[v1] RISC-V: Bugfix for RVV integer reduction in ZVE32/64.
Checks
Commit Message
From: Pan Li <pan2.li@intel.com>
The rvv integer reduction has 3 different patterns for zve128+, zve64
and zve32. They take the same iterator with different attributions.
However, we need the generated function code_for_reduc (code, mode1, mode2).
The implementation of code_for_reduc may look like below.
code_for_reduc (code, mode1, mode2)
{
if (code == max && mode1 == VNx1QI && mode2 == VNx1QI)
return CODE_FOR_pred_reduc_maxvnx1qivnx16qi; // ZVE128+
if (code == max && mode1 == VNx1QI && mode2 == VNx1QI)
return CODE_FOR_pred_reduc_maxvnx1qivnx8qi; // ZVE64
if (code == max && mode1 == VNx1QI && mode2 == VNx1QI)
return CODE_FOR_pred_reduc_maxvnx1qivnx4qi; // ZVE32
}
Thus there will be a problem here. For example zve32, we will have
code_for_reduc (max, VNx1QI, VNx1QI) which will return the code of
the ZVE128+ instead of the ZVE32 logically.
This patch will merge the 3 patterns into one pattern, and pass both the
input_vector and the ret_vector of code_for_reduc. For example, ZVE32 will be
code_for_reduc (max, VNx1Q1, VNx4QI), then the correct code of ZVE32
will be returned as expectation.
Signed-off-by: Pan Li <pan2.li@intel.com>
Co-Authored by: Juzhe-Zhong <juzhe.zhong@rivai.ai>
PR 110265
gcc/ChangeLog:
PR target/110265
* config/riscv/riscv-vector-builtins-bases.cc: Add ret_mode for
integer reduction expand.
* config/riscv/vector-iterators.md: Add VQI, VHI, VSI and VDI,
and the LMUL1 attr respectively.
* config/riscv/vector.md.
(@pred_reduc_<reduc><mode><vlmul1>): Removed.
(@pred_reduc_<reduc><mode><vlmul1_zve64>): Likewise.
(@pred_reduc_<reduc><mode><vlmul1_zve32>): Likewise.
(@pred_reduc_<reduc><VQI:mode><VQI_LMUL1:mode>): New pattern.
(@pred_reduc_<reduc><VHI:mode><VHI_LMUL1:mode>): Likewise.
(@pred_reduc_<reduc><VSI:mode><VSI_LMUL1:mode>): Likewise.
(@pred_reduc_<reduc><VDI:mode><VDI_LMUL1:mode>): Likewise.
* machmode.h (VECTOR_FLOAT_MODE_P): New macro.
gcc/testsuite/ChangeLog:
PR target/110265
* gcc.target/riscv/rvv/base/pr110265-1.c: New test.
* gcc.target/riscv/rvv/base/pr110265-1.h: New test.
* gcc.target/riscv/rvv/base/pr110265-2.c: New test.
* gcc.target/riscv/rvv/base/pr110265-2.h: New test.
* gcc.target/riscv/rvv/base/pr110265-3.c: New test.
---
.../riscv/riscv-vector-builtins-bases.cc | 13 +-
gcc/config/riscv/vector-iterators.md | 61 +++++
gcc/config/riscv/vector.md | 208 +++++++++++++-----
gcc/machmode.h | 4 +
.../gcc.target/riscv/rvv/base/pr110265-1.c | 13 ++
.../gcc.target/riscv/rvv/base/pr110265-1.h | 65 ++++++
.../gcc.target/riscv/rvv/base/pr110265-2.c | 14 ++
.../gcc.target/riscv/rvv/base/pr110265-2.h | 57 +++++
.../gcc.target/riscv/rvv/base/pr110265-3.c | 14 ++
9 files changed, 389 insertions(+), 60 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.h
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.h
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-3.c
Comments
+/* Nonzero if MODE is a vector float mode. */
+#define VECTOR_FLOAT_MODE_P(MODE) \
+ (GET_MODE_CLASS (MODE) == MODE_VECTOR_FLOAT)
Why you add this?
Remove it. Otherwise, LGTM.
juzhe.zhong@rivai.ai
From: pan2.li
Date: 2023-06-16 15:28
To: gcc-patches
CC: juzhe.zhong; rdapp.gcc; jeffreyalaw; pan2.li; yanzhang.wang; kito.cheng
Subject: [PATCH v1] RISC-V: Bugfix for RVV integer reduction in ZVE32/64.
From: Pan Li <pan2.li@intel.com>
The rvv integer reduction has 3 different patterns for zve128+, zve64
and zve32. They take the same iterator with different attributions.
However, we need the generated function code_for_reduc (code, mode1, mode2).
