On 10/26/18, Uros Bizjak <ubiz...@gmail.com> wrote:
> On Fri, Oct 26, 2018 at 9:37 AM Uros Bizjak <ubiz...@gmail.com> wrote:
>>
>> On Fri, Oct 26, 2018 at 9:35 AM Uros Bizjak <ubiz...@gmail.com> wrote:
>> >
>> > On Fri, Oct 26, 2018 at 9:19 AM H.J. Lu <hjl.to...@gmail.com> wrote:
>> > >
>> > > On 10/25/18, Uros Bizjak <ubiz...@gmail.com> wrote:
>> > > > On Fri, Oct 26, 2018 at 8:07 AM H.J. Lu <hjl.to...@gmail.com>
>> > > > wrote:
>> > > >>
>> > > >> Many x86 pmovzx/pmovsx instructions with memory operands are
>> > > >> modeled in
>> > > >> a wrong way. For example:
>> > > >>
>> > > >> (define_insn "sse4_1_<code>v8qiv8hi2<mask_name>"
>> > > >> [(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
>> > > >> (any_extend:V8HI
>> > > >> (vec_select:V8QI
>> > > >> (match_operand:V16QI 1 "nonimmediate_operand"
>> > > >> "Yrm,*xm,vm")
>> > > >> (parallel [(const_int 0) (const_int 1)
>> > > >> (const_int 2) (const_int 3)
>> > > >> (const_int 4) (const_int 5)
>> > > >> (const_int 6) (const_int 7)]))))]
>> > > >>
>> > > >> should be defind for memory operands as:
>> > > >>
>> > > >> (define_insn "sse4_1_<code>v8qiv8hi2<mask_name>"
>> > > >> [(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
>> > > >> (any_extend:V8HI
>> > > >> (match_operand:V8QI "memory_operand" "m,m,m")))]
>> > > >>
>> > > >> This set of patches updates them to
>> > > >>
>> > > >> (define_insn "sse4_1_<code>v8qiv8hi2<mask_name>"
>> > > >> [(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
>> > > >> (any_extend:V8HI
>> > > >> (vec_select:V8QI
>> > > >> (match_operand:V16QI 1 "nonimmediate_operand" "Yr,*x,v")
>> > > >> (parallel [(const_int 0) (const_int 1)
>> > > >> (const_int 2) (const_int 3)
>> > > >> (const_int 4) (const_int 5)
>> > > >> (const_int 6) (const_int 7)]))))]
>> > > >>
>> > > >> (define_insn "*sse4_1_<code>v8qiv8hi2<mask_name>_1"
>> > > >> [(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
>> > > >> (any_extend:V8HI
>> > > >> (match_operand:V8QI "subreg_memory_operand" "m,m,m")))]
>> > > >>
>> > > >> with a splitter:
>> > > >>
>> > > >> (define_insn_and_split "*sse4_1_<code>v8qiv8hi2<mask_name>_2"
>> > > >> [(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
>> > > >
>> > > > No constraints needed for pre-reload splitter.
>> > > >
>> > > >> (any_extend:V8HI
>> > > >> (vec_select:V8QI
>> > > >> (subreg:V16QI
>> > > >> (vec_concat:V2DI
>> > > >> (match_operand:DI 1 "memory_operand" "m,*m,m")
>> > > >> (const_int 0)) 0)
>> > > >> (parallel [(const_int 0) (const_int 1)
>> > > >> (const_int 2) (const_int 3)
>> > > >> (const_int 4) (const_int 5)
>> > > >> (const_int 6) (const_int 7)]))))]
>> > > >> "TARGET_SSE4_1 && <mask_avx512bw_condition> &&
>> > > >> <mask_avx512vl_condition>"
>> > > >> "#"
>> > > >> "&& can_create_pseudo_p ()"
>> > > >> [(set (match_dup 0) (match_dup 1))]
>> > > >
>> > > > [(set (match_dup 0)
>> > > > (any_extend:V8HI (match_dup 1)))]
>> > > >
>> > > >> {
>> > > >> operands[1] = gen_rtx_<CODE> (V8HImode,
>> > > >> gen_rtx_SUBREG (V8QImode,
>> > > >> operands[1], 0));
>> > > >> })
>> > > >
>> > > > Don't create subregs of memory. Use adjust_address_nv.
