNMODE 2 "register_operand" "0,0")
+ (match_operand:<CSGNVMODE> 3 "nonimmediate_operand" "xm,vm")]
UNSPEC_COPYSIGN))]
"(SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH)
|| (TARGET_SSE && (<MODE>mode == TFmode))"
"#"
"&& reload_completed"
[(const_int 0)]
- "ix86_split_copysign_const (operands); DONE;")
+ "ix86_split_copysign_const (operands); DONE;"
+ [(set_attr "isa" "*,avx512vl")])
(define_insn "copysign<mode>3_var"
- [(set (match_operand:CSGNMODE 0 "register_operand" "=x,x,x,x,x")
+ [(set (match_operand:CSGNMODE 0 "register_operand" "=x,x,x,x,x,v,v,v,v,v")
(unspec:CSGNMODE
- [(match_operand:CSGNMODE 2 "register_operand" "x,0,0,x,x")
- (match_operand:CSGNMODE 3 "register_operand" "1,1,x,1,x")
- (match_operand:<CSGNVMODE> 4 "nonimmediate_operand" "X,xm,xm,0,0")
- (match_operand:<CSGNVMODE> 5 "nonimmediate_operand" "0,xm,1,xm,1")]
+ [(match_operand:CSGNMODE 2 "register_operand" "x,0,0,x,x,v,0,0,v,v")
+ (match_operand:CSGNMODE 3 "register_operand" "1,1,x,1,x,1,1,v,1,v")
+ (match_operand:<CSGNVMODE> 4
+ "nonimmediate_operand" "X,xm,xm,0,0,X,vm,vm,0,0")
+ (match_operand:<CSGNVMODE> 5
+ "nonimmediate_operand" "0,xm,1,xm,1,0,vm,1,vm,1")]
UNSPEC_COPYSIGN))
- (clobber (match_scratch:<CSGNVMODE> 1 "=x,x,x,x,x"))]
+ (clobber (match_scratch:<CSGNVMODE> 1 "=x,x,x,x,x,v,v,v,v,v"))]
"(SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH)
|| (TARGET_SSE && (<MODE>mode == TFmode))"
- "#")
+ "#"
+ [(set_attr "isa" "*,*,*,*,*,avx512vl,avx512vl,avx512vl,avx512vl,avx512vl")])
(define_split
[(set (match_operand:CSGNMODE 0 "register_operand")
--- gcc/config/i386/sse.md.jj 2016-05-03 13:34:09.946986488 +0200
+++ gcc/config/i386/sse.md 2016-05-03 17:38:02.486935094 +0200
@@ -3000,11 +3013,11 @@ (define_expand "copysign<mode>3"
;; because the native instructions read the full 128-bits.
(define_insn "*andnot<mode>3"
- [(set (match_operand:MODEF 0 "register_operand" "=x,x")
+ [(set (match_operand:MODEF 0 "register_operand" "=x,x,v,v")
(and:MODEF
(not:MODEF
- (match_operand:MODEF 1 "register_operand" "0,x"))
- (match_operand:MODEF 2 "register_operand" "x,x")))]
+ (match_operand:MODEF 1 "register_operand" "0,x,v,v"))
+ (match_operand:MODEF 2 "register_operand" "x,x,v,v")))]
"SSE_FLOAT_MODE_P (<MODE>mode)"
{
static char buf[32];
@@ -3020,6 +3033,24 @@ (define_insn "*andnot<mode>3"
case 1:
ops = "vandn%s\t{%%2, %%1, %%0|%%0, %%1, %%2}";
break;
+ case 2:
+ if (TARGET_AVX512DQ)
+ ops = "vandn%s\t{%%2, %%1, %%0|%%0, %%1, %%2}";
+ else
+ {
+ suffix = <MODE>mode == DFmode ? "q" : "d";
+ ops = "vpandn%s\t{%%2, %%1, %%0|%%0, %%1, %%2}";
+ }
+ break;
+ case 3:
+ if (TARGET_AVX512DQ)
+ ops = "vandn%s\t{%%g2, %%g1, %%g0|%%g0, %%g1, %%g2}";
+ else
+ {
+ suffix = <MODE>mode == DFmode ? "q" : "d";