The implementation of code_for_reduc may look like below.
code_for_reduc (code, mode1, mode2)
{
if (code == max && mode1 == VNx1QI && mode2 == VNx1QI)
return CODE_FOR_pred_reduc_maxvnx1qivnx16qi; // ZVE128+
if (code == max && mode1 == VNx1QI && mode2 == VNx1QI)
return CODE_FOR_pred_reduc_maxvnx1qivnx8qi; // ZVE64
if (code == max && mode1 == VNx1QI && mode2 == VNx1QI)
return CODE_FOR_pred_reduc_maxvnx1qivnx4qi; // ZVE32
}
Thus there will be a problem here. For example zve32, we will have
code_for_reduc (max, VNx1QI, VNx1QI) which will return the code of
the ZVE128+ instead of the ZVE32 logically.
This patch will merge the 3 patterns into one pattern, and pass both the
input_vector and the ret_vector of code_for_reduc. For example, ZVE32 will be
code_for_reduc (max, VNx1Q1, VNx4QI), then the correct code of ZVE32
will be returned as expectation.
Signed-off-by: Pan Li <pan2.li@intel.com>
Co-Authored by: Juzhe-Zhong <juzhe.zhong@rivai.ai>
PR 110265
gcc/ChangeLog:
PR target/110265
* config/riscv/riscv-vector-builtins-bases.cc: Add ret_mode for
integer reduction expand.
* config/riscv/vector-iterators.md: Add VQI, VHI, VSI and VDI,
and the LMUL1 attr respectively.
* config/riscv/vector.md.
(@pred_reduc_<reduc><mode><vlmul1>): Removed.
(@pred_reduc_<reduc><mode><vlmul1_zve64>): Likewise.
(@pred_reduc_<reduc><mode><vlmul1_zve32>): Likewise.
(@pred_reduc_<reduc><VQI:mode><VQI_LMUL1:mode>): New pattern.
(@pred_reduc_<reduc><VHI:mode><VHI_LMUL1:mode>): Likewise.
(@pred_reduc_<reduc><VSI:mode><VSI_LMUL1:mode>): Likewise.
(@pred_reduc_<reduc><VDI:mode><VDI_LMUL1:mode>): Likewise.
* machmode.h (VECTOR_FLOAT_MODE_P): New macro.
gcc/testsuite/ChangeLog:
PR target/110265
* gcc.target/riscv/rvv/base/pr110265-1.c: New test.
* gcc.target/riscv/rvv/base/pr110265-1.h: New test.
* gcc.target/riscv/rvv/base/pr110265-2.c: New test.
* gcc.target/riscv/rvv/base/pr110265-2.h: New test.
* gcc.target/riscv/rvv/base/pr110265-3.c: New test.
---
.../riscv/riscv-vector-builtins-bases.cc | 13 +-
gcc/config/riscv/vector-iterators.md | 61 +++++
gcc/config/riscv/vector.md | 208 +++++++++++++-----
gcc/machmode.h | 4 +
.../gcc.target/riscv/rvv/base/pr110265-1.c | 13 ++
.../gcc.target/riscv/rvv/base/pr110265-1.h | 65 ++++++
.../gcc.target/riscv/rvv/base/pr110265-2.c | 14 ++
.../gcc.target/riscv/rvv/base/pr110265-2.h | 57 +++++
.../gcc.target/riscv/rvv/base/pr110265-3.c | 14 ++
9 files changed, 389 insertions(+), 60 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.h
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.h
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-3.c
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index 87a684dd127..a77933d60d5 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -1396,8 +1396,17 @@ public:
rtx expand (function_expander &e) const override
{
- return e.use_exact_insn (
- code_for_pred_reduc (CODE, e.vector_mode (), e.vector_mode ()));
+ machine_mode mode = e.vector_mode ();
+ machine_mode ret_mode = e.ret_mode ();
