XMM broadcast instructions broadcast value from general reg to all
elements of the vector. This is not allowed for TARGET_MMX_WITH_SSE,
where it is expected that bits outside lower 64bits load or retain
zero value. Following testcases expect broadcast, and are thus invalid:
FAIL: gcc.target/i386/sse2-mmx-18b.c scan-assembler-not movd
FAIL: gcc.target/i386/sse2-mmx-18b.c scan-assembler-times pbroadcastd 1
FAIL: gcc.target/i386/sse2-mmx-19b.c scan-assembler-not movd
FAIL: gcc.target/i386/sse2-mmx-19b.c scan-assembler-times pbroadcastw 1
FAIL: gcc.target/i386/sse2-mmx-19d.c scan-assembler-times pbroadcastw 1
FAIL: gcc.target/i386/sse2-mmx-19e.c scan-assembler-times pbroadcastw 1
These testcases will be fixed or removed entirely.
(The patch is prerequisite to implement support for generic
v2sf/v2si/v4hi shuffles).
2020-05-24 Uroš Bizjak <ubiz...@gmail.com>
gcc/ChangeLog:
* config/i386/mmx.md (*vec_dupv2sf): Redefine as define_insn.
(mmx_pshufw_1): Change Yv constraint to xYw. Correct type attribute.
(*vec_dupv4hi): Redefine as define_insn.
Remove alternative with general register input.
(*vec_dupv2si): Ditto.
Uros.
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 5deef683b0b..b5564711aa4 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -947,27 +947,22 @@
(set_attr "prefix_extra" "1")
(set_attr "mode" "V2SF")])
-(define_insn_and_split "*vec_dupv2sf"
+(define_insn "*vec_dupv2sf"
[(set (match_operand:V2SF 0 "register_operand" "=y,x,Yv")
(vec_duplicate:V2SF
(match_operand:SF 1 "register_operand" "0,0,Yv")))]
"TARGET_MMX || TARGET_MMX_WITH_SSE"
"@
punpckldq\t%0, %0
- #
- #"
- "TARGET_SSE && reload_completed
- && SSE_REGNO_P (REGNO (operands[0]))"
- [(set (match_dup 0)
- (vec_duplicate:V4SF (match_dup 1)))]
-{
- operands[0] = lowpart_subreg (V4SFmode, operands[0],
- GET_MODE (operands[0]));
-}
- [(set_attr "isa" "*,sse_noavx,avx")
+ shufps\t{$0xe0, %0, %0|%0, %0, 0xe0}
+ %vmovsldup\t{%1, %0|%0, %1}"
+ [(set_attr "isa" "*,sse_noavx,sse3")
(set_attr "mmx_isa" "native,*,*")
- (set_attr "type" "mmxcvt,ssemov,ssemov")
- (set_attr "mode" "DI,TI,TI")])
+ (set_attr "type" "mmxcvt,sseshuf1,sse")
+ (set_attr "length_immediate" "*,1,*")
+ (set_attr "prefix_rep" "*,*,1")
+ (set_attr "prefix" "*,orig,maybe_vex")
+ (set_attr "mode" "DI,V4SF,V4SF")])
(define_insn "*mmx_concatv2sf"
[(set (match_operand:V2SF 0 "register_operand" "=y,y")
@@ -1960,9 +1955,9 @@
})
(define_insn "mmx_pshufw_1"
- [(set (match_operand:V4HI 0 "register_operand" "=y,Yv")
+ [(set (match_operand:V4HI 0 "register_operand" "=y,xYw")
(vec_select:V4HI
- (match_operand:V4HI 1 "register_mmxmem_operand" "ym,Yv")
+ (match_operand:V4HI 1 "register_mmxmem_operand" "ym,xYw")
(parallel [(match_operand 2 "const_0_to_3_operand")
(match_operand 3 "const_0_to_3_operand")
(match_operand 4 "const_0_to_3_operand")
@@ -1989,7 +1984,7 @@
}
[(set_attr "isa" "*,sse2")
(set_attr "mmx_isa" "native,*")
- (set_attr "type" "mmxcvt,sselog")
+ (set_attr "type" "mmxcvt,sselog1")
(set_attr "length_immediate" "1")
(set_attr "mode" "DI,TI")])
@@ -2004,77 +1999,37 @@
(set_attr "prefix_extra" "1")
(set_attr "mode" "DI")])
-(define_insn_and_split "*vec_dupv4hi"
- [(set (match_operand:V4HI 0 "register_operand" "=y,xYw,Yw")
+(define_insn "*vec_dupv4hi"
+ [(set (match_operand:V4HI 0 "register_operand" "=y,xYw")
(vec_duplicate:V4HI
(truncate:HI
- (match_operand:SI 1 "register_operand" "0,xYw,r"))))]
+ (match_operand:SI 1 "register_operand" "0,xYw"))))]
"(TARGET_MMX || TARGET_MMX_WITH_SSE)
&& (TARGET_SSE || TARGET_3DNOW_A)"
"@
pshufw\t{$0, %0, %0|%0, %0, 0}
- #
- #"
- "TARGET_SSE2 && reload_completed
- && SSE_REGNO_P (REGNO (operands[0]))"
- [(const_int 0)]
-{
- rtx op;
- operands[0] = lowpart_subreg (V8HImode, operands[0],
- GET_MODE (operands[0]));
- if (TARGET_AVX2)
- {
- operands[1] = lowpart_subreg (HImode, operands[1],
- GET_MODE (operands[1]));
- op = gen_rtx_VEC_DUPLICATE (V8HImode, operands[1]);
- }
- else
- {
- operands[1] = lowpart_subreg (V8HImode, operands[1],
- GET_MODE (operands[1]));
- rtx mask = gen_rtx_PARALLEL (VOIDmode,
- gen_rtvec (8,
- GEN_INT (0),
- GEN_INT (0),
- GEN_INT (0),
- GEN_INT (0),
- GEN_INT (4),
- GEN_INT (5),
- GEN_INT (6),
- GEN_INT (7)));
-
- op = gen_rtx_VEC_SELECT (V8HImode, operands[1], mask);
- }
- emit_insn (gen_rtx_SET (operands[0], op));
- DONE;
-}
- [(set_attr "mmx_isa" "native,sse,avx")
- (set_attr "type" "mmxcvt,sselog1,ssemov")
- (set_attr "length_immediate" "1,1,0")
- (set_attr "mode" "DI,TI,TI")])
+ %vpshuflw\t{$0, %1, %0|%0, %1, 0}"
+ [(set_attr "isa" "*,sse2")
+ (set_attr "mmx_isa" "native,*")
+ (set_attr "type" "mmxcvt,sselog1")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "DI,TI")])
+
-(define_insn_and_split "*vec_dupv2si"
- [(set (match_operand:V2SI 0 "register_operand" "=y,x,Yv,Yw")
+(define_insn "*vec_dupv2si"
+ [(set (match_operand:V2SI 0 "register_operand" "=y,Yv")
(vec_duplicate:V2SI
- (match_operand:SI 1 "register_operand" "0,0,Yv,r")))]
+ (match_operand:SI 1 "register_operand" "0,Yv")))]
"TARGET_MMX || TARGET_MMX_WITH_SSE"
"@
punpckldq\t%0, %0
- #
- #
- #"
- "TARGET_SSE && reload_completed
- && SSE_REGNO_P (REGNO (operands[0]))"
- [(set (match_dup 0)
- (vec_duplicate:V4SI (match_dup 1)))]
-{
- operands[0] = lowpart_subreg (V4SImode, operands[0],
- GET_MODE (operands[0]));
-}
- [(set_attr "isa" "*,sse_noavx,avx,avx")
- (set_attr "mmx_isa" "native,*,*,*")
- (set_attr "type" "mmxcvt,ssemov,ssemov,ssemov")
- (set_attr "mode" "DI,TI,TI,TI")])
+ %vpshufd\t{$0xe0, %1, %0|%0, %1, 0xe0}"
+ [(set_attr "isa" "*,sse2")
+ (set_attr "mmx_isa" "native,*")
+ (set_attr "type" "mmxcvt,sselog1")
+ (set_attr "prefix_data16" "*,1")
+ (set_attr "length_immediate" "*,1")
+ (set_attr "mode" "DI,TI")])
(define_insn "*mmx_concatv2si"
[(set (match_operand:V2SI 0 "register_operand" "=y,y")
