@@ -5355,6 +5355,12 @@ ix86_expand_sse_unpack (rtx dest, rtx src, bool unsigned_p, bool high_p)
else
unpack = gen_sse4_1_sign_extendv2hiv2si2;
break;
+ case E_V4QImode:
+ if (unsigned_p)
+ unpack = gen_sse4_1_zero_extendv2qiv2hi2;
+ else
+ unpack = gen_sse4_1_sign_extendv2qiv2hi2;
+ break;
default:
gcc_unreachable ();
}
@@ -5380,6 +5386,12 @@ ix86_expand_sse_unpack (rtx dest, rtx src, bool unsigned_p, bool high_p)
emit_insn (gen_mmx_lshrv1di3 (tmp, gen_lowpart (V1DImode, src),
GEN_INT (32)));
break;
+ case 4:
+ /* Shift higher 2 bytes to lower 2 bytes. */
+ tmp = gen_reg_rtx (V1SImode);
+ emit_insn (gen_mmx_lshrv1si3 (tmp, gen_lowpart (V1SImode, src),
+ GEN_INT (16)));
+ break;
default:
gcc_unreachable ();
}
@@ -5427,6 +5439,12 @@ ix86_expand_sse_unpack (rtx dest, rtx src, bool unsigned_p, bool high_p)
else
unpack = gen_mmx_punpcklwd;
break;
+ case E_V4QImode:
+ if (high_p)
+ unpack = gen_mmx_punpckhbw_low;
+ else
+ unpack = gen_mmx_punpcklbw_low;
+ break;
default:
gcc_unreachable ();
}
@@ -1016,7 +1016,7 @@ extern const char *host_detect_local_cpu (int argc, const char **argv);
#define VALID_SSE2_REG_MODE(MODE) \
((MODE) == V16QImode || (MODE) == V8HImode || (MODE) == V2DFmode \
- || (MODE) == V4QImode || (MODE) == V2HImode \
+ || (MODE) == V4QImode || (MODE) == V2HImode || (MODE) == V1SImode \
|| (MODE) == V2DImode || (MODE) == DFmode)
#define VALID_SSE_REG_MODE(MODE) \
@@ -1048,7 +1048,7 @@ extern const char *host_detect_local_cpu (int argc, const char **argv);
|| (MODE) == SImode || (MODE) == DImode \
|| (MODE) == CQImode || (MODE) == CHImode \
|| (MODE) == CSImode || (MODE) == CDImode \
- || (MODE) == V4QImode || (MODE) == V2HImode \
+ || (MODE) == V4QImode || (MODE) == V2HImode || (MODE) == V1SImode \
|| (TARGET_64BIT \
&& ((MODE) == TImode || (MODE) == CTImode \
|| (MODE) == TFmode || (MODE) == TCmode \
@@ -57,10 +57,13 @@ (define_mode_iterator MMXMODE14 [V8QI V2SI])
(define_mode_iterator MMXMODE24 [V4HI V2SI])
(define_mode_iterator MMXMODE248 [V4HI V2SI V1DI])
-;; All 32bit integer vector modes
+;; All 4-byte integer vector modes
+(define_mode_iterator V_32 [V4QI V2HI V1SI])
+
+;; 4-byte integer vector modes
(define_mode_iterator VI_32 [V4QI V2HI])
-;; All V2S* modes
+;; V2S* modes
(define_mode_iterator V2FI [V2SF V2SI])
;; Mapping from integer vector mode to mnemonic suffix
@@ -238,8 +241,8 @@ (define_expand "movmisalign<mode>"
})
(define_expand "mov<mode>"
- [(set (match_operand:VI_32 0 "nonimmediate_operand")
- (match_operand:VI_32 1 "nonimmediate_operand"))]
+ [(set (match_operand:V_32 0 "nonimmediate_operand")
+ (match_operand:V_32 1 "nonimmediate_operand"))]
"TARGET_SSE2"
{
ix86_expand_vector_move (<MODE>mode, operands);
@@ -247,9 +250,9 @@ (define_expand "mov<mode>"
})
(define_insn "*mov<mode>_internal"
- [(set (match_operand:VI_32 0 "nonimmediate_operand"
+ [(set (match_operand:V_32 0 "nonimmediate_operand"
"=r ,m ,v,v,v,m,r,v")
- (match_operand:VI_32 1 "general_operand"
+ (match_operand:V_32 1 "general_operand"
"rmC,rC,C,v,m,v,v,r"))]
"TARGET_SSE2 &&
!(MEM_P (operands[0]) && MEM_P (operands[1]))"
@@ -304,8 +307,8 @@ (define_insn "*mov<mode>_internal"
;; For TARGET_64BIT we always round up to 8 bytes.