>> > >
>> > > Here is the updated patch.
>> >
>> > > with a splitter:
>> > >
>> > > (define_insn_and_split "*sse4_1_<code>v8qiv8hi2<mask_name>_2"
>> > > [(set (match_operand:V8HI 0 "register_operand")
>> > > (any_extend:V8HI
>> > > (vec_select:V8QI
>> > > (subreg:V16QI
>> > > (vec_concat:V2DI
>> > > (match_operand:DI 1 "memory_operand")
>> > > (const_int 0)) 0)
>> > > (parallel [(const_int 0) (const_int 1)
>> > > (const_int 2) (const_int 3)
>> > > (const_int 4) (const_int 5)
>> > > (const_int 6) (const_int 7)]))))]
>> > > "TARGET_SSE4_1 && <mask_avx512bw_condition> &&
>> > > <mask_avx512vl_condition>"
>> > > "#"
>> > > "&& can_create_pseudo_p ()"
>> >
>> > "can_create_pseudo_p ()" should go to the insn constraint and "&& 1"
>> > should be used for split constraint. Both, insn and splitter are valid
>> > only before reload.
>> >
>> > > [(set (match_dup 0)
>> > > (any_extend:V8HI (match_dup 1)))]
>> > > {
>> > > operands[1] = adjust_address_nv (operands[1], V8QImode, 0);
>> > > })
>> >
>> > Please use double quotes for one-line preparation statement.
>> >
>> > > (any_extend:V4SI
>> > > (match_operand:V4HI 1 "memory_operand" "m,*m,m")))]
>> >
>> > Please remove star in front of memory constraint.
>> >
>> > OK with the above changes.
>>
>> Oh, and you should remove "q" and "k" operand modifiers in all old
>> patterns.
>
> Well, the new ones, obviously.
This is the patch I am going to check in after the apply_subst_iterator
fix is approved.
Thanks.
--
H.J.
From 585a4e65822b07c85b83096905d8c6130bf0381a Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.to...@gmail.com>
Date: Sat, 15 Sep 2018 20:54:42 -0700
Subject: [PATCH] x86: Add pmovzx/pmovsx patterns with memory operands
Many x86 pmovzx/pmovsx instructions with memory operands are modeled in
a wrong way. For example:
(define_insn "sse4_1_<code>v8qiv8hi2<mask_name>"
[(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
(any_extend:V8HI
(vec_select:V8QI
(match_operand:V16QI 1 "nonimmediate_operand" "Yrm,*xm,vm")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)
(const_int 4) (const_int 5)
(const_int 6) (const_int 7)]))))]
should be defind for memory operands as:
(define_insn "sse4_1_<code>v8qiv8hi2<mask_name>"
[(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
(any_extend:V8HI
(match_operand:V8QI "memory_operand" "m,m,m")))]
This patch updates them to
(define_insn "sse4_1_<code>v8qiv8hi2<mask_name>"
[(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
(any_extend:V8HI
(vec_select:V8QI
(match_operand:V16QI 1 "register_operand" "Yr,*x,v")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)
(const_int 4) (const_int 5)
(const_int 6) (const_int 7)]))))]
(define_insn "*sse4_1_<code>v8qiv8hi2<mask_name>_1"
[(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
(any_extend:V8HI
(match_operand:V8QI "subreg_memory_operand" "m,m,m")))]
with a splitter:
(define_insn_and_split "*sse4_1_<code>v8qiv8hi2<mask_name>_2"
[(set (match_operand:V8HI 0 "register_operand")
(any_extend:V8HI
(vec_select:V8QI
(subreg:V16QI
(vec_concat:V2DI
(match_operand:DI 1 "memory_operand")
(const_int 0)) 0)
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)
(const_int 4) (const_int 5)
(const_int 6) (const_int 7)]))))]
"TARGET_SSE4_1
&& <mask_avx512bw_condition>
&& <mask_avx512vl_condition>
"&& can_create_pseudo_p ()"
"#"
"&& 1"
[(set (match_dup 0)
(any_extend:V8HI (match_dup 1)))]
{
operands[1] = adjust_address_nv (operands[1], V8QImode, 0);
})
This patch requires updating apply_subst_iterator to handle
define_insn_and_split.
gcc/
PR target/87317
* config/i386/sse.md (sse4_1_<code>v8qiv8hi2<mask_name>): Replace
nonimmediate_operand with register_operand.