+ ops = "vpandn%s\t{%%g2, %%g1, %%g0|%%g0, %%g1, %%g2}";
+ }
+ break;
default:
gcc_unreachable ();
}
@@ -3027,11 +3058,19 @@ (define_insn "*andnot<mode>3"
snprintf (buf, sizeof (buf), ops, suffix);
return buf;
}
- [(set_attr "isa" "noavx,avx")
+ [(set_attr "isa" "noavx,avx,avx512vl,avx512f")
(set_attr "type" "sselog")
- (set_attr "prefix" "orig,vex")
+ (set_attr "prefix" "orig,vex,evex,evex")
(set (attr "mode")
- (cond [(and (match_test "<MODE_SIZE> == 16")
+ (cond [(eq_attr "alternative" "2")
+ (if_then_else (match_test "TARGET_AVX512DQ")
+ (const_string "<ssevecmode>")
+ (const_string "TI"))
+ (eq_attr "alternative" "3")
+ (if_then_else (match_test "TARGET_AVX512DQ")
+ (const_string "<avx512fvecmode>")
+ (const_string "XI"))
+ (and (match_test "<MODE_SIZE> == 16")
(match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL"))
(const_string "V4SF")
(match_test "TARGET_AVX")
@@ -3042,16 +3081,17 @@ (define_insn "*andnot<mode>3"
(const_string "<ssevecmode>")))])
(define_insn "*andnottf3"
- [(set (match_operand:TF 0 "register_operand" "=x,x")
+ [(set (match_operand:TF 0 "register_operand" "=x,x,v,v")
(and:TF
- (not:TF (match_operand:TF 1 "register_operand" "0,x"))
- (match_operand:TF 2 "vector_operand" "xBm,xm")))]
+ (not:TF (match_operand:TF 1 "register_operand" "0,x,v,v"))
+ (match_operand:TF 2 "vector_operand" "xBm,xm,vm,v")))]
"TARGET_SSE"
{
static char buf[32];
const char *ops;
const char *tmp
- = (get_attr_mode (insn) == MODE_V4SF) ? "andnps" : "pandn";
+ = (which_alternative >= 2 ? "pandnq"
+ : get_attr_mode (insn) == MODE_V4SF ? "andnps" : "pandn");
switch (which_alternative)
{
@@ -3059,8 +3099,12 @@ (define_insn "*andnottf3"
ops = "%s\t{%%2, %%0|%%0, %%2}";
break;
case 1:
+ case 2:
ops = "v%s\t{%%2, %%1, %%0|%%0, %%1, %%2}";
break;
+ case 3:
+ ops = "v%s\t{%%g2, %%g1, %%g0|%%g0, %%g1, %%g2}";
+ break;
default:
gcc_unreachable ();
}
@@ -3068,7 +3112,7 @@ (define_insn "*andnottf3"
snprintf (buf, sizeof (buf), ops, tmp);
return buf;
}
- [(set_attr "isa" "noavx,avx")
+ [(set_attr "isa" "noavx,avx,avx512vl,avx512f")
(set_attr "type" "sselog")
(set (attr "prefix_data16")
(if_then_else
@@ -3076,9 +3120,13 @@ (define_insn "*andnottf3"
(eq_attr "mode" "TI"))
(const_string "1")
(const_string "*")))
- (set_attr "prefix" "orig,vex")
+ (set_attr "prefix" "orig,vex,evex,evex")
(set (attr "mode")
- (cond [(match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")
+ (cond [(eq_attr "alternative" "2")
+ (const_string "TI")
+ (eq_attr "alternative" "3")
+ (const_string "XI")
+ (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")
(const_string "V4SF")
(match_test "TARGET_AVX")
(const_string "TI")
@@ -3089,10 +3137,10 @@ (define_insn "*andnottf3"