(define_insn "*push<mode>2_rex64"
- [(set (match_operand:VI_32 0 "push_operand" "=X,X")
- (match_operand:VI_32 1 "nonmemory_no_elim_operand" "rC,*v"))]
+ [(set (match_operand:V_32 0 "push_operand" "=X,X")
+ (match_operand:V_32 1 "nonmemory_no_elim_operand" "rC,*v"))]
"TARGET_SSE2 && TARGET_64BIT"
"@
push{q}\t%q1
@@ -314,8 +317,8 @@ (define_insn "*push<mode>2_rex64"
(set_attr "mode" "DI")])
(define_insn "*push<mode>2"
- [(set (match_operand:VI_32 0 "push_operand" "=<,<")
- (match_operand:VI_32 1 "general_no_elim_operand" "rC*m,*v"))]
+ [(set (match_operand:V_32 0 "push_operand" "=<,<")
+ (match_operand:V_32 1 "general_no_elim_operand" "rC*m,*v"))]
"TARGET_SSE2 && !TARGET_64BIT"
"@
push{l}\t%1
@@ -324,20 +327,20 @@ (define_insn "*push<mode>2"
(set_attr "mode" "SI")])
(define_split
- [(set (match_operand:VI_32 0 "push_operand")
- (match_operand:VI_32 1 "sse_reg_operand"))]
+ [(set (match_operand:V_32 0 "push_operand")
+ (match_operand:V_32 1 "sse_reg_operand"))]
"TARGET_SSE2 && reload_completed"
[(set (reg:P SP_REG) (plus:P (reg:P SP_REG) (match_dup 2)))
(set (match_dup 0) (match_dup 1))]
{
- operands[2] = GEN_INT (-PUSH_ROUNDING (GET_MODE_SIZE (<VI_32:MODE>mode)));
+ operands[2] = GEN_INT (-PUSH_ROUNDING (GET_MODE_SIZE (<V_32:MODE>mode)));
/* Preserve memory attributes. */
operands[0] = replace_equiv_address (operands[0], stack_pointer_rtx);
})
(define_expand "movmisalign<mode>"
- [(set (match_operand:VI_32 0 "nonimmediate_operand")
- (match_operand:VI_32 1 "nonimmediate_operand"))]
+ [(set (match_operand:V_32 0 "nonimmediate_operand")
+ (match_operand:V_32 1 "nonimmediate_operand"))]
"TARGET_SSE2"
{
ix86_expand_vector_move (<MODE>mode, operands);
@@ -2006,6 +2009,23 @@ (define_expand "<insn><mode>3"
(match_operand:DI 2 "nonmemory_operand")))]
"TARGET_MMX_WITH_SSE")
+(define_insn "mmx_<insn>v1si3"
+ [(set (match_operand:V1SI 0 "register_operand" "=x,Yw")
+ (any_lshift:V1SI
+ (match_operand:V1SI 1 "register_operand" "0,Yw")
+ (match_operand:DI 2 "nonmemory_operand" "xN,YwN")))]
+ "TARGET_SSE2"
+ "@
+ p<vshift>d\t{%2, %0|%0, %2}
+ vp<vshift>d\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "noavx,avx")
+ (set_attr "type" "sseishft")
+ (set (attr "length_immediate")
+ (if_then_else (match_operand 2 "const_int_operand")
+ (const_string "1")
+ (const_string "0")))
+ (set_attr "mode" "TI")])
+
(define_insn "<insn>v2hi3"
[(set (match_operand:V2HI 0 "register_operand" "=x,Yw")
(any_shift:V2HI
@@ -2732,6 +2752,20 @@ (define_insn "sse4_1_<code>v2hiv2si2"
(set_attr "prefix" "orig,orig,maybe_evex")
(set_attr "mode" "TI")])
+(define_insn "sse4_1_<code>v2qiv2hi2"
+ [(set (match_operand:V2HI 0 "register_operand" "=Yr,*x,Yw")
+ (any_extend:V2HI
+ (vec_select:V2QI
+ (match_operand:V4QI 1 "register_operand" "Yr,*x,Yw")
+ (parallel [(const_int 0) (const_int 1)]))))]
+ "TARGET_SSE4_1"
+ "%vpmov<extsuffix>bw\t{%1, %0|%0, %1}"
+ [(set_attr "isa" "noavx,noavx,avx")
+ (set_attr "type" "ssemov")
+ (set_attr "prefix_extra" "1")
+ (set_attr "prefix" "orig,orig,maybe_evex")
+ (set_attr "mode" "TI")])
+
;; Pack/unpack vector modes
(define_mode_attr mmxpackmode
[(V4HI "V8QI") (V2SI "V4HI")])
@@ -2748,6 +2782,18 @@ (define_expand "vec_pack_trunc_<mode>"
DONE;
})
+(define_expand "vec_pack_trunc_v2hi"
+ [(match_operand:V4QI 0 "register_operand")
+ (match_operand:V2HI 1 "register_operand")
+ (match_operand:V2HI 2 "register_operand")]
+ "TARGET_SSE2"
+{
+ rtx op1 = gen_lowpart (V4QImode, operands[1]);
+ rtx op2 = gen_lowpart (V4QImode, operands[2]);
+ ix86_expand_vec_extract_even_odd (operands[0], op1, op2, 0);
+ DONE;
+})
+
(define_mode_attr mmxunpackmode
[(V8QI "V4HI") (V4HI "V2SI")])
@@ -2775,6 +2821,30 @@ (define_expand "vec_unpacku_hi_<mode>"
"TARGET_MMX_WITH_SSE"
"ix86_expand_sse_unpack (operands[0], operands[1], true, true); DONE;")
+(define_expand "vec_unpacks_lo_v4qi"
+ [(match_operand:V2HI 0 "register_operand")
+ (match_operand:V4QI 1 "register_operand")]
+ "TARGET_SSE2"
+ "ix86_expand_sse_unpack (operands[0], operands[1], false, false); DONE;")
+
+(define_expand "vec_unpacks_hi_v4qi"
+ [(match_operand:V2HI 0 "register_operand")
+ (match_operand:V4QI 1 "register_operand")]
+ "TARGET_SSE2"
+ "ix86_expand_sse_unpack (operands[0], operands[1], false, true); DONE;")
+
+(define_expand "vec_unpacku_lo_v4qi"
+ [(match_operand:V2HI 0 "register_operand")
+ (match_operand:V4QI 1 "register_operand")]
+ "TARGET_SSE2"
+ "ix86_expand_sse_unpack (operands[0], operands[1], true, false); DONE;")
+
+(define_expand "vec_unpacku_hi_v4qi"
+ [(match_operand:V2HI 0 "register_operand")
+ (match_operand:V4QI 1 "register_operand")]
+ "TARGET_SSE2"
+ "ix86_expand_sse_unpack (operands[0], operands[1], true, true); DONE;")
+
(define_insn "*mmx_pinsrd"
[(set (match_operand:V2SI 0 "register_operand" "=x,Yv")
(vec_merge:V2SI
V1SI mode shift is needed to shift 32bit operands and consequently we need to implement V1SI moves and pushes. 2021-07-08 Uroš Bizjak <ubizjak@gmail.com> gcc/ PR target/100637 * config/i386/i386-expand.c (ix86_expand_sse_unpack): Handle V4QI mode. * config/i386/mmx.md (V_32): New mode iterator. (mov<V_32:mode>): Use V_32 mode iterator. (*mov<V_32:mode>_internal): Ditto. (*push<V_32:mode>2_rex64): Ditto. (*push<V_32:mode>2): Ditto. (movmisalign<V_32:mode>): Ditto. (mmx_<any_shiftrt:insn>v1si3): New insn pattern. (sse4_1_<any_extend:code>v2qiv2hi2): Ditto. (vec_unpacks_lo_v4qi): New expander. (vec_unpacks_hi_v4qi): Ditto. (vec_unpacku_lo_v4qi): Ditto. (vec_unpacku_hi_v4qi): Ditto. * config/i386/i386.h (VALID_SSE2_REG_MODE): Add V1SImode. (VALID_INT_MODE_P): Ditto. Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}. Pushed to master. Uros.