Hello,
Patch in the bottom extends plus/minus/abs/andnot patterns
to support AVX-512.
I've used questionable hack in the patterns.
Instead of writing dozen similar patterns with masking
I've simply substed them, prohibiting non-mask variant in
the pattern condition. E.g.:
(define_expand "<mask_codefor><plusminus_insn><mode>3<mask_name>"
[(set (match_operand:VI12_AVX512VL 0 "register_operand")
(plusminus:VI12_AVX512VL
(match_operand:VI12_AVX512VL 1 "nonimmediate_operand")
(match_operand:VI12_AVX512VL 2 "nonimmediate_operand")))]
"TARGET_AVX512BW && <mask_applied>"
"ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
If this is not acceptable, I'll rewrite it to somthing like:
(define_expand "<mask_codefor><plusminus_insn><mode>3<mask_name>"
[(set (match_operand:VI12_AVX512VL 0 "register_operand")
(vec_merge: VI12_AVX512VL
(plusminus:VI12_AVX512VL
(match_operand:VI12_AVX512VL 1 "nonimmediate_operand")
(match_operand:VI12_AVX512VL 2 "nonimmediate_operand"))
(match_operand:SUBST_V 2 "vector_move_operand" "0C")
(match_operand:<avx512fmaskmode> 3 "register_operand" "Yk")))]
"TARGET_AVX512BW && <mask_applied>"
"ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
Testing is in progress. Is it ok for trunk if pass?
Also we might want to rename VI_AVX2, but I didn't do that
since new (generic) name would be too long. Say: VI_AVX2_AVX512BW_AVX512F.
gcc/
* config/i386/sse.md (define_mode_iterator VI_AVX2): Extend
to support AVX-512BW.
(define_mode_iterator VI124_AVX2_48_AVX512F): Remove.
(define_expand "<plusminus_insn><mode>3"): Remove masking support.
(define_insn "*<plusminus_insn><mode>3"): Ditto.
(define_expand
"<mask_codefor><plusminus_insn><VI48_AVX512VL:mode>3<mask_name>"):
New.
(define_expand
"<mask_codefor><plusminus_insn><VI12_AVX512VL:mode>3<mask_name>"):
Ditto.
(define_insn "*<plusminus_insn><VI48_AVX512VL:mode>3<mask_name>"):
Ditto.
(define_insn "*<plusminus_insn><VI12_AVX512VL:mode>3<mask_name>"):
Ditto.
(define_expand "<sse2_avx2>_andnot<mode>3"): Remove masking support.
(define_insn "*andnot<mode>3"): Ditto.
(define_expand
"<mask_codefor><sse2_avx2>_andnot<VI48_AVX512VL:mode>3<mask_name>"): New.
(define_expand
"<mask_codefor><sse2_avx2>_andnot<VI12_AVX512VL:mode>3<mask_name>"): Ditto.
(define_insn "*andnot<VI48_AVX512VL:mode>3<mask_name>"): Ditto.
(define_insn "*andnot<VI12_AVX512VL:mode>3<mask_name>"): Ditto.
(define_insn "*abs<mode>2"): Remove masking support.
(define_insn "<mask_codefor>abs<VI48_AVX512VL:mode>2<mask_name>"): New.
(define_insn "<mask_codefor>abs<VI12_AVX512VL:mode>2<mask_name>"):
Ditto.
(define_expand "abs<mode>2"): Use VI_AVX2 mode iterator.
--
Thanks, K
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index ffc831f..d6861e5 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -268,8 +268,8 @@
(V4DI "TARGET_AVX") V2DI])
(define_mode_iterator VI_AVX2
- [(V32QI "TARGET_AVX2") V16QI
- (V16HI "TARGET_AVX2") V8HI
+ [(V64QI "TARGET_AVX512BW") (V32QI "TARGET_AVX2") V16QI
+ (V32HI "TARGET_AVX512BW") (V16HI "TARGET_AVX2") V8HI
(V16SI "TARGET_AVX512F") (V8SI "TARGET_AVX2") V4SI
(V8DI "TARGET_AVX512F") (V4DI "TARGET_AVX2") V2DI])
@@ -359,12 +359,6 @@
[(V16HI "TARGET_AVX2") V8HI
(V8SI "TARGET_AVX2") V4SI])
-(define_mode_iterator VI124_AVX2_48_AVX512F
- [(V32QI "TARGET_AVX2") V16QI
- (V16HI "TARGET_AVX2") V8HI
- (V16SI "TARGET_AVX512F") (V8SI "TARGET_AVX2") V4SI
- (V8DI "TARGET_AVX512F")])
-
(define_mode_iterator VI124_AVX512F
[(V32QI "TARGET_AVX2") V16QI
(V32HI "TARGET_AVX512F") (V16HI "TARGET_AVX2") V8HI
@@ -9051,20 +9045,37 @@
"TARGET_SSE2"
"operands[2] = force_reg (<MODE>mode, CONST0_RTX (<MODE>mode));")
-(define_expand "<plusminus_insn><mode>3<mask_name>"
+(define_expand "<plusminus_insn><mode>3"
[(set (match_operand:VI_AVX2 0 "register_operand")
(plusminus:VI_AVX2
(match_operand:VI_AVX2 1 "nonimmediate_operand")