(avx2_<code>v8qiv8si2<mask_name>): Likewise.
(sse4_1_<code>v4qiv4si2<mask_name>): Likewise.
(sse4_1_<code>v4hiv4si2<mask_name>): Likewise.
(sse4_1_<code>v2qiv2di2<mask_name>): Likewise.
(avx512f_<code>v8qiv8di2<mask_name>): Likewise.
(avx2_<code>v4qiv4di2<mask_name>): Likewise.
(avx2_<code>v4hiv4di2<mask_name>): Likewise.
(sse4_1_<code>v2hiv2di2<mask_name>): Likewise.
(sse4_1_<code>v2siv2di2<mask_name>): Likewise.
(*sse4_1_<code>v8qiv8hi2<mask_name>_1): New pattern.
(*sse4_1_<code>v8qiv8hi2<mask_name>_2): Likewise.
(*avx2_<code>v8qiv8si2<mask_name>_1): Likewise.
(*avx2_<code>v8qiv8si2<mask_name>_2): Likewise.
(*sse4_1_<code>v4qiv4si2<mask_name>_1): Likewise.
(*sse4_1_<code>v4qiv4si2<mask_name>_2): Likewise.
(*sse4_1_<code>v4hiv4si2<mask_name>_1): Likewise.
(*sse4_1_<code>v4hiv4si2<mask_name>_2): Likewise.
(*avx512f_<code>v8qiv8di2<mask_name>_1): Likewise.
(*avx512f_<code>v8qiv8di2<mask_name>_2): Likewise.
(*avx2_<code>v4qiv4di2<mask_name>_1): Likewise.
(*avx2_<code>v4qiv4di2<mask_name>_2): Likewise.
(*avx2_<code>v4hiv4di2<mask_name>_1): Likewise.
(*avx2_<code>v4hiv4di2<mask_name>_2): Likewise.
(*sse4_1_<code>v2hiv2di2<mask_name>_1): Likewise.
(*sse4_1_<code>v2hiv2di2<mask_name>_2): Likewise.
(*sse4_1_<code>v2siv2di2<mask_name>_1): Likewise.
(*sse4_1_<code>v2siv2di2<mask_name>_2): Likewise.
gcc/testsuite/
PR target/87317
* gcc.target/i386/pr87317-1.c: New file.
* gcc.target/i386/pr87317-2.c: Likewise.
* gcc.target/i386/pr87317-3.c: Likewise.
* gcc.target/i386/pr87317-4.c: Likewise.
* gcc.target/i386/pr87317-5.c: Likewise.
* gcc.target/i386/pr87317-6.c: Likewise.
* gcc.target/i386/pr87317-7.c: Likewise.
* gcc.target/i386/pr87317-8.c: Likewise.
* gcc.target/i386/pr87317-9.c: Likewise.
* gcc.target/i386/pr87317-10.c: Likewise.
* gcc.target/i386/pr87317-11.c: Likewise.
* gcc.target/i386/pr87317-12.c: Likewise.
* gcc.target/i386/pr87317-13.c: Likewise.
---
gcc/config/i386/sse.md | 349 +++++++++++++++++++--
gcc/testsuite/gcc.target/i386/pr87317-1.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-10.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-11.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-12.c | 22 ++
gcc/testsuite/gcc.target/i386/pr87317-13.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-2.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-3.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-4.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-5.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-6.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-7.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-8.c | 14 +
gcc/testsuite/gcc.target/i386/pr87317-9.c | 14 +
14 files changed, 519 insertions(+), 20 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-1.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-10.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-11.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-12.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-13.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-2.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-3.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-4.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-5.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-6.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-7.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-8.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr87317-9.c
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index ee73e1fdf80..4ba2c96a35b 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -15878,19 +15878,55 @@
[(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
(any_extend:V8HI
(vec_select:V8QI
- (match_operand:V16QI 1 "nonimmediate_operand" "Yrm,*xm,vm")
+ (match_operand:V16QI 1 "register_operand" "Yr,*x,v")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)
(const_int 4) (const_int 5)
(const_int 6) (const_int 7)]))))]
"TARGET_SSE4_1 && <mask_avx512bw_condition> && <mask_avx512vl_condition>"
- "%vpmov<extsuffix>bw\t{%1, %0<mask_operand2>|%0<mask_operand2>, %q1}"
+ "%vpmov<extsuffix>bw\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+(define_insn "*sse4_1_<code>v8qiv8hi2<mask_name>_1"
+ [(set (match_operand:V8HI 0 "register_operand" "=Yr,*x,v")
+ (any_extend:V8HI
+ (match_operand:V8QI 1 "memory_operand" "m,m,m")))]
+ "TARGET_SSE4_1 && <mask_avx512bw_condition> && <mask_avx512vl_condition>"
+ "%vpmov<extsuffix>bw\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+
+(define_insn_and_split "*sse4_1_<code>v8qiv8hi2<mask_name>_2"
+ [(set (match_operand:V8HI 0 "register_operand")
+ (any_extend:V8HI
+ (vec_select:V8QI
+ (subreg:V16QI
+ (vec_concat:V2DI
+ (match_operand:DI 1 "memory_operand")
+ (const_int 0)) 0)
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)]))))]
+ "TARGET_SSE4_1
+ && <mask_avx512bw_condition>
+ && <mask_avx512vl_condition>
+ && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V8HI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V8QImode, 0);
+})
+
(define_insn "<mask_codefor>avx512f_<code>v16qiv16si2<mask_name>"
[(set (match_operand:V16SI 0 "register_operand" "=v")
(any_extend:V16SI
@@ -15905,33 +15941,105 @@
[(set (match_operand:V8SI 0 "register_operand" "=v")
(any_extend:V8SI
(vec_select:V8QI
- (match_operand:V16QI 1 "nonimmediate_operand" "vm")
+ (match_operand:V16QI 1 "register_operand" "v")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)
(const_int 4) (const_int 5)
(const_int 6) (const_int 7)]))))]
"TARGET_AVX2 && <mask_avx512vl_condition>"
- "vpmov<extsuffix>bd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %q1}"
+ "vpmov<extsuffix>bd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "type" "ssemov")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "maybe_evex")
(set_attr "mode" "OI")])
+(define_insn "*avx2_<code>v8qiv8si2<mask_name>_1"
+ [(set (match_operand:V8SI 0 "register_operand" "=v")
+ (any_extend:V8SI
+ (match_operand:V8QI 1 "memory_operand" "m")))]
+ "TARGET_AVX2 && <mask_avx512vl_condition>"
+ "%vpmov<extsuffix>bd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix_extra" "1")
+ (set_attr "prefix" "maybe_evex")
+ (set_attr "mode" "OI")])
+
+(define_insn_and_split "*avx2_<code>v8qiv8si2<mask_name>_2"
+ [(set (match_operand:V8SI 0 "register_operand")
+ (any_extend:V8SI
+ (vec_select:V8QI
+ (subreg:V16QI
+ (vec_concat:V2DI
+ (match_operand:DI 1 "memory_operand")
+ (const_int 0)) 0)
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)]))))]
+ "TARGET_AVX2
+ && <mask_avx512vl_condition>
+ && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V8SI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V8QImode, 0);
+})
+
(define_insn "sse4_1_<code>v4qiv4si2<mask_name>"
[(set (match_operand:V4SI 0 "register_operand" "=Yr,*x,v")
(any_extend:V4SI
(vec_select:V4QI
- (match_operand:V16QI 1 "nonimmediate_operand" "Yrm,*xm,vm")
+ (match_operand:V16QI 1 "register_operand" "Yr,*x,v")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)]))))]
"TARGET_SSE4_1 && <mask_avx512vl_condition>"
- "%vpmov<extsuffix>bd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %k1}"
+ "%vpmov<extsuffix>bd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+(define_insn "*sse4_1_<code>v4qiv4si2<mask_name>_1"
+ [(set (match_operand:V4SI 0 "register_operand" "=Yr,*x,v")
+ (any_extend:V4SI
+ (match_operand:V4QI 1 "memory_operand" "m,m,m")))]
+ "TARGET_SSE4_1 && <mask_avx512vl_condition>"
+ "%vpmov<extsuffix>bd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+
+(define_insn_and_split "*sse4_1_<code>v4qiv4si2<mask_name>_2"
+ [(set (match_operand:V4SI 0 "register_operand")
+ (any_extend:V4SI
+ (vec_select:V4QI
+ (subreg:V16QI
+ (vec_merge:V4SI
+ (vec_duplicate:V4SI
+ (match_operand:SI 1 "memory_operand"))
+ (const_vector:V4SI
+ [(const_int 0) (const_int 0)
+ (const_int 0) (const_int 0)])
+ (const_int 1)) 0)
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)]))))]
+ "TARGET_SSE4_1
+ && <mask_avx512bw_condition>
+ && <mask_avx512vl_condition>
+ && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V4SI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V4QImode, 0);
+})
+
(define_insn "avx512f_<code>v16hiv16si2<mask_name>"
[(set (match_operand:V16SI 0 "register_operand" "=v")
(any_extend:V16SI
@@ -15957,54 +16065,155 @@
[(set (match_operand:V4SI 0 "register_operand" "=Yr,*x,v")
(any_extend:V4SI
(vec_select:V4HI
- (match_operand:V8HI 1 "nonimmediate_operand" "Yrm,*xm,vm")
+ (match_operand:V8HI 1 "register_operand" "Yr,*x,v")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)]))))]
"TARGET_SSE4_1 && <mask_avx512vl_condition>"
- "%vpmov<extsuffix>wd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %q1}"
+ "%vpmov<extsuffix>wd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+(define_insn "*sse4_1_<code>v4hiv4si2<mask_name>_1"
+ [(set (match_operand:V4SI 0 "register_operand" "=Yr,*x,v")
+ (any_extend:V4SI
+ (match_operand:V4HI 1 "memory_operand" "m,m,m")))]
+ "TARGET_SSE4_1 && <mask_avx512vl_condition>"
+ "%vpmov<extsuffix>wd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+
+(define_insn_and_split "*sse4_1_<code>v4hiv4si2<mask_name>_2"
+ [(set (match_operand:V4SI 0 "register_operand")
+ (any_extend:V4SI
+ (vec_select:V4HI
+ (subreg:V8HI
+ (vec_concat:V2DI
+ (match_operand:DI 1 "memory_operand")
+ (const_int 0)) 0)
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)]))))]
+ "TARGET_SSE4_1
+ && <mask_avx512bw_condition>
+ && <mask_avx512vl_condition>
+ && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V4SI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V4HImode, 0);
+})
+
(define_insn "avx512f_<code>v8qiv8di2<mask_name>"
[(set (match_operand:V8DI 0 "register_operand" "=v")
(any_extend:V8DI
(vec_select:V8QI
- (match_operand:V16QI 1 "nonimmediate_operand" "vm")
+ (match_operand:V16QI 1 "register_operand" "v")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)
(const_int 4) (const_int 5)
(const_int 6) (const_int 7)]))))]
"TARGET_AVX512F"
- "vpmov<extsuffix>bq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %k1}"
+ "vpmov<extsuffix>bq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
+(define_insn "*avx512f_<code>v8qiv8di2<mask_name>_1"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (any_extend:V8DI
+ (match_operand:V8QI 1 "memory_operand" "m")))]
+ "TARGET_AVX512F"
+ "vpmov<extsuffix>bq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "type" "ssemov")
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
+(define_insn_and_split "*avx512f_<code>v8qiv8di2<mask_name>_2"
+ [(set (match_operand:V8DI 0 "register_operand")
+ (any_extend:V8DI
+ (vec_select:V8QI
+ (subreg:V16QI
+ (vec_concat:V2DI
+ (match_operand:DI 1 "memory_operand")
+ (const_int 0)) 0)
