[v1] RISC-V: Support RVV VFWREDUSUM.VS rounding mode intrinsic API
Checks
Commit Message
From: Pan Li <pan2.li@intel.com>
This patch would like to support the rounding mode API for the
VFWREDUSUM.VS as the below samples
* __riscv_vfwredusum_vs_f32m1_f64m1_rm
* __riscv_vfwredusum_vs_f32m1_f64m1_rm_m
Signed-off-by: Pan Li <pan2.li@intel.com>
gcc/ChangeLog:
* config/riscv/riscv-vector-builtins-bases.cc
(vfwredusum_frm_obj): New declaration.
(BASE): Ditto.
* config/riscv/riscv-vector-builtins-bases.h: Ditto.
* config/riscv/riscv-vector-builtins-functions.def
(vfwredusum_frm): New intrinsic function def.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/float-point-wredusum.c: New test.
---
.../riscv/riscv-vector-builtins-bases.cc | 2 ++
.../riscv/riscv-vector-builtins-bases.h | 1 +
.../riscv/riscv-vector-builtins-functions.def | 1 +
.../riscv/rvv/base/float-point-wredusum.c | 33 +++++++++++++++++++
4 files changed, 37 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c
Comments
Why does this patch not have HAS_FRM?
juzhe.zhong@rivai.ai
From: pan2.li
Date: 2023-08-17 16:05
To: gcc-patches
CC: juzhe.zhong; pan2.li; yanzhang.wang; kito.cheng
Subject: [PATCH v1] RISC-V: Support RVV VFWREDUSUM.VS rounding mode intrinsic API
From: Pan Li <pan2.li@intel.com>
This patch would like to support the rounding mode API for the
VFWREDUSUM.VS as the below samples
* __riscv_vfwredusum_vs_f32m1_f64m1_rm
* __riscv_vfwredusum_vs_f32m1_f64m1_rm_m
Signed-off-by: Pan Li <pan2.li@intel.com>
gcc/ChangeLog:
* config/riscv/riscv-vector-builtins-bases.cc
(vfwredusum_frm_obj): New declaration.
(BASE): Ditto.
* config/riscv/riscv-vector-builtins-bases.h: Ditto.
* config/riscv/riscv-vector-builtins-functions.def
(vfwredusum_frm): New intrinsic function def.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/float-point-wredusum.c: New test.
---
.../riscv/riscv-vector-builtins-bases.cc | 2 ++
.../riscv/riscv-vector-builtins-bases.h | 1 +
.../riscv/riscv-vector-builtins-functions.def | 1 +
.../riscv/rvv/base/float-point-wredusum.c | 33 +++++++++++++++++++
4 files changed, 37 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index abf03bab0da..5ee7d3119db 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -2548,6 +2548,7 @@ static CONSTEXPR const freducop<UNSPEC_ORDERED, HAS_FRM> vfredosum_frm_obj;
static CONSTEXPR const reducop<SMAX> vfredmax_obj;
static CONSTEXPR const reducop<SMIN> vfredmin_obj;
static CONSTEXPR const widen_freducop<UNSPEC_UNORDERED> vfwredusum_obj;
+static CONSTEXPR const widen_freducop<UNSPEC_UNORDERED, HAS_FRM> vfwredusum_frm_obj;
static CONSTEXPR const widen_freducop<UNSPEC_ORDERED> vfwredosum_obj;
static CONSTEXPR const widen_freducop<UNSPEC_ORDERED, HAS_FRM> vfwredosum_frm_obj;
static CONSTEXPR const vmv vmv_x_obj;
@@ -2810,6 +2811,7 @@ BASE (vfredmin)
BASE (vfwredosum)
BASE (vfwredosum_frm)
BASE (vfwredusum)
+BASE (vfwredusum_frm)
BASE (vmv_x)
BASE (vmv_s)
BASE (vfmv_f)
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.h b/gcc/config/riscv/riscv-vector-builtins-bases.h
index c1bb164a712..69d4562091f 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.h
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.h