+
+ /* TODO: we will use ret_mode after all types of PR110265 are addressed. */
+ if (VECTOR_FLOAT_MODE_P (mode)
+ || GET_MODE_INNER (mode) != GET_MODE_INNER (ret_mode))
+ return e.use_exact_insn (
+ code_for_pred_reduc (CODE, e.vector_mode (), e.vector_mode ()));
+ else
+ return e.use_exact_insn (
+ code_for_pred_reduc (CODE, e.vector_mode (), e.ret_mode ()));
}
};
diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md
index 8c71c9e22cc..e2c8ade98eb 100644
--- a/gcc/config/riscv/vector-iterators.md
+++ b/gcc/config/riscv/vector-iterators.md
@@ -929,6 +929,67 @@ (define_mode_iterator V64T [
(VNx2x64QI "TARGET_MIN_VLEN >= 128")
])
+(define_mode_iterator VQI [
+ (VNx1QI "TARGET_MIN_VLEN < 128")
+ VNx2QI
+ VNx4QI
+ VNx8QI
+ VNx16QI
+ VNx32QI
+ (VNx64QI "TARGET_MIN_VLEN > 32")
+ (VNx128QI "TARGET_MIN_VLEN >= 128")
+])
+
+(define_mode_iterator VHI [
+ (VNx1HI "TARGET_MIN_VLEN < 128")
+ VNx2HI
+ VNx4HI
+ VNx8HI
+ VNx16HI
+ (VNx32HI "TARGET_MIN_VLEN > 32")
+ (VNx64HI "TARGET_MIN_VLEN >= 128")
+])
+
+(define_mode_iterator VSI [
+ (VNx1SI "TARGET_MIN_VLEN < 128")
+ VNx2SI
+ VNx4SI
+ VNx8SI
+ (VNx16SI "TARGET_MIN_VLEN > 32")
+ (VNx32SI "TARGET_MIN_VLEN >= 128")
+])
+
+(define_mode_iterator VDI [
+ (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128")
+ (VNx2DI "TARGET_VECTOR_ELEN_64")
+ (VNx4DI "TARGET_VECTOR_ELEN_64")
+ (VNx8DI "TARGET_VECTOR_ELEN_64")
+ (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128")
+])
+
+(define_mode_iterator VQI_LMUL1 [
+ (VNx16QI "TARGET_MIN_VLEN >= 128")
+ (VNx8QI "TARGET_MIN_VLEN == 64")
+ (VNx4QI "TARGET_MIN_VLEN == 32")
+])
+
+(define_mode_iterator VHI_LMUL1 [
+ (VNx8HI "TARGET_MIN_VLEN >= 128")
+ (VNx4HI "TARGET_MIN_VLEN == 64")
+ (VNx2HI "TARGET_MIN_VLEN == 32")
+])
+
+(define_mode_iterator VSI_LMUL1 [
+ (VNx4SI "TARGET_MIN_VLEN >= 128")
+ (VNx2SI "TARGET_MIN_VLEN == 64")
+ (VNx1SI "TARGET_MIN_VLEN == 32")
+])
+
+(define_mode_iterator VDI_LMUL1 [
+ (VNx2DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128")
+ (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN == 64")
+])
+
(define_mode_attr VLMULX2 [
(VNx1QI "VNx2QI") (VNx2QI "VNx4QI") (VNx4QI "VNx8QI") (VNx8QI "VNx16QI") (VNx16QI "VNx32QI") (VNx32QI "VNx64QI") (VNx64QI "VNx128QI")
(VNx1HI "VNx2HI") (VNx2HI "VNx4HI") (VNx4HI "VNx8HI") (VNx8HI "VNx16HI") (VNx16HI "VNx32HI") (VNx32HI "VNx64HI")
diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md
index 1d1847bd85a..d396e278503 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -7244,76 +7244,168 @@ (define_insn "@pred_rod_trunc<mode>"
;; -------------------------------------------------------------------------------
;; For reduction operations, we should have seperate patterns for
-;; TARGET_MIN_VLEN == 32 and TARGET_MIN_VLEN > 32.
+;; different types. For each type, we will cover MIN_VLEN == 32, MIN_VLEN == 64
+;; and the MIN_VLEN >= 128 from the well defined iterators.
;; Since reduction need LMUL = 1 scalar operand as the input operand
;; and they are different.
