[v2] RISC-V: Fix ICE of RVV vget/vset intrinsic[PR111935]
Checks
Commit Message
Calling vget/vset intrinsic without receiving a return value will cause
a crash. Because in this case e.target is null.
This patch should be backported to releases/gcc-13.
PR/target 111935
gcc/ChangeLog:
* config/riscv/riscv-vector-builtins-bases.cc: fix bug.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/pr111935.c: New test.
---
.../riscv/riscv-vector-builtins-bases.cc | 4 +++
.../gcc.target/riscv/rvv/base/pr111935.c | 26 +++++++++++++++++++
2 files changed, 30 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
--
2.17.1
xuli1@eswincomputing.com
Comments
Ok for trunk (You can commit it to the trunk now).
For GCC-13, I'd like to wait for kito's comment.
Thanks.
juzhe.zhong@rivai.ai
From: Li Xu
Date: 2023-10-24 15:29
To: gcc-patches
CC: kito.cheng; palmer; juzhe.zhong
Subject: [PATCH v2] RISC-V: Fix ICE of RVV vget/vset intrinsic[PR111935]
Calling vget/vset intrinsic without receiving a return value will cause
a crash. Because in this case e.target is null.
This patch should be backported to releases/gcc-13.
PR/target 111935
gcc/ChangeLog:
* config/riscv/riscv-vector-builtins-bases.cc: fix bug.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/pr111935.c: New test.
---
.../riscv/riscv-vector-builtins-bases.cc | 4 +++
.../gcc.target/riscv/rvv/base/pr111935.c | 26 +++++++++++++++++++
2 files changed, 30 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index ab12e130907..0b1409a52e0 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -1740,6 +1740,8 @@ public:
rtx expand (function_expander &e) const override
{
+ if (!e.target)
+ return NULL_RTX;
rtx dest = expand_normal (CALL_EXPR_ARG (e.exp, 0));
gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (dest)));
rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
@@ -1777,6 +1779,8 @@ public:
rtx expand (function_expander &e) const override
{
+ if (!e.target)
+ return NULL_RTX;
rtx src = expand_normal (CALL_EXPR_ARG (e.exp, 0));
gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (src)));
rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
new file mode 100644
index 00000000000..0b936d849a1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O0 -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+inline vuint32m4_t __attribute__((__always_inline__)) transpose_indexes() {
+ static const uint32_t idx_[16] = {0, 4, 8, 12,
+ 1, 5, 9, 13,
+ 2, 6, 10, 14,
+ 3, 7, 11, 15};
+ return __riscv_vle32_v_u32m4(idx_, 16);
+}
+
+void pffft_real_preprocess_4x4(const float *in) {
+ vfloat32m1_t r0=__riscv_vle32_v_f32m1(in,4);
+ vfloat32m4_t tmp = __riscv_vundefined_f32m4();
+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 0, r0);
+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 1, r0);
+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 2, r0);
+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 3, r0);
+ tmp = __riscv_vrgather_vv_f32m4(tmp, transpose_indexes(), 16);
+ r0 = __riscv_vget_v_f32m4_f32m1(tmp, 0);
+}
+
+/* { dg-final { scan-assembler-times {vl[0-9]+re[0-9]+\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 10 } } */
+/* { dg-final { scan-assembler-times {vs[0-9]+r\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 8 } } */
--
2.17.1
xuli1@eswincomputing.com
Committed to trunk. Thanks juzhe.
--------------
Li Xu
>Ok for trunk (You can commit it to the trunk now).
>
>For GCC-13, I'd like to wait for kito's comment.
>
>Thanks.
>
>
>juzhe.zhong@rivai.ai
>
>From: Li Xu
>Date: 2023-10-24 15:29
>To: gcc-patches
>CC: kito.cheng; palmer; juzhe.zhong
>Subject: [PATCH v2] RISC-V: Fix ICE of RVV vget/vset intrinsic[PR111935]
>
>Calling vget/vset intrinsic without receiving a return value will cause
>a crash. Because in this case e.target is null.
>This patch should be backported to releases/gcc-13.
>
> PR/target 111935
>
>gcc/ChangeLog:
>
> * config/riscv/riscv-vector-builtins-bases.cc: fix bug.
>
>gcc/testsuite/ChangeLog:
>
> * gcc.target/riscv/rvv/base/pr111935.c: New test.
>---
> .../riscv/riscv-vector-builtins-bases.cc | 4 +++
> .../gcc.target/riscv/rvv/base/pr111935.c | 26 +++++++++++++++++++
> 2 files changed, 30 insertions(+)
> create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>
>diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
>index ab12e130907..0b1409a52e0 100644
>--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
>+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
>@@ -1740,6 +1740,8 @@ public:
>
> rtx expand (function_expander &e) const override
> {
>+ if (!e.target)
>+ return NULL_RTX;
> rtx dest = expand_normal (CALL_EXPR_ARG (e.exp, 0));
> gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (dest)));
> rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
>@@ -1777,6 +1779,8 @@ public:
>
> rtx expand (function_expander &e) const override
> {
>+ if (!e.target)
>+ return NULL_RTX;
> rtx src = expand_normal (CALL_EXPR_ARG (e.exp, 0));
> gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (src)));
> rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
>diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>new file mode 100644
>index 00000000000..0b936d849a1
>--- /dev/null
>+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>@@ -0,0 +1,26 @@
>+/* { dg-do compile } */
>+/* { dg-options "-march=rv64gcv -mabi=lp64d -O0 -Wno-psabi" } */
>+
>+#include "riscv_vector.h"
>+
>+inline vuint32m4_t __attribute__((__always_inline__)) transpose_indexes() {
>+ static const uint32_t idx_[16] = {0, 4, 8, 12,
>+ 1, 5, 9, 13,
>+ 2, 6, 10, 14,
>+ 3, 7, 11, 15};
>+ return __riscv_vle32_v_u32m4(idx_, 16);
>+}
>+
>+void pffft_real_preprocess_4x4(const float *in) {
>+ vfloat32m1_t r0=__riscv_vle32_v_f32m1(in,4);
>+ vfloat32m4_t tmp = __riscv_vundefined_f32m4();
>+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 0, r0);
>+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 1, r0);
>+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 2, r0);
>+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 3, r0);
>+ tmp = __riscv_vrgather_vv_f32m4(tmp, transpose_indexes(), 16);
>+ r0 = __riscv_vget_v_f32m4_f32m1(tmp, 0);
>+}
>+
>+/* { dg-final { scan-assembler-times {vl[0-9]+re[0-9]+\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 10 } } */
>+/* { dg-final { scan-assembler-times {vs[0-9]+r\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 8 } } */
>--
>2.17.1
>
>
>xuli1@eswincomputing.com
Ok for gcc 13 but just wait one more week to make sure everything is fine
as gcc convention :)
Li Xu <xuli1@eswincomputing.com>於 2023年10月24日 週二，15:49寫道：
> Committed to trunk. Thanks juzhe.
>
>
> --------------
>
>
>
> Li Xu
>
>
>
> >Ok for trunk (You can commit it to the trunk now).
>
>
>
> >
>
>
>
> >For GCC-13, I'd like to wait for kito's comment.
>
>
>
> >
>
>
>
> >Thanks.
>
>
>
> >
>
>
>
> >
>
>
>
> >juzhe.zhong@rivai.ai
>
>
>
> >
>
>
>
> >From: Li Xu
>
>
>
> >Date: 2023-10-24 15:29
>
>
>
> >To: gcc-patches
>
>
>
> >CC: kito.cheng; palmer; juzhe.zhong
>
>
>
> >Subject: [PATCH v2] RISC-V: Fix ICE of RVV vget/vset intrinsic[PR111935]
>
>
>
> >
>
>
>
> >Calling vget/vset intrinsic without receiving a return value will cause
>
>
>
> >a crash. Because in this case e.target is null.
>
>
>
> >This patch should be backported to releases/gcc-13.
>
>
>
> >
>
>
>
> > PR/target 111935
>
>
>
> >
>
>
>
> >gcc/ChangeLog:
>
>
>
> >
>
>
>
> > * config/riscv/riscv-vector-builtins-bases.cc: fix bug.
>
>
>
> >
>
>
>
> >gcc/testsuite/ChangeLog:
>
>
>
> >
>
>
>
> > * gcc.target/riscv/rvv/base/pr111935.c: New test.
>
>
>
> >---
>
>
>
> > .../riscv/riscv-vector-builtins-bases.cc | 4 +++
>
>
>
> > .../gcc.target/riscv/rvv/base/pr111935.c | 26 +++++++++++++++++++
>
>
>
> > 2 files changed, 30 insertions(+)
>
>
>
> > create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>
>
>
> >
>
>
>
> >diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc
> b/gcc/config/riscv/riscv-vector-builtins-bases.cc
>
>
>
> >index ab12e130907..0b1409a52e0 100644
>
>
>
> >--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
>
>
>
> >+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
>
>
>
> >@@ -1740,6 +1740,8 @@ public:
>
>
>
> >
>
>
>
> > rtx expand (function_expander &e) const override
>
>
>
> > {
>
>
>
> >+ if (!e.target)
>
>
>
> >+ return NULL_RTX;
>
>
>
> > rtx dest = expand_normal (CALL_EXPR_ARG (e.exp, 0));
>
>
>
> > gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (dest)));
>
>
>
> > rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
>
>
>
> >@@ -1777,6 +1779,8 @@ public:
>
>
>
> >
>
>
>
> > rtx expand (function_expander &e) const override
>
>
>
> > {
>
>
>
> >+ if (!e.target)
>
>
>
> >+ return NULL_RTX;
>
>
>
> > rtx src = expand_normal (CALL_EXPR_ARG (e.exp, 0));
>
>
>
> > gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (src)));
>
>
>
> > rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
>
>
>
> >diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
> b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>
>
>
> >new file mode 100644
>
>
>
> >index 00000000000..0b936d849a1
>
>
>
> >--- /dev/null
>
>
>
> >+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>
>
>
> >@@ -0,0 +1,26 @@
>
>
>
> >+/* { dg-do compile } */
>
>
>
> >+/* { dg-options "-march=rv64gcv -mabi=lp64d -O0 -Wno-psabi" } */
>
>
>
> >+
>
>
>
> >+#include "riscv_vector.h"
>
>
>
> >+
>
>
>
> >+inline vuint32m4_t __attribute__((__always_inline__))
> transpose_indexes() {
>
>
>
> >+ static const uint32_t idx_[16] = {0, 4, 8, 12,
>
>
>
> >+ 1, 5, 9, 13,
>
>
>
> >+ 2, 6, 10, 14,
>
>
>
> >+ 3, 7, 11, 15};
>
>
>
> >+ return __riscv_vle32_v_u32m4(idx_, 16);
>
>
>
> >+}
>
>
>
> >+
>
>
>
> >+void pffft_real_preprocess_4x4(const float *in) {
>
>
>
> >+ vfloat32m1_t r0=__riscv_vle32_v_f32m1(in,4);
>
>
>
> >+ vfloat32m4_t tmp = __riscv_vundefined_f32m4();
>
>
>
> >+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 0, r0);
>
>
>
> >+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 1, r0);
>
>
>
> >+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 2, r0);
>
>
>
> >+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 3, r0);
>
>
>
> >+ tmp = __riscv_vrgather_vv_f32m4(tmp, transpose_indexes(), 16);
>
>
>
> >+ r0 = __riscv_vget_v_f32m4_f32m1(tmp, 0);
>
>
>
> >+}
>
>
>
> >+
>
>
>
> >+/* { dg-final { scan-assembler-times
> {vl[0-9]+re[0-9]+\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 10 } } */
>
>
>
> >+/* { dg-final { scan-assembler-times
> {vs[0-9]+r\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 8 } } */
>
>
>
> >--
>
>
>
> >2.17.1
>
>
>
> >
>
>
>
> >
>
>
>
> >xuli1@eswincomputing.com
>
>
>
Already backported to releases/gcc-13.
--------------
Li Xu
>Ok for gcc 13 but just wait one more week to make sure everything is fine
>as gcc convention :)
>
>Li Xu <xuli1@eswincomputing.com>於 2023年10月24日 週二，15:49寫道：
>
>> Committed to trunk. Thanks juzhe.
>>
>>
>> --------------
>>
>>
>>
>> Li Xu
>>
>>
>>
>> >Ok for trunk (You can commit it to the trunk now).
>>
>>
>>
>> >
>>
>>
>>
>> >For GCC-13, I'd like to wait for kito's comment.
>>
>>
>>
>> >
>>
>>
>>
>> >Thanks.
>>
>>
>>
>> >
>>
>>
>>
>> >
>>
>>
>>
>> >juzhe.zhong@rivai.ai
>>
>>
>>
>> >
>>
>>
>>
>> >From: Li Xu
>>
>>
>>
>> >Date: 2023-10-24 15:29
>>
>>
>>
>> >To: gcc-patches
>>
>>
>>
>> >CC: kito.cheng; palmer; juzhe.zhong
>>
>>
>>
>> >Subject: [PATCH v2] RISC-V: Fix ICE of RVV vget/vset intrinsic[PR111935]
>>
>>
>>
>> >
>>
>>
>>
>> >Calling vget/vset intrinsic without receiving a return value will cause
>>
>>
>>
>> >a crash. Because in this case e.target is null.
>>
>>
>>
>> >This patch should be backported to releases/gcc-13.
>>
>>
>>
>> >
>>
>>
>>
>> > PR/target 111935
>>
>>
>>
>> >
>>
>>
>>
>> >gcc/ChangeLog:
>>
>>
>>
>> >
>>
>>
>>
>> > * config/riscv/riscv-vector-builtins-bases.cc: fix bug.
>>
>>
>>
>> >
>>
>>
>>
>> >gcc/testsuite/ChangeLog:
>>
>>
>>
>> >
>>
>>
>>
>> > * gcc.target/riscv/rvv/base/pr111935.c: New test.
>>
>>
>>
>> >---
>>
>>
>>
>> > .../riscv/riscv-vector-builtins-bases.cc | 4 +++
>>
>>
>>
>> > .../gcc.target/riscv/rvv/base/pr111935.c | 26 +++++++++++++++++++
>>
>>
>>
>> > 2 files changed, 30 insertions(+)
>>
>>
>>
>> > create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>>
>>
>>
>> >
>>
>>
>>
>> >diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc
>> b/gcc/config/riscv/riscv-vector-builtins-bases.cc
>>
>>
>>
>> >index ab12e130907..0b1409a52e0 100644
>>
>>
>>
>> >--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
>>
>>
>>
>> >+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
>>
>>
>>
>> >@@ -1740,6 +1740,8 @@ public:
>>
>>
>>
>> >
>>
>>
>>
>> > rtx expand (function_expander &e) const override
>>
>>
>>
>> > {
>>
>>
>>
>> >+ if (!e.target)
>>
>>
>>
>> >+ return NULL_RTX;
>>
>>
>>
>> > rtx dest = expand_normal (CALL_EXPR_ARG (e.exp, 0));
>>
>>
>>
>> > gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (dest)));
>>
>>
>>
>> > rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
>>
>>
>>
>> >@@ -1777,6 +1779,8 @@ public:
>>
>>
>>
>> >
>>
>>
>>
>> > rtx expand (function_expander &e) const override
>>
>>
>>
>> > {
>>
>>
>>
>> >+ if (!e.target)
>>
>>
>>
>> >+ return NULL_RTX;
>>
>>
>>
>> > rtx src = expand_normal (CALL_EXPR_ARG (e.exp, 0));
>>
>>
>>
>> > gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (src)));
>>
>>
>>
>> > rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
>>
>>
>>
>> >diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>> b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>>
>>
>>
>> >new file mode 100644
>>
>>
>>
>> >index 00000000000..0b936d849a1
>>
>>
>>
>> >--- /dev/null
>>
>>
>>
>> >+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111935.c
>>
>>
>>
>> >@@ -0,0 +1,26 @@
>>
>>
>>
>> >+/* { dg-do compile } */
>>
>>
>>
>> >+/* { dg-options "-march=rv64gcv -mabi=lp64d -O0 -Wno-psabi" } */
>>
>>
>>
>> >+
>>
>>
>>
>> >+#include "riscv_vector.h"
>>
>>
>>
>> >+
>>
>>
>>
>> >+inline vuint32m4_t __attribute__((__always_inline__))
>> transpose_indexes() {
>>
>>
>>
>> >+ static const uint32_t idx_[16] = {0, 4, 8, 12,
>>
>>
>>
>> >+ 1, 5, 9, 13,
>>
>>
>>
>> >+ 2, 6, 10, 14,
>>
>>
>>
>> >+ 3, 7, 11, 15};
>>
>>
>>
>> >+ return __riscv_vle32_v_u32m4(idx_, 16);
>>
>>
>>
>> >+}
>>
>>
>>
>> >+
>>
>>
>>
>> >+void pffft_real_preprocess_4x4(const float *in) {
>>
>>
>>
>> >+ vfloat32m1_t r0=__riscv_vle32_v_f32m1(in,4);
>>
>>
>>
>> >+ vfloat32m4_t tmp = __riscv_vundefined_f32m4();
>>
>>
>>
>> >+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 0, r0);
>>
>>
>>
>> >+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 1, r0);
>>
>>
>>
>> >+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 2, r0);
>>
>>
>>
>> >+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 3, r0);
>>
>>
>>
>> >+ tmp = __riscv_vrgather_vv_f32m4(tmp, transpose_indexes(), 16);
>>
>>
>>
>> >+ r0 = __riscv_vget_v_f32m4_f32m1(tmp, 0);
>>
>>
>>
>> >+}
>>
>>
>>
>> >+
>>
>>
>>
>> >+/* { dg-final { scan-assembler-times
>> {vl[0-9]+re[0-9]+\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 10 } } */
>>
>>
>>
>> >+/* { dg-final { scan-assembler-times
>> {vs[0-9]+r\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 8 } } */
>>
>>
>>
>> >--
>>
>>
>>
>> >2.17.1
>>
>>
>>
>> >
>>
>>
>>
>> >
>>
>>
>>
>> >xuli1@eswincomputing.com
>>
>>
>>
@@ -1740,6 +1740,8 @@ public:
rtx expand (function_expander &e) const override
{
+ if (!e.target)
+ return NULL_RTX;
rtx dest = expand_normal (CALL_EXPR_ARG (e.exp, 0));
gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (dest)));
rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
@@ -1777,6 +1779,8 @@ public:
rtx expand (function_expander &e) const override
{
+ if (!e.target)
+ return NULL_RTX;
rtx src = expand_normal (CALL_EXPR_ARG (e.exp, 0));
gcc_assert (riscv_v_ext_vector_mode_p (GET_MODE (src)));
rtx index = expand_normal (CALL_EXPR_ARG (e.exp, 1));
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O0 -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+inline vuint32m4_t __attribute__((__always_inline__)) transpose_indexes() {
+ static const uint32_t idx_[16] = {0, 4, 8, 12,
+ 1, 5, 9, 13,
+ 2, 6, 10, 14,
+ 3, 7, 11, 15};
+ return __riscv_vle32_v_u32m4(idx_, 16);
+}
+
+void pffft_real_preprocess_4x4(const float *in) {
+ vfloat32m1_t r0=__riscv_vle32_v_f32m1(in,4);
+ vfloat32m4_t tmp = __riscv_vundefined_f32m4();
+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 0, r0);
+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 1, r0);
+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 2, r0);
+ tmp = __riscv_vset_v_f32m1_f32m4(tmp, 3, r0);
+ tmp = __riscv_vrgather_vv_f32m4(tmp, transpose_indexes(), 16);
+ r0 = __riscv_vget_v_f32m4_f32m1(tmp, 0);
+}
+
+/* { dg-final { scan-assembler-times {vl[0-9]+re[0-9]+\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 10 } } */
+/* { dg-final { scan-assembler-times {vs[0-9]+r\.v\s+v[0-9]+,\s*0\([a-z]+[0-9]+\)} 8 } } */