(const_string "TI")))])
(define_insn "*<code><mode>3"
- [(set (match_operand:MODEF 0 "register_operand" "=x,x")
+ [(set (match_operand:MODEF 0 "register_operand" "=x,x,v,v")
(any_logic:MODEF
- (match_operand:MODEF 1 "register_operand" "%0,x")
- (match_operand:MODEF 2 "register_operand" "x,x")))]
+ (match_operand:MODEF 1 "register_operand" "%0,x,v,v")
+ (match_operand:MODEF 2 "register_operand" "x,x,v,v")))]
"SSE_FLOAT_MODE_P (<MODE>mode)"
{
static char buf[32];
@@ -3105,9 +3153,26 @@ (define_insn "*<code><mode>3"
case 0:
ops = "<logic>%s\t{%%2, %%0|%%0, %%2}";
break;
+ case 2:
+ if (!TARGET_AVX512DQ)
+ {
+ suffix = <MODE>mode == DFmode ? "q" : "d";
+ ops = "vp<logic>%s\t{%%2, %%1, %%0|%%0, %%1, %%2}";
+ break;
+ }
+ /* FALLTHRU */
case 1:
ops = "v<logic>%s\t{%%2, %%1, %%0|%%0, %%1, %%2}";
break;
+ case 3:
+ if (TARGET_AVX512DQ)
+ ops = "v<logic>%s\t{%%g2, %%g1, %%g0|%%g0, %%g1, %%g2}";
+ else
+ {
+ suffix = <MODE>mode == DFmode ? "q" : "d";
+ ops = "vp<logic>%s\t{%%g2, %%g1, %%g0|%%g0, %%g1, %%g2}";
+ }
+ break;
default:
gcc_unreachable ();
}
@@ -3115,11 +3180,19 @@ (define_insn "*<code><mode>3"
snprintf (buf, sizeof (buf), ops, suffix);
return buf;
}
- [(set_attr "isa" "noavx,avx")
+ [(set_attr "isa" "noavx,avx,avx512vl,avx512f")
(set_attr "type" "sselog")
- (set_attr "prefix" "orig,vex")
+ (set_attr "prefix" "orig,vex,evex,evex")
(set (attr "mode")
- (cond [(and (match_test "<MODE_SIZE> == 16")
+ (cond [(eq_attr "alternative" "2")
+ (if_then_else (match_test "TARGET_AVX512DQ")
+ (const_string "<ssevecmode>")
+ (const_string "TI"))
+ (eq_attr "alternative" "3")
+ (if_then_else (match_test "TARGET_AVX512DQ")
+ (const_string "<avx512fvecmode>")
+ (const_string "XI"))
+ (and (match_test "<MODE_SIZE> == 16")
(match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL"))
(const_string "V4SF")
(match_test "TARGET_AVX")
@@ -3138,17 +3211,18 @@ (define_expand "<code>tf3"
"ix86_fixup_binary_operands_no_copy (<CODE>, TFmode, operands);")
(define_insn "*<code>tf3"
- [(set (match_operand:TF 0 "register_operand" "=x,x")
+ [(set (match_operand:TF 0 "register_operand" "=x,x,v,v")
(any_logic:TF
- (match_operand:TF 1 "vector_operand" "%0,x")
- (match_operand:TF 2 "vector_operand" "xBm,xm")))]
+ (match_operand:TF 1 "vector_operand" "%0,x,v,v")
+ (match_operand:TF 2 "vector_operand" "xBm,xm,vm,v")))]
"TARGET_SSE
&& ix86_binary_operator_ok (<CODE>, TFmode, operands)"
{
static char buf[32];
const char *ops;
const char *tmp
- = (get_attr_mode (insn) == MODE_V4SF) ? "<logic>ps" : "p<logic>";
+ = (which_alternative >= 2 ? "p<logic>q"
+ : get_attr_mode (insn) == MODE_V4SF ? "<logic>ps" : "p<logic>");
switch (which_alternative)
{
@@ -3156,8 +3230,12 @@ (define_insn "*<code>tf3"
ops = "%s\t{%%2, %%0|%%0, %%2}";
break;
case 1:
+ case 2:
ops = "v%s\t{%%2, %%1, %%0|%%0, %%1, %%2}";
break;
+ case 3:
+ ops = "v%s\t{%%g2, %%g1, %%g0|%%g0, %%g1, %%g2}";
+ break;
default:
gcc_unreachable ();
}
@@ -3165,7 +3243,7 @@ (define_insn "*<code>tf3"
snprintf (buf, sizeof (buf), ops, tmp);
return buf;
}
- [(set_attr "isa" "noavx,avx")
+ [(set_attr "isa" "noavx,avx,avx512vl,avx512f")
(set_attr "type" "sselog")
(set (attr "prefix_data16")
(if_then_else
@@ -3173,9 +3251,13 @@ (define_insn "*<code>tf3"
(eq_attr "mode" "TI"))
(const_string "1")
(const_string "*")))
- (set_attr "prefix" "orig,vex")
+ (set_attr "prefix" "orig,vex,evex,evex")
(set (attr "mode")
- (cond [(match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")
+ (cond [(eq_attr "alternative" "2")
+ (const_string "TI")
+ (eq_attr "alternative" "3")
+ (const_string "QI")
+ (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")
(const_string "V4SF")
(match_test "TARGET_AVX")
(const_string "TI")
Jakub
void
f1 (float x)
{
register float a __asm ("xmm16");
a = x;
asm volatile ("" : "+v" (a));
a = __builtin_fabsf (a);
asm volatile ("" : "+v" (a));
}
void
f2 (float x, float y)
{
register float a __asm ("xmm16"), b __asm ("xmm17");
a = x;
b = y;
asm volatile ("" : "+v" (a), "+v" (b));
a = __builtin_copysignf (a, b);
asm volatile ("" : "+v" (a));
}
void
f3 (float x)
{
register float a __asm ("xmm16");
a = x;
asm volatile ("" : "+v" (a));
a = -a;
asm volatile ("" : "+v" (a));
}
void
f4 (double x)
{
register double a __asm ("xmm16");
a = x;
asm volatile ("" : "+v" (a));
a = __builtin_fabs (a);
asm volatile ("" : "+v" (a));
}
void
f5 (double x, double y)
{
register double a __asm ("xmm16"), b __asm ("xmm17");
a = x;
b = y;
asm volatile ("" : "+v" (a), "+v" (b));
a = __builtin_copysign (a, b);
asm volatile ("" : "+v" (a));
}
void
f6 (double x)
{
register double a __asm ("xmm16");
a = x;
asm volatile ("" : "+v" (a));
a = -a;
asm volatile ("" : "+v" (a));
}
void
f1 (__float128 x)
{
register __float128 a __asm ("xmm16");
a = x;
asm volatile ("" : "+v" (a));
a = __builtin_fabsq (a);
asm volatile ("" : "+v" (a));
}
void
f2 (__float128 x, __float128 y)
{
register __float128 a __asm ("xmm16"), b __asm ("xmm17");
a = x;
b = y;
asm volatile ("" : "+v" (a), "+v" (b));
a = __builtin_copysignq (a, b);
asm volatile ("" : "+v" (a));
}
void
f3 (__float128 x)
{
register __float128 a __asm ("xmm16");
a = x;
asm volatile ("" : "+v" (a));
a = -a;
asm volatile ("" : "+v" (a));
}
__int128_t
f4 (void)
{
register __int128_t a __asm ("xmm16");
register __int128_t __attribute__((vector_size (16))) b __asm ("xmm17");
a = 1;
asm volatile ("" : "+v" (a));
b[0] = a;
asm volatile ("" : "+v" (b));
return b[0];
}