@@ -247,6 +247,7 @@ extern const function_base *const vfredmin;
extern const function_base *const vfwredosum;
extern const function_base *const vfwredosum_frm;
extern const function_base *const vfwredusum;
+extern const function_base *const vfwredusum_frm;
extern const function_base *const vmv_x;
extern const function_base *const vmv_s;
extern const function_base *const vfmv_f;
diff --git a/gcc/config/riscv/riscv-vector-builtins-functions.def b/gcc/config/riscv/riscv-vector-builtins-functions.def
index da1157f5a56..3ce06dc60b7 100644
--- a/gcc/config/riscv/riscv-vector-builtins-functions.def
+++ b/gcc/config/riscv/riscv-vector-builtins-functions.def
@@ -508,6 +508,7 @@ DEF_RVV_FUNCTION (vfwredosum, reduc_alu, no_mu_preds, wf_vs_ops)
DEF_RVV_FUNCTION (vfwredusum, reduc_alu, no_mu_preds, wf_vs_ops)
DEF_RVV_FUNCTION (vfwredosum_frm, reduc_alu_frm, no_mu_preds, wf_vs_ops)
+DEF_RVV_FUNCTION (vfwredusum_frm, reduc_alu_frm, no_mu_preds, wf_vs_ops)
/* 15. Vector Mask Instructions. */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c
new file mode 100644
index 00000000000..6c888c10c0d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c
@@ -0,0 +1,33 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3 -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vfloat64m1_t
+test_riscv_vfwredusum_vs_f32m1_f64m1_rm (vfloat32m1_t op1, vfloat64m1_t op2,
+ size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_rm (op1, op2, 0, vl);
+}
+
+vfloat64m1_t
+test_vfwredusum_vs_f32m1_f64m1_rm_m (vbool32_t mask, vfloat32m1_t op1,
+ vfloat64m1_t op2, size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_rm_m (mask, op1, op2, 1, vl);
+}
+
+vfloat64m1_t
+test_riscv_vfwredusum_vs_f32m1_f64m1 (vfloat32m1_t op1, vfloat64m1_t op2,
+ size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1 (op1, op2, vl);
+}
+
+vfloat64m1_t
+test_vfwredusum_vs_f32m1_f64m1_m (vbool32_t mask, vfloat32m1_t op1,
+ vfloat64m1_t op2, size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_m (mask, op1, op2, vl);
+}
+
+/* { dg-final { scan-assembler-times {vfwredusum\.vs\s+v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {frrm\s+[axs][0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {fsrm\s+[axs][0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {fsrmi\s+[01234]} 2 } } */
--
2.34.1
To double confirm, you mean this declaration ?
+static CONSTEXPR const widen_freducop<UNSPEC_UNORDERED, HAS_FRM> vfwredusum_frm_obj;
Pan
From: juzhe.zhong@rivai.ai <juzhe.zhong@rivai.ai>
Sent: Monday, August 21, 2023 2:40 PM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>
Cc: Li, Pan2 <pan2.li@intel.com>; Wang, Yanzhang <yanzhang.wang@intel.com>; kito.cheng <kito.cheng@gmail.com>
Subject: Re: [PATCH v1] RISC-V: Support RVV VFWREDUSUM.VS rounding mode intrinsic API
Why does this patch not have HAS_FRM?
Yes. I wonder why some floating-point rounding mode has HAS_FRM, some doesn't have?
juzhe.zhong@rivai.ai
From: Li, Pan2
Date: 2023-08-21 15:10
To: juzhe.zhong@rivai.ai; gcc-patches
CC: Wang, Yanzhang; kito.cheng
Subject: RE: [PATCH v1] RISC-V: Support RVV VFWREDUSUM.VS rounding mode intrinsic API
To double confirm, you mean this declaration ?
+static CONSTEXPR const widen_freducop<UNSPEC_UNORDERED, HAS_FRM> vfwredusum_frm_obj;
Pan
From: juzhe.zhong@rivai.ai <juzhe.zhong@rivai.ai>
Sent: Monday, August 21, 2023 2:40 PM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>
Cc: Li, Pan2 <pan2.li@intel.com>; Wang, Yanzhang <yanzhang.wang@intel.com>; kito.cheng <kito.cheng@gmail.com>
Subject: Re: [PATCH v1] RISC-V: Support RVV VFWREDUSUM.VS rounding mode intrinsic API
Why does this patch not have HAS_FRM?
juzhe.zhong@rivai.ai
From: pan2.li
Date: 2023-08-17 16:05
To: gcc-patches
CC: juzhe.zhong; pan2.li; yanzhang.wang; kito.cheng
Subject: [PATCH v1] RISC-V: Support RVV VFWREDUSUM.VS rounding mode intrinsic API
From: Pan Li <pan2.li@intel.com>
This patch would like to support the rounding mode API for the
VFWREDUSUM.VS as the below samples
* __riscv_vfwredusum_vs_f32m1_f64m1_rm
* __riscv_vfwredusum_vs_f32m1_f64m1_rm_m
Signed-off-by: Pan Li <pan2.li@intel.com>
gcc/ChangeLog:
* config/riscv/riscv-vector-builtins-bases.cc
(vfwredusum_frm_obj): New declaration.
(BASE): Ditto.
* config/riscv/riscv-vector-builtins-bases.h: Ditto.
* config/riscv/riscv-vector-builtins-functions.def
(vfwredusum_frm): New intrinsic function def.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/float-point-wredusum.c: New test.
---
.../riscv/riscv-vector-builtins-bases.cc | 2 ++
.../riscv/riscv-vector-builtins-bases.h | 1 +
.../riscv/riscv-vector-builtins-functions.def | 1 +
.../riscv/rvv/base/float-point-wredusum.c | 33 +++++++++++++++++++
4 files changed, 37 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index abf03bab0da..5ee7d3119db 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -2548,6 +2548,7 @@ static CONSTEXPR const freducop<UNSPEC_ORDERED, HAS_FRM> vfredosum_frm_obj;
static CONSTEXPR const reducop<SMAX> vfredmax_obj;
static CONSTEXPR const reducop<SMIN> vfredmin_obj;
static CONSTEXPR const widen_freducop<UNSPEC_UNORDERED> vfwredusum_obj;
+static CONSTEXPR const widen_freducop<UNSPEC_UNORDERED, HAS_FRM> vfwredusum_frm_obj;
static CONSTEXPR const widen_freducop<UNSPEC_ORDERED> vfwredosum_obj;
static CONSTEXPR const widen_freducop<UNSPEC_ORDERED, HAS_FRM> vfwredosum_frm_obj;
static CONSTEXPR const vmv vmv_x_obj;
@@ -2810,6 +2811,7 @@ BASE (vfredmin)
BASE (vfwredosum)
BASE (vfwredosum_frm)
BASE (vfwredusum)
+BASE (vfwredusum_frm)
BASE (vmv_x)
BASE (vmv_s)
BASE (vfmv_f)
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.h b/gcc/config/riscv/riscv-vector-builtins-bases.h
index c1bb164a712..69d4562091f 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.h
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.h
@@ -247,6 +247,7 @@ extern const function_base *const vfredmin;
extern const function_base *const vfwredosum;
extern const function_base *const vfwredosum_frm;
extern const function_base *const vfwredusum;
+extern const function_base *const vfwredusum_frm;
extern const function_base *const vmv_x;
extern const function_base *const vmv_s;
extern const function_base *const vfmv_f;
diff --git a/gcc/config/riscv/riscv-vector-builtins-functions.def b/gcc/config/riscv/riscv-vector-builtins-functions.def
index da1157f5a56..3ce06dc60b7 100644
--- a/gcc/config/riscv/riscv-vector-builtins-functions.def
+++ b/gcc/config/riscv/riscv-vector-builtins-functions.def
@@ -508,6 +508,7 @@ DEF_RVV_FUNCTION (vfwredosum, reduc_alu, no_mu_preds, wf_vs_ops)
DEF_RVV_FUNCTION (vfwredusum, reduc_alu, no_mu_preds, wf_vs_ops)
DEF_RVV_FUNCTION (vfwredosum_frm, reduc_alu_frm, no_mu_preds, wf_vs_ops)
+DEF_RVV_FUNCTION (vfwredusum_frm, reduc_alu_frm, no_mu_preds, wf_vs_ops)
/* 15. Vector Mask Instructions. */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c
new file mode 100644
index 00000000000..6c888c10c0d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-wredusum.c
@@ -0,0 +1,33 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3 -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vfloat64m1_t
+test_riscv_vfwredusum_vs_f32m1_f64m1_rm (vfloat32m1_t op1, vfloat64m1_t op2,
+ size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_rm (op1, op2, 0, vl);
+}
+
+vfloat64m1_t
+test_vfwredusum_vs_f32m1_f64m1_rm_m (vbool32_t mask, vfloat32m1_t op1,
+ vfloat64m1_t op2, size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_rm_m (mask, op1, op2, 1, vl);
+}
+
+vfloat64m1_t
+test_riscv_vfwredusum_vs_f32m1_f64m1 (vfloat32m1_t op1, vfloat64m1_t op2,
+ size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1 (op1, op2, vl);
+}
+
+vfloat64m1_t
+test_vfwredusum_vs_f32m1_f64m1_m (vbool32_t mask, vfloat32m1_t op1,
+ vfloat64m1_t op2, size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_m (mask, op1, op2, vl);
+}
+
+/* { dg-final { scan-assembler-times {vfwredusum\.vs\s+v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {frrm\s+[axs][0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {fsrm\s+[axs][0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {fsrmi\s+[01234]} 2 } } */
--
2.34.1
By design, HAS_FRM must be present if this insn honor FRM.
For example, if one insn don't honor FRM, there should be only one declaration as below.
static CONSTEXPR const binop<SMAX> vfmax_obj;
But if one insn honors FRM, there will be 2 declaration as below for code reuse.
static CONSTEXPR const binop<MINUS> vfsub_obj;
static CONSTEXPR const binop_frm<PLUS> vfadd_frm_obj;
Pan
From: juzhe.zhong@rivai.ai <juzhe.zhong@rivai.ai>
Sent: Monday, August 21, 2023 4:48 PM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>
Cc: Wang, Yanzhang <yanzhang.wang@intel.com>; kito.cheng <kito.cheng@gmail.com>
Subject: Re: RE: [PATCH v1] RISC-V: Support RVV VFWREDUSUM.VS rounding mode intrinsic API
Yes. I wonder why some floating-point rounding mode has HAS_FRM, some doesn't have?
On 8/17/23 02:05, Pan Li via Gcc-patches wrote:
> From: Pan Li <pan2.li@intel.com>
>
> This patch would like to support the rounding mode API for the
> VFWREDUSUM.VS as the below samples
>
> * __riscv_vfwredusum_vs_f32m1_f64m1_rm
> * __riscv_vfwredusum_vs_f32m1_f64m1_rm_m
>
> Signed-off-by: Pan Li <pan2.li@intel.com>
>
> gcc/ChangeLog:
>
> * config/riscv/riscv-vector-builtins-bases.cc
> (vfwredusum_frm_obj): New declaration.
> (BASE): Ditto.
> * config/riscv/riscv-vector-builtins-bases.h: Ditto.
> * config/riscv/riscv-vector-builtins-functions.def
> (vfwredusum_frm): New intrinsic function def.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/riscv/rvv/base/float-point-wredusum.c: New test.
OK
jeff
Committed, thanks Jeff.
Pan
-----Original Message-----
From: Jeff Law <jeffreyalaw@gmail.com>
Sent: Monday, August 21, 2023 11:06 PM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches@gcc.gnu.org
Cc: juzhe.zhong@rivai.ai; Wang, Yanzhang <yanzhang.wang@intel.com>; kito.cheng@gmail.com
Subject: Re: [PATCH v1] RISC-V: Support RVV VFWREDUSUM.VS rounding mode intrinsic API
On 8/17/23 02:05, Pan Li via Gcc-patches wrote:
> From: Pan Li <pan2.li@intel.com>
>
> This patch would like to support the rounding mode API for the
> VFWREDUSUM.VS as the below samples
>
> * __riscv_vfwredusum_vs_f32m1_f64m1_rm
> * __riscv_vfwredusum_vs_f32m1_f64m1_rm_m
>
> Signed-off-by: Pan Li <pan2.li@intel.com>
>
> gcc/ChangeLog:
>
> * config/riscv/riscv-vector-builtins-bases.cc
> (vfwredusum_frm_obj): New declaration.
> (BASE): Ditto.
> * config/riscv/riscv-vector-builtins-bases.h: Ditto.
> * config/riscv/riscv-vector-builtins-functions.def
> (vfwredusum_frm): New intrinsic function def.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/riscv/rvv/base/float-point-wredusum.c: New test.
OK
jeff
@@ -2548,6 +2548,7 @@ static CONSTEXPR const freducop<UNSPEC_ORDERED, HAS_FRM> vfredosum_frm_obj;
static CONSTEXPR const reducop<SMAX> vfredmax_obj;
static CONSTEXPR const reducop<SMIN> vfredmin_obj;
static CONSTEXPR const widen_freducop<UNSPEC_UNORDERED> vfwredusum_obj;
+static CONSTEXPR const widen_freducop<UNSPEC_UNORDERED, HAS_FRM> vfwredusum_frm_obj;
static CONSTEXPR const widen_freducop<UNSPEC_ORDERED> vfwredosum_obj;
static CONSTEXPR const widen_freducop<UNSPEC_ORDERED, HAS_FRM> vfwredosum_frm_obj;
static CONSTEXPR const vmv vmv_x_obj;
@@ -2810,6 +2811,7 @@ BASE (vfredmin)
BASE (vfwredosum)
BASE (vfwredosum_frm)
BASE (vfwredusum)
+BASE (vfwredusum_frm)
BASE (vmv_x)
BASE (vmv_s)
BASE (vfmv_f)
@@ -247,6 +247,7 @@ extern const function_base *const vfredmin;
extern const function_base *const vfwredosum;
extern const function_base *const vfwredosum_frm;
extern const function_base *const vfwredusum;
+extern const function_base *const vfwredusum_frm;
extern const function_base *const vmv_x;
extern const function_base *const vmv_s;
extern const function_base *const vfmv_f;
@@ -508,6 +508,7 @@ DEF_RVV_FUNCTION (vfwredosum, reduc_alu, no_mu_preds, wf_vs_ops)
DEF_RVV_FUNCTION (vfwredusum, reduc_alu, no_mu_preds, wf_vs_ops)
DEF_RVV_FUNCTION (vfwredosum_frm, reduc_alu_frm, no_mu_preds, wf_vs_ops)
+DEF_RVV_FUNCTION (vfwredusum_frm, reduc_alu_frm, no_mu_preds, wf_vs_ops)
/* 15. Vector Mask Instructions. */
new file mode 100644
@@ -0,0 +1,33 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3 -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vfloat64m1_t
+test_riscv_vfwredusum_vs_f32m1_f64m1_rm (vfloat32m1_t op1, vfloat64m1_t op2,
+ size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_rm (op1, op2, 0, vl);
+}
+
+vfloat64m1_t
+test_vfwredusum_vs_f32m1_f64m1_rm_m (vbool32_t mask, vfloat32m1_t op1,
+ vfloat64m1_t op2, size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_rm_m (mask, op1, op2, 1, vl);
+}
+
+vfloat64m1_t
+test_riscv_vfwredusum_vs_f32m1_f64m1 (vfloat32m1_t op1, vfloat64m1_t op2,
+ size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1 (op1, op2, vl);
+}
+
+vfloat64m1_t
+test_vfwredusum_vs_f32m1_f64m1_m (vbool32_t mask, vfloat32m1_t op1,
+ vfloat64m1_t op2, size_t vl) {
+ return __riscv_vfwredusum_vs_f32m1_f64m1_m (mask, op1, op2, vl);
+}
+
+/* { dg-final { scan-assembler-times {vfwredusum\.vs\s+v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {frrm\s+[axs][0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {fsrm\s+[axs][0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {fsrmi\s+[01234]} 2 } } */