(match_operand:VI_AVX2 2 "nonimmediate_operand")))]
- "TARGET_SSE2 && <mask_mode512bit_condition>"
+ "TARGET_SSE2"
"ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
-(define_insn "*<plusminus_insn><mode>3<mask_name>"
+(define_expand "<mask_codefor><plusminus_insn><mode>3<mask_name>"
+ [(set (match_operand:VI48_AVX512VL 0 "register_operand")
+ (plusminus:VI48_AVX512VL
+ (match_operand:VI48_AVX512VL 1 "nonimmediate_operand")
+ (match_operand:VI48_AVX512VL 2 "nonimmediate_operand")))]
+ "TARGET_AVX512F && <mask_applied>"
+ "ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
+
+(define_expand "<mask_codefor><plusminus_insn><mode>3<mask_name>"
+ [(set (match_operand:VI12_AVX512VL 0 "register_operand")
+ (plusminus:VI12_AVX512VL
+ (match_operand:VI12_AVX512VL 1 "nonimmediate_operand")
+ (match_operand:VI12_AVX512VL 2 "nonimmediate_operand")))]
+ "TARGET_AVX512BW && <mask_applied>"
+ "ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
+
+(define_insn "*<plusminus_insn><mode>3"
[(set (match_operand:VI_AVX2 0 "register_operand" "=x,v")
(plusminus:VI_AVX2
(match_operand:VI_AVX2 1 "nonimmediate_operand" "<comm>0,v")
(match_operand:VI_AVX2 2 "nonimmediate_operand" "xm,vm")))]
- "TARGET_SSE2 && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands) &&
<mask_mode512bit_condition>"
+ "TARGET_SSE2
+ && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
"@
p<plusminus_mnemonic><ssemodesuffix>\t{%2, %0|%0, %2}
vp<plusminus_mnemonic><ssemodesuffix>\t{%2, %1,
%0<mask_operand3>|%0<mask_operand3>, %1, %2}"
@@ -9074,6 +9085,30 @@
(set_attr "prefix" "<mask_prefix3>")
(set_attr "mode" "<sseinsnmode>")])
+(define_insn "*<plusminus_insn><mode>3<mask_name>"
+ [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v")
+ (plusminus:VI48_AVX512VL
+ (match_operand:VI48_AVX512VL 1 "nonimmediate_operand" "<comm>v")
+ (match_operand:VI48_AVX512VL 2 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F && <mask_applied>
+ && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
+ "vp<plusminus_mnemonic><ssemodesuffix>\t{%2, %1,
%0<mask_operand3>|%0<mask_operand3>, %1, %2}"
+ [(set_attr "type" "sseiadd")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "*<plusminus_insn><mode>3<mask_name>"
+ [(set (match_operand:VI12_AVX512VL 0 "register_operand" "=v")
+ (plusminus:VI12_AVX512VL
+ (match_operand:VI12_AVX512VL 1 "nonimmediate_operand" "<comm>v")
+ (match_operand:VI12_AVX512VL 2 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512BW && <mask_applied>
+ && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
+ "vp<plusminus_mnemonic><ssemodesuffix>\t{%2, %1,
%0<mask_operand3>|%0<mask_operand3>, %1, %2}"
+ [(set_attr "type" "sseiadd")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
(define_expand "<sse2_avx2>_<plusminus_insn><mode>3<mask_name>"
[(set (match_operand:VI12_AVX2 0 "register_operand")
(sat_plusminus:VI12_AVX2
@@ -10489,19 +10524,33 @@
operands[2] = force_reg (<MODE>mode, gen_rtx_CONST_VECTOR (<MODE>mode, v));
})
-(define_expand "<sse2_avx2>_andnot<mode>3<mask_name>"
+(define_expand "<sse2_avx2>_andnot<mode>3"
[(set (match_operand:VI_AVX2 0 "register_operand")
(and:VI_AVX2
(not:VI_AVX2 (match_operand:VI_AVX2 1 "register_operand"))
(match_operand:VI_AVX2 2 "nonimmediate_operand")))]
- "TARGET_SSE2 && <mask_mode512bit_condition>")
+ "TARGET_SSE2")
-(define_insn "*andnot<mode>3<mask_name>"
+(define_expand "<mask_codefor><sse2_avx2>_andnot<mode>3<mask_name>"
+ [(set (match_operand:VI48_AVX512VL 0 "register_operand")
+ (and:VI48_AVX512VL
+ (not:VI48_AVX512VL (match_operand:VI48_AVX512VL 1 "register_operand"))
+ (match_operand:VI48_AVX512VL 2 "nonimmediate_operand")))]
+ "TARGET_AVX512F && <mask_applied>")
+
+(define_expand "<mask_codefor><sse2_avx2>_andnot<mode>3<mask_name>"
+ [(set (match_operand:VI12_AVX512VL 0 "register_operand")
+ (and:VI12_AVX512VL
+ (not:VI12_AVX512VL (match_operand:VI12_AVX512VL 1 "register_operand"))
+ (match_operand:VI12_AVX512VL 2 "nonimmediate_operand")))]
+ "TARGET_AVX512BW && <mask_applied>")
+
+(define_insn "*andnot<mode>3"
[(set (match_operand:VI 0 "register_operand" "=x,v")
(and:VI
(not:VI (match_operand:VI 1 "register_operand" "0,v"))
(match_operand:VI 2 "nonimmediate_operand" "xm,vm")))]
- "TARGET_SSE && <mask_mode512bit_condition>"
+ "TARGET_SSE"
{
static char buf[64];
const char *ops;
@@ -10560,7 +10609,7 @@
(eq_attr "mode" "TI"))
(const_string "1")
(const_string "*")))
- (set_attr "prefix" "<mask_prefix3>")
+ (set_attr "prefix" "orig,vex")
(set (attr "mode")
(cond [(and (match_test "<MODE_SIZE> == 16")
(match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL"))
@@ -10578,6 +10627,30 @@
]
(const_string "<sseinsnmode>")))])
+(define_insn "*andnot<mode>3<mask_name>"
+ [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v")
+ (and:VI48_AVX512VL
+ (not:VI48_AVX512VL
+ (match_operand:VI48_AVX512VL 1 "register_operand" "v"))
+ (match_operand:VI48_AVX512VL 2 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F && <mask_applied>"
+ "vpandn<ssemodesuffix>\t{%%2, %%1, %%0<mask_operand3>|%%0<mask_operand3>,
%%1, %%2}";
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "*andnot<mode>3<mask_name>"
+ [(set (match_operand:VI12_AVX512VL 0 "register_operand" "=v")
+ (and:VI12_AVX512VL
+ (not:VI12_AVX512VL
+ (match_operand:VI12_AVX512VL 1 "register_operand" "v"))
+ (match_operand:VI12_AVX512VL 2 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512BW && <mask_applied>"
+ "vpandn<ssemodesuffix>\t{%%2, %%1, %%0<mask_operand3>|%%0<mask_operand3>,
%%1, %%2}";
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
(define_expand "<code><mode>3"
[(set (match_operand:VI 0 "register_operand")
(any_logic:VI
@@ -13361,22 +13434,43 @@
(set (attr "prefix_rex") (symbol_ref "x86_extended_reg_mentioned_p (insn)"))
(set_attr "mode" "DI")])
-(define_insn "<mask_codefor>abs<mode>2<mask_name>"
- [(set (match_operand:VI124_AVX2_48_AVX512F 0 "register_operand" "=v")
- (abs:VI124_AVX2_48_AVX512F
- (match_operand:VI124_AVX2_48_AVX512F 1 "nonimmediate_operand" "vm")))]
- "TARGET_SSSE3 && <mask_mode512bit_condition>"
- "%vpabs<ssemodesuffix>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+(define_insn "*abs<mode>2"
+ [(set (match_operand:VI_AVX2 0 "register_operand" "=v")
+ (abs:VI_AVX2
+ (match_operand:VI_AVX2 1 "nonimmediate_operand" "vm")))]
+ "TARGET_SSSE3"
+ "%vpabs<ssemodesuffix>\t{%1, %0|%0, %1}"
[(set_attr "type" "sselog1")
(set_attr "prefix_data16" "1")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "<sseinsnmode>")])
+(define_insn "<mask_codefor>abs<mode>2<mask_name>"
+ [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v")
+ (abs:VI48_AVX512VL
+ (match_operand:VI48_AVX512VL 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F && <mask_applied>"
+ "vpabs<ssemodesuffix>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ [(set_attr "type" "sselog1")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "<mask_codefor>abs<mode>2<mask_name>"
+ [(set (match_operand:VI12_AVX512VL 0 "register_operand" "=v")
+ (abs:VI12_AVX512VL
+ (match_operand:VI12_AVX512VL 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512BW && <mask_applied>"
+ "vpabs<ssemodesuffix>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ [(set_attr "type" "sselog1")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+
(define_expand "abs<mode>2"
- [(set (match_operand:VI124_AVX2_48_AVX512F 0 "register_operand")
- (abs:VI124_AVX2_48_AVX512F
- (match_operand:VI124_AVX2_48_AVX512F 1 "nonimmediate_operand")))]
+ [(set (match_operand:VI_AVX2 0 "register_operand")
+ (abs:VI_AVX2
+ (match_operand:VI_AVX2 1 "nonimmediate_operand")))]
"TARGET_SSE2"
{
if (!TARGET_SSSE3)