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)]))))]
+ "TARGET_AVX512F && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V8DI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V8QImode, 0);
+})
+
(define_insn "avx2_<code>v4qiv4di2<mask_name>"
[(set (match_operand:V4DI 0 "register_operand" "=v")
(any_extend:V4DI
(vec_select:V4QI
- (match_operand:V16QI 1 "nonimmediate_operand" "vm")
+ (match_operand:V16QI 1 "register_operand" "v")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)]))))]
"TARGET_AVX2 && <mask_avx512vl_condition>"
- "vpmov<extsuffix>bq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %k1}"
+ "vpmov<extsuffix>bq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "type" "ssemov")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "maybe_evex")
(set_attr "mode" "OI")])
+(define_insn "*avx2_<code>v4qiv4di2<mask_name>_1"
+ [(set (match_operand:V4DI 0 "register_operand" "=v")
+ (any_extend:V4DI
+ (match_operand:V4QI 1 "memory_operand" "m")))]
+ "TARGET_AVX2 && <mask_avx512vl_condition>"
+ "vpmov<extsuffix>bq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix_extra" "1")
+ (set_attr "prefix" "maybe_evex")
+ (set_attr "mode" "OI")])
+
+(define_insn_and_split "*avx2_<code>v4qiv4di2<mask_name>_2"
+ [(set (match_operand:V4DI 0 "register_operand")
+ (any_extend:V4DI
+ (vec_select:V4QI
+ (subreg:V16QI
+ (vec_merge:V4SI
+ (vec_duplicate:V4SI
+ (match_operand:SI 1 "memory_operand"))
+ (const_vector:V4SI
+ [(const_int 0) (const_int 0)
+ (const_int 0) (const_int 0)])
+ (const_int 1)) 0)
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)]))))]
+ "TARGET_AVX2
+ && <mask_avx512vl_condition>
+ && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V4DI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V4QImode, 0);
+})
+
(define_insn "sse4_1_<code>v2qiv2di2<mask_name>"
[(set (match_operand:V2DI 0 "register_operand" "=Yr,*x,v")
(any_extend:V2DI
(vec_select:V2QI
- (match_operand:V16QI 1 "nonimmediate_operand" "Yrm,*xm,vm")
+ (match_operand:V16QI 1 "register_operand" "Yr,*x,v")
(parallel [(const_int 0) (const_int 1)]))))]
"TARGET_SSE4_1 && <mask_avx512vl_condition>"
- "%vpmov<extsuffix>bq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %w1}"
+ "%vpmov<extsuffix>bq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemov")
(set_attr "prefix_extra" "1")
@@ -16025,30 +16234,98 @@
[(set (match_operand:V4DI 0 "register_operand" "=v")
(any_extend:V4DI
(vec_select:V4HI
- (match_operand:V8HI 1 "nonimmediate_operand" "vm")
+ (match_operand:V8HI 1 "register_operand" "v")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)]))))]
"TARGET_AVX2 && <mask_avx512vl_condition>"
- "vpmov<extsuffix>wq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %q1}"
+ "vpmov<extsuffix>wq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "type" "ssemov")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "maybe_evex")
(set_attr "mode" "OI")])
+(define_insn "*avx2_<code>v4hiv4di2<mask_name>_1"
+ [(set (match_operand:V4DI 0 "register_operand" "=v")
+ (any_extend:V4DI
+ (match_operand:V4HI 1 "memory_operand" "m")))]
+ "TARGET_AVX2 && <mask_avx512vl_condition>"
+ "vpmov<extsuffix>wq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix_extra" "1")
+ (set_attr "prefix" "maybe_evex")
+ (set_attr "mode" "OI")])
+
+(define_insn_and_split "*avx2_<code>v4hiv4di2<mask_name>_2"
+ [(set (match_operand:V4DI 0 "register_operand")
+ (any_extend:V4DI
+ (vec_select:V4HI
+ (subreg:V8HI
+ (vec_concat:V2DI
+ (match_operand:DI 1 "memory_operand")
+ (const_int 0)) 0)
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)]))))]
+ "TARGET_AVX2
+ && <mask_avx512vl_condition>
+ && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V4DI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V4HImode, 0);
+})
+
(define_insn "sse4_1_<code>v2hiv2di2<mask_name>"
[(set (match_operand:V2DI 0 "register_operand" "=Yr,*x,v")
(any_extend:V2DI
(vec_select:V2HI
- (match_operand:V8HI 1 "nonimmediate_operand" "Yrm,*xm,vm")
+ (match_operand:V8HI 1 "register_operand" "Yr,*x,v")
(parallel [(const_int 0) (const_int 1)]))))]
"TARGET_SSE4_1 && <mask_avx512vl_condition>"
- "%vpmov<extsuffix>wq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %k1}"
+ "%vpmov<extsuffix>wq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+
+(define_insn "*sse4_1_<code>v2hiv2di2<mask_name>_1"
+ [(set (match_operand:V2DI 0 "register_operand" "=Yr,*x,v")
+ (any_extend:V2DI
+ (match_operand:V2HI 1 "memory_operand" "m,m,m")))]
+ "TARGET_SSE4_1 && <mask_avx512vl_condition>"
+ "%vpmov<extsuffix>wq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+(define_insn_and_split "*sse4_1_<code>v2hiv2di2<mask_name>_2"
+ [(set (match_operand:V2DI 0 "register_operand")
+ (any_extend:V2DI
+ (vec_select:V2HI
+ (subreg:V8HI
+ (vec_merge:V4SI
+ (vec_duplicate:V4SI
+ (match_operand:SI 1 "memory_operand"))
+ (const_vector:V4SI
+ [(const_int 0) (const_int 0)
+ (const_int 0) (const_int 0)])
+ (const_int 1)) 0)
+ (parallel [(const_int 0) (const_int 1)]))))]
+ "TARGET_SSE4_1
+ && <mask_avx512vl_condition>
+ && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V2DI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V2HImode, 0);
+})
+
(define_insn "avx512f_<code>v8siv8di2<mask_name>"
[(set (match_operand:V8DI 0 "register_operand" "=v")
(any_extend:V8DI
@@ -16074,16 +16351,48 @@
[(set (match_operand:V2DI 0 "register_operand" "=Yr,*x,v")
(any_extend:V2DI
(vec_select:V2SI
- (match_operand:V4SI 1 "nonimmediate_operand" "Yrm,*xm,vm")
+ (match_operand:V4SI 1 "register_operand" "Yr,*x,v")
(parallel [(const_int 0) (const_int 1)]))))]
"TARGET_SSE4_1 && <mask_avx512vl_condition>"
- "%vpmov<extsuffix>dq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %q1}"
+ "%vpmov<extsuffix>dq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+(define_insn "*sse4_1_<code>v2siv2di2<mask_name>_1"
+ [(set (match_operand:V2DI 0 "register_operand" "=Yr,*x,v")
+ (any_extend:V2DI
+ (match_operand:V2SI 1 "memory_operand" "m,m,m")))]
+ "TARGET_SSE4_1 && <mask_avx512vl_condition>"
+ "%vpmov<extsuffix>dq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %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")])
+
+(define_insn_and_split "*sse4_1_<code>v2siv2di2<mask_name>_2"
+ [(set (match_operand:V2DI 0 "register_operand")
+ (any_extend:V2DI
+ (vec_select:V2SI
+ (subreg:V4SI
+ (vec_concat:V2DI
+ (match_operand:DI 1 "memory_operand")
+ (const_int 0)) 0)
+ (parallel [(const_int 0) (const_int 1)]))))]
+ "TARGET_SSE4_1
+ && <mask_avx512vl_condition>
+ && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (any_extend:V2DI (match_dup 1)))]
+{
+ operands[1] = adjust_address_nv (operands[1], V2SImode, 0);
+})
+
;; ptestps/ptestpd are very similar to comiss and ucomiss when
;; setting FLAGS_REG. But it is not a really compare instruction.
(define_insn "avx_vtest<ssemodesuffix><avxsizesuffix>"
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-1.c b/gcc/testsuite/gcc.target/i386/pr87317-1.c
new file mode 100644
index 00000000000..ec6b11d371d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-1.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxbw" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i data = _mm_cvtsi64_si128(*(long long int*)ptr);
+ data = _mm_cvtepu8_epi16(data);
+ _mm_storeu_si128((__m128i*)dst, data);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-10.c b/gcc/testsuite/gcc.target/i386/pr87317-10.c
new file mode 100644
index 00000000000..ea9a7a2f101
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-10.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxbd" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i y = _mm_cvtsi64_si128(*(long long int*)ptr);
+ __m256i z = _mm256_cvtepu8_epi32 (y);
+ _mm256_storeu_si256((__m256i*)dst, z);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-11.c b/gcc/testsuite/gcc.target/i386/pr87317-11.c
new file mode 100644
index 00000000000..13f0c23458a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-11.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxwq" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i y = _mm_cvtsi64_si128(*(long long int*)ptr);
+ __m256i z = _mm256_cvtepu16_epi64 (y);
+ _mm256_storeu_si256((__m256i*)dst, z);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-12.c b/gcc/testsuite/gcc.target/i386/pr87317-12.c
new file mode 100644
index 00000000000..1090966c4d1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-12.c
@@ -0,0 +1,22 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O3 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovsxwq" 1 } } */
+
+#include <immintrin.h>
+
+#define MAX 4
+
+long long int dst[MAX];
+short src[MAX];
+
+void
+foo (void)
+{
+ int i;
+ for (i = 0; i < MAX; i += 4)
+ {
+ __m128i data = _mm_cvtsi64_si128(*(long long int*)(src + i));
+ __m256i x = _mm256_cvtepi16_epi64(data);
+ _mm256_storeu_si256((__m256i*)(dst + i), x);
+ }
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-13.c b/gcc/testsuite/gcc.target/i386/pr87317-13.c
new file mode 100644
index 00000000000..d3c3def8680
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-13.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mavx512f" } */
+/* { dg-final { scan-assembler-times "vpmovzxbq" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i y = _mm_cvtsi64_si128(*(long long int*)ptr);
+ __m512i z = _mm512_cvtepu8_epi64 (y);
+ _mm512_storeu_si512((__m512i*)dst, z);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-2.c b/gcc/testsuite/gcc.target/i386/pr87317-2.c
new file mode 100644
index 00000000000..e7eaaf66eef
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-2.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovsxwd" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i data = _mm_cvtsi64_si128(*(long long int*)ptr);
+ data = _mm_cvtepi16_epi32(data);
+ _mm_storeu_si128((__m128i*)dst, data);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-3.c b/gcc/testsuite/gcc.target/i386/pr87317-3.c
new file mode 100644
index 00000000000..f2e041ab4af
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-3.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovsxdq" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i data = _mm_cvtsi64_si128(*(long long int*)ptr);
+ data = _mm_cvtepi32_epi64(data);
+ _mm_storeu_si128((__m128i*)dst, data);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-4.c b/gcc/testsuite/gcc.target/i386/pr87317-4.c
new file mode 100644
index 00000000000..2d4f24a89e9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-4.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxbd" 1 } } */
+/* { dg-final { scan-assembler-not "vmovd" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i data = _mm_cvtsi32_si128(*(int*)ptr);
+ data = _mm_cvtepu8_epi32(data);
+ _mm_storeu_si128((__m128i*)dst, data);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-5.c b/gcc/testsuite/gcc.target/i386/pr87317-5.c
new file mode 100644
index 00000000000..96f82847e5d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-5.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxwq" 1 } } */
+/* { dg-final { scan-assembler-not "vmovd" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i data = _mm_cvtsi32_si128(*(int*)ptr);
+ data = _mm_cvtepu16_epi64(data);
+ _mm_storeu_si128((__m128i*)dst, data);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-6.c b/gcc/testsuite/gcc.target/i386/pr87317-6.c
new file mode 100644
index 00000000000..4fe9b11c1be
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-6.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxbq" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i y = _mm_cvtsi32_si128(*(int*)ptr);
+ __m256i z = _mm256_cvtepu8_epi64 (y);
+ _mm256_storeu_si256((__m256i*)dst, z);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-7.c b/gcc/testsuite/gcc.target/i386/pr87317-7.c
new file mode 100644
index 00000000000..2c043d9eb26
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-7.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxbd" 1 } } */
+/* { dg-final { scan-assembler-not "vmovd" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i data = _mm_cvtsi32_si128(*(int*)ptr);
+ data = _mm_cvtepu8_epi32(data);
+ _mm_storeu_si128((__m128i*)dst, data);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-8.c b/gcc/testsuite/gcc.target/i386/pr87317-8.c
new file mode 100644
index 00000000000..178455f42c1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-8.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxwq" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i data = _mm_cvtsi64_si128(*(long long int*)ptr);
+ __m256i x = _mm256_cvtepu16_epi64(data);
+ _mm256_storeu_si256((__m256i*)dst, x);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr87317-9.c b/gcc/testsuite/gcc.target/i386/pr87317-9.c
new file mode 100644
index 00000000000..c5144fb667b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr87317-9.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=haswell" } */
+/* { dg-final { scan-assembler-times "vpmovzxbd" 1 } } */
+/* { dg-final { scan-assembler-not "vmovq" } } */
+
+#include <immintrin.h>
+
+void
+f (void *dst, void *ptr)
+{
+ __m128i data = _mm_cvtsi64_si128(*(long long int*)ptr);
+ __m256i x = _mm256_cvtepu8_epi32(data);
+ _mm256_storeu_si256((__m256i*)dst, x);
+}
--
2.17.2