;; For example, The LMUL = 1 corresponding mode of VNx16QImode is VNx4QImode
;; for -march=rv*zve32* wheras VNx8QImode for -march=rv*zve64*
-(define_insn "@pred_reduc_<reduc><mode><vlmul1>"
- [(set (match_operand:<VLMUL1> 0 "register_operand" "=vr, vr")
- (unspec:<VLMUL1>
- [(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 5 "vector_length_operand" " rK, rK")
- (match_operand 6 "const_int_operand" " i, i")
- (match_operand 7 "const_int_operand" " i, i")
+
+;; Integer Reduction for QI
+(define_insn "@pred_reduc_<reduc><VQI:mode><VQI_LMUL1:mode>"
+ [
+ (set
+ (match_operand:VQI_LMUL1 0 "register_operand" "=vr, vr")
+ (unspec:VQI_LMUL1
+ [
+ (unspec:<VQI:VM>
+ [
+ (match_operand:<VQI:VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK")
+ (match_operand 6 "const_int_operand" " i, i")
+ (match_operand 7 "const_int_operand" " i, i")
(reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (any_reduc:VI
- (vec_duplicate:VI
- (vec_select:<VEL>
- (match_operand:<VLMUL1> 4 "register_operand" " vr, vr")
- (parallel [(const_int 0)])))
- (match_operand:VI 3 "register_operand" " vr, vr"))
- (match_operand:<VLMUL1> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC))]
- "TARGET_VECTOR && TARGET_MIN_VLEN >= 128"
+ (reg:SI VTYPE_REGNUM)
+ ] UNSPEC_VPREDICATE
+ )
+ (any_reduc:VQI
+ (vec_duplicate:VQI
+ (vec_select:<VEL>
+ (match_operand:VQI_LMUL1 4 "register_operand" " vr, vr")
+ (parallel [(const_int 0)])
+ )
+ )
+ (match_operand:VQI 3 "register_operand" " vr, vr")
+ )
+ (match_operand:VQI_LMUL1 2 "vector_merge_operand" " vu, 0")
+ ] UNSPEC_REDUC
+ )
+ )
+ ]
+ "TARGET_VECTOR"
"vred<reduc>.vs\t%0,%3,%4%p1"
- [(set_attr "type" "vired")
- (set_attr "mode" "<MODE>")])
+ [
+ (set_attr "type" "vired")
+ (set_attr "mode" "<VQI:MODE>")
+ ]
+)
-(define_insn "@pred_reduc_<reduc><mode><vlmul1_zve64>"
- [(set (match_operand:<VLMUL1_ZVE64> 0 "register_operand" "=vr, vr")
- (unspec:<VLMUL1_ZVE64>
- [(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 5 "vector_length_operand" " rK, rK")
- (match_operand 6 "const_int_operand" " i, i")
- (match_operand 7 "const_int_operand" " i, i")
+;; Integer Reduction for HI
+(define_insn "@pred_reduc_<reduc><VHI:mode><VHI_LMUL1:mode>"
+ [
+ (set
+ (match_operand:VHI_LMUL1 0 "register_operand" "=vr, vr")
+ (unspec:VHI_LMUL1
+ [
+ (unspec:<VHI:VM>
+ [
+ (match_operand:<VHI:VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK")
+ (match_operand 6 "const_int_operand" " i, i")
+ (match_operand 7 "const_int_operand" " i, i")
(reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (any_reduc:VI_ZVE64
- (vec_duplicate:VI_ZVE64
- (vec_select:<VEL>
- (match_operand:<VLMUL1_ZVE64> 4 "register_operand" " vr, vr")
- (parallel [(const_int 0)])))
- (match_operand:VI_ZVE64 3 "register_operand" " vr, vr"))
- (match_operand:<VLMUL1_ZVE64> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC))]
- "TARGET_VECTOR && TARGET_MIN_VLEN == 64"
+ (reg:SI VTYPE_REGNUM)
+ ] UNSPEC_VPREDICATE
+ )
+ (any_reduc:VHI
+ (vec_duplicate:VHI
+ (vec_select:<VEL>
+ (match_operand:VHI_LMUL1 4 "register_operand" " vr, vr")
+ (parallel [(const_int 0)])
+ )
+ )
+ (match_operand:VHI 3 "register_operand" " vr, vr")
+ )
+ (match_operand:VHI_LMUL1 2 "vector_merge_operand" " vu, 0")
+ ] UNSPEC_REDUC
+ )
+ )
+ ]
+ "TARGET_VECTOR"
"vred<reduc>.vs\t%0,%3,%4%p1"
- [(set_attr "type" "vired")
- (set_attr "mode" "<MODE>")])
+ [
+ (set_attr "type" "vired")
+ (set_attr "mode" "<VHI:MODE>")
+ ]
+)
-(define_insn "@pred_reduc_<reduc><mode><vlmul1_zve32>"
- [(set (match_operand:<VLMUL1_ZVE32> 0 "register_operand" "=vd, vd, vr, vr")
- (unspec:<VLMUL1_ZVE32>
- [(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" " vm, vm,Wc1,Wc1")
- (match_operand 5 "vector_length_operand" " rK, rK, rK, rK")
- (match_operand 6 "const_int_operand" " i, i, i, i")
- (match_operand 7 "const_int_operand" " i, i, i, i")
+;; Integer Reduction for SI
+(define_insn "@pred_reduc_<reduc><VSI:mode><VSI_LMUL1:mode>"
+ [
+ (set
+ (match_operand:VSI_LMUL1 0 "register_operand" "=vr, vr")
+ (unspec:VSI_LMUL1
+ [
+ (unspec:<VSI:VM>
+ [
+ (match_operand:<VSI:VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK")
+ (match_operand 6 "const_int_operand" " i, i")
+ (match_operand 7 "const_int_operand" " i, i")
(reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (any_reduc:VI_ZVE32
- (vec_duplicate:VI_ZVE32
- (vec_select:<VEL>
- (match_operand:<VLMUL1_ZVE32> 4 "register_operand" " vr, vr, vr, vr")
- (parallel [(const_int 0)])))
- (match_operand:VI_ZVE32 3 "register_operand" " vr, vr, vr, vr"))
- (match_operand:<VLMUL1_ZVE32> 2 "vector_merge_operand" " vu, 0, vu, 0")] UNSPEC_REDUC))]
- "TARGET_VECTOR && TARGET_MIN_VLEN == 32"
+ (reg:SI VTYPE_REGNUM)
+ ] UNSPEC_VPREDICATE
+ )
+ (any_reduc:VSI
+ (vec_duplicate:VSI
+ (vec_select:<VEL>
+ (match_operand:VSI_LMUL1 4 "register_operand" " vr, vr")
+ (parallel [(const_int 0)])
+ )
+ )
+ (match_operand:VSI 3 "register_operand" " vr, vr")
+ )
+ (match_operand:VSI_LMUL1 2 "vector_merge_operand" " vu, 0")
+ ] UNSPEC_REDUC
+ )
+ )
+ ]
+ "TARGET_VECTOR"
"vred<reduc>.vs\t%0,%3,%4%p1"
- [(set_attr "type" "vired")
- (set_attr "mode" "<MODE>")])
+ [
+ (set_attr "type" "vired")
+ (set_attr "mode" "<VSI:MODE>")
+ ]
+)
+
+;; Integer Reduction for DI
+(define_insn "@pred_reduc_<reduc><VDI:mode><VDI_LMUL1:mode>"
+ [
+ (set
+ (match_operand:VDI_LMUL1 0 "register_operand" "=vr, vr")
+ (unspec:VDI_LMUL1
+ [
+ (unspec:<VDI:VM>
+ [
+ (match_operand:<VDI:VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK")
+ (match_operand 6 "const_int_operand" " i, i")
+ (match_operand 7 "const_int_operand" " i, i")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)
+ ] UNSPEC_VPREDICATE
+ )
+ (any_reduc:VDI
+ (vec_duplicate:VDI
+ (vec_select:<VEL>
+ (match_operand:VDI_LMUL1 4 "register_operand" " vr, vr")
+ (parallel [(const_int 0)])
+ )
+ )
+ (match_operand:VDI 3 "register_operand" " vr, vr")
+ )
+ (match_operand:VDI_LMUL1 2 "vector_merge_operand" " vu, 0")
+ ] UNSPEC_REDUC
+ )
+ )
+ ]
+ "TARGET_VECTOR"
+ "vred<reduc>.vs\t%0,%3,%4%p1"
+ [
+ (set_attr "type" "vired")
+ (set_attr "mode" "<VDI:MODE>")
+ ]
+)
(define_insn "@pred_widen_reduc_plus<v_su><mode><vwlmul1>"
[(set (match_operand:<VWLMUL1> 0 "register_operand" "=&vr, &vr")
diff --git a/gcc/machmode.h b/gcc/machmode.h
index a22df60dc20..8ecfc2a656e 100644
--- a/gcc/machmode.h
+++ b/gcc/machmode.h
@@ -134,6 +134,10 @@ extern const unsigned char mode_class[NUM_MACHINE_MODES];
|| GET_MODE_CLASS (MODE) == MODE_VECTOR_ACCUM \
|| GET_MODE_CLASS (MODE) == MODE_VECTOR_UACCUM)
+/* Nonzero if MODE is a vector float mode. */
+#define VECTOR_FLOAT_MODE_P(MODE) \
+ (GET_MODE_CLASS (MODE) == MODE_VECTOR_FLOAT) \
+
/* Nonzero if MODE is a scalar integral mode. */
#define SCALAR_INT_MODE_P(MODE) \
(GET_MODE_CLASS (MODE) == MODE_INT \
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.c
new file mode 100644
index 00000000000..2e4aeb5b90b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zve32f -mabi=ilp32f -O3 -Wno-psabi" } */
+
+#include "pr110265-1.h"
+
+/* { dg-final { scan-assembler-times {vredand\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredmax\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredmaxu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredmin\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredminu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredsum\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredxor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.h b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.h
new file mode 100644
index 00000000000..ade44cc27ea
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-1.h
@@ -0,0 +1,65 @@
+#include "riscv_vector.h"
+
+vint8m1_t test_vredand_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredand_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredand_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredand_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredmax_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredmax_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vint32m1_t test_vredmax_vs_i32m8_i32m1(vint32m8_t vector, vint32m1_t scalar, size_t vl) {
+ return __riscv_vredmax_vs_i32m8_i32m1(vector, scalar, vl);
+}
+
+vuint8m1_t test_vredmaxu_vs_u8mf4_u8m1(vuint8mf4_t vector, vuint8m1_t scalar, size_t vl) {
+ return __riscv_vredmaxu_vs_u8mf4_u8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredmaxu_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredmaxu_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredmin_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredmin_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vint32m1_t test_vredmin_vs_i32m8_i32m1(vint32m8_t vector, vint32m1_t scalar, size_t vl) {
+ return __riscv_vredmin_vs_i32m8_i32m1(vector, scalar, vl);
+}
+
+vuint8m1_t test_vredminu_vs_u8mf4_u8m1(vuint8mf4_t vector, vuint8m1_t scalar, size_t vl) {
+ return __riscv_vredminu_vs_u8mf4_u8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredminu_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredminu_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredor_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredor_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredor_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredor_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredsum_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredsum_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredsum_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredsum_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredxor_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredxor_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredxor_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredxor_vs_u32m8_u32m1(vector, scalar, vl);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.c
new file mode 100644
index 00000000000..7454c1cc918
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zve64d -mabi=ilp32d -O3 -Wno-psabi" } */
+
+#include "pr110265-1.h"
+#include "pr110265-2.h"
+
+/* { dg-final { scan-assembler-times {vredand\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredmax\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vredmaxu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredmin\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vredminu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredsum\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredxor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.h b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.h
new file mode 100644
index 00000000000..6a7e14e51f8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-2.h
@@ -0,0 +1,57 @@
+#include "riscv_vector.h"
+
+vint8m1_t test_vredand_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredand_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredmax_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredmax_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vuint8m1_t test_vredmaxu_vs_u8mf8_u8m1(vuint8mf8_t vector, vuint8m1_t scalar, size_t vl) {
+ return __riscv_vredmaxu_vs_u8mf8_u8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredmin_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredmin_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vuint8m1_t test_vredminu_vs_u8mf8_u8m1(vuint8mf8_t vector, vuint8m1_t scalar, size_t vl) {
+ return __riscv_vredminu_vs_u8mf8_u8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredor_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredor_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredsum_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredsum_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredxor_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredxor_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredand_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredand_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredmaxu_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredmaxu_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredminu_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredminu_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredor_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredor_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredsum_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredsum_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredxor_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredxor_vs_u64m8_u64m1(vector, scalar, vl);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-3.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-3.c
new file mode 100644
index 00000000000..0ed1fbae35a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr110265-3.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zve64f -mabi=ilp32f -O3 -Wno-psabi" } */
+
+#include "pr110265-1.h"
+#include "pr110265-2.h"
+
+/* { dg-final { scan-assembler-times {vredand\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredmax\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vredmaxu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredmin\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vredminu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredsum\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredxor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
--
2.34.1
VECTOR_FLOAT_MODE_P referenced from expand, will remove it as it will be removed shortly.
Pan
From: juzhe.zhong@rivai.ai <juzhe.zhong@rivai.ai>
Sent: Friday, June 16, 2023 3:48 PM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>
Cc: Robin Dapp <rdapp.gcc@gmail.com>; jeffreyalaw <jeffreyalaw@gmail.com>; Li, Pan2 <pan2.li@intel.com>; Wang, Yanzhang <yanzhang.wang@intel.com>; kito.cheng <kito.cheng@gmail.com>
Subject: Re: [PATCH v1] RISC-V: Bugfix for RVV integer reduction in ZVE32/64.
+/* Nonzero if MODE is a vector float mode. */
+#define VECTOR_FLOAT_MODE_P(MODE) \
+ (GET_MODE_CLASS (MODE) == MODE_VECTOR_FLOAT)
Why you add this?
Remove it. Otherwise, LGTM.
@@ -1396,8 +1396,17 @@ public:
rtx expand (function_expander &e) const override
{
- return e.use_exact_insn (
- code_for_pred_reduc (CODE, e.vector_mode (), e.vector_mode ()));
+ machine_mode mode = e.vector_mode ();
+ machine_mode ret_mode = e.ret_mode ();
+
+ /* TODO: we will use ret_mode after all types of PR110265 are addressed. */
+ if (VECTOR_FLOAT_MODE_P (mode)
+ || GET_MODE_INNER (mode) != GET_MODE_INNER (ret_mode))
+ return e.use_exact_insn (
+ code_for_pred_reduc (CODE, e.vector_mode (), e.vector_mode ()));
+ else
+ return e.use_exact_insn (
+ code_for_pred_reduc (CODE, e.vector_mode (), e.ret_mode ()));
}
};
@@ -929,6 +929,67 @@ (define_mode_iterator V64T [
(VNx2x64QI "TARGET_MIN_VLEN >= 128")
])
+(define_mode_iterator VQI [
+ (VNx1QI "TARGET_MIN_VLEN < 128")
+ VNx2QI
+ VNx4QI
+ VNx8QI
+ VNx16QI
+ VNx32QI
+ (VNx64QI "TARGET_MIN_VLEN > 32")
+ (VNx128QI "TARGET_MIN_VLEN >= 128")
+])
+
+(define_mode_iterator VHI [
+ (VNx1HI "TARGET_MIN_VLEN < 128")
+ VNx2HI
+ VNx4HI
+ VNx8HI
+ VNx16HI
+ (VNx32HI "TARGET_MIN_VLEN > 32")
+ (VNx64HI "TARGET_MIN_VLEN >= 128")
+])
+
+(define_mode_iterator VSI [
+ (VNx1SI "TARGET_MIN_VLEN < 128")
+ VNx2SI
+ VNx4SI
+ VNx8SI
+ (VNx16SI "TARGET_MIN_VLEN > 32")
+ (VNx32SI "TARGET_MIN_VLEN >= 128")
+])
+
+(define_mode_iterator VDI [
+ (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128")
+ (VNx2DI "TARGET_VECTOR_ELEN_64")
+ (VNx4DI "TARGET_VECTOR_ELEN_64")
+ (VNx8DI "TARGET_VECTOR_ELEN_64")
+ (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128")
+])
+
+(define_mode_iterator VQI_LMUL1 [
+ (VNx16QI "TARGET_MIN_VLEN >= 128")
+ (VNx8QI "TARGET_MIN_VLEN == 64")
+ (VNx4QI "TARGET_MIN_VLEN == 32")
+])
+
+(define_mode_iterator VHI_LMUL1 [
+ (VNx8HI "TARGET_MIN_VLEN >= 128")
+ (VNx4HI "TARGET_MIN_VLEN == 64")
+ (VNx2HI "TARGET_MIN_VLEN == 32")
+])
+
+(define_mode_iterator VSI_LMUL1 [
+ (VNx4SI "TARGET_MIN_VLEN >= 128")
+ (VNx2SI "TARGET_MIN_VLEN == 64")
+ (VNx1SI "TARGET_MIN_VLEN == 32")
+])
+
+(define_mode_iterator VDI_LMUL1 [
+ (VNx2DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128")
+ (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN == 64")
+])
+
(define_mode_attr VLMULX2 [
(VNx1QI "VNx2QI") (VNx2QI "VNx4QI") (VNx4QI "VNx8QI") (VNx8QI "VNx16QI") (VNx16QI "VNx32QI") (VNx32QI "VNx64QI") (VNx64QI "VNx128QI")
(VNx1HI "VNx2HI") (VNx2HI "VNx4HI") (VNx4HI "VNx8HI") (VNx8HI "VNx16HI") (VNx16HI "VNx32HI") (VNx32HI "VNx64HI")
@@ -7244,76 +7244,168 @@ (define_insn "@pred_rod_trunc<mode>"
;; -------------------------------------------------------------------------------
;; For reduction operations, we should have seperate patterns for
-;; TARGET_MIN_VLEN == 32 and TARGET_MIN_VLEN > 32.
+;; different types. For each type, we will cover MIN_VLEN == 32, MIN_VLEN == 64
+;; and the MIN_VLEN >= 128 from the well defined iterators.
;; Since reduction need LMUL = 1 scalar operand as the input operand
;; and they are different.
;; For example, The LMUL = 1 corresponding mode of VNx16QImode is VNx4QImode
;; for -march=rv*zve32* wheras VNx8QImode for -march=rv*zve64*
-(define_insn "@pred_reduc_<reduc><mode><vlmul1>"
- [(set (match_operand:<VLMUL1> 0 "register_operand" "=vr, vr")
- (unspec:<VLMUL1>
- [(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 5 "vector_length_operand" " rK, rK")
- (match_operand 6 "const_int_operand" " i, i")
- (match_operand 7 "const_int_operand" " i, i")
+
+;; Integer Reduction for QI
+(define_insn "@pred_reduc_<reduc><VQI:mode><VQI_LMUL1:mode>"
+ [
+ (set
+ (match_operand:VQI_LMUL1 0 "register_operand" "=vr, vr")
+ (unspec:VQI_LMUL1
+ [
+ (unspec:<VQI:VM>
+ [
+ (match_operand:<VQI:VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK")
+ (match_operand 6 "const_int_operand" " i, i")
+ (match_operand 7 "const_int_operand" " i, i")
(reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (any_reduc:VI
- (vec_duplicate:VI
- (vec_select:<VEL>
- (match_operand:<VLMUL1> 4 "register_operand" " vr, vr")
- (parallel [(const_int 0)])))
- (match_operand:VI 3 "register_operand" " vr, vr"))
- (match_operand:<VLMUL1> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC))]
- "TARGET_VECTOR && TARGET_MIN_VLEN >= 128"
+ (reg:SI VTYPE_REGNUM)
+ ] UNSPEC_VPREDICATE
+ )
+ (any_reduc:VQI
+ (vec_duplicate:VQI
+ (vec_select:<VEL>
+ (match_operand:VQI_LMUL1 4 "register_operand" " vr, vr")
+ (parallel [(const_int 0)])
+ )
+ )
+ (match_operand:VQI 3 "register_operand" " vr, vr")
+ )
+ (match_operand:VQI_LMUL1 2 "vector_merge_operand" " vu, 0")
+ ] UNSPEC_REDUC
+ )
+ )
+ ]
+ "TARGET_VECTOR"
"vred<reduc>.vs\t%0,%3,%4%p1"
- [(set_attr "type" "vired")
- (set_attr "mode" "<MODE>")])
+ [
+ (set_attr "type" "vired")
+ (set_attr "mode" "<VQI:MODE>")
+ ]
+)
-(define_insn "@pred_reduc_<reduc><mode><vlmul1_zve64>"
- [(set (match_operand:<VLMUL1_ZVE64> 0 "register_operand" "=vr, vr")
- (unspec:<VLMUL1_ZVE64>
- [(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 5 "vector_length_operand" " rK, rK")
- (match_operand 6 "const_int_operand" " i, i")
- (match_operand 7 "const_int_operand" " i, i")
+;; Integer Reduction for HI
+(define_insn "@pred_reduc_<reduc><VHI:mode><VHI_LMUL1:mode>"
+ [
+ (set
+ (match_operand:VHI_LMUL1 0 "register_operand" "=vr, vr")
+ (unspec:VHI_LMUL1
+ [
+ (unspec:<VHI:VM>
+ [
+ (match_operand:<VHI:VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK")
+ (match_operand 6 "const_int_operand" " i, i")
+ (match_operand 7 "const_int_operand" " i, i")
(reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (any_reduc:VI_ZVE64
- (vec_duplicate:VI_ZVE64
- (vec_select:<VEL>
- (match_operand:<VLMUL1_ZVE64> 4 "register_operand" " vr, vr")
- (parallel [(const_int 0)])))
- (match_operand:VI_ZVE64 3 "register_operand" " vr, vr"))
- (match_operand:<VLMUL1_ZVE64> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC))]
- "TARGET_VECTOR && TARGET_MIN_VLEN == 64"
+ (reg:SI VTYPE_REGNUM)
+ ] UNSPEC_VPREDICATE
+ )
+ (any_reduc:VHI
+ (vec_duplicate:VHI
+ (vec_select:<VEL>
+ (match_operand:VHI_LMUL1 4 "register_operand" " vr, vr")
+ (parallel [(const_int 0)])
+ )
+ )
+ (match_operand:VHI 3 "register_operand" " vr, vr")
+ )
+ (match_operand:VHI_LMUL1 2 "vector_merge_operand" " vu, 0")
+ ] UNSPEC_REDUC
+ )
+ )
+ ]
+ "TARGET_VECTOR"
"vred<reduc>.vs\t%0,%3,%4%p1"
- [(set_attr "type" "vired")
- (set_attr "mode" "<MODE>")])
+ [
+ (set_attr "type" "vired")
+ (set_attr "mode" "<VHI:MODE>")
+ ]
+)
-(define_insn "@pred_reduc_<reduc><mode><vlmul1_zve32>"
- [(set (match_operand:<VLMUL1_ZVE32> 0 "register_operand" "=vd, vd, vr, vr")
- (unspec:<VLMUL1_ZVE32>
- [(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" " vm, vm,Wc1,Wc1")
- (match_operand 5 "vector_length_operand" " rK, rK, rK, rK")
- (match_operand 6 "const_int_operand" " i, i, i, i")
- (match_operand 7 "const_int_operand" " i, i, i, i")
+;; Integer Reduction for SI
+(define_insn "@pred_reduc_<reduc><VSI:mode><VSI_LMUL1:mode>"
+ [
+ (set
+ (match_operand:VSI_LMUL1 0 "register_operand" "=vr, vr")
+ (unspec:VSI_LMUL1
+ [
+ (unspec:<VSI:VM>
+ [
+ (match_operand:<VSI:VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK")
+ (match_operand 6 "const_int_operand" " i, i")
+ (match_operand 7 "const_int_operand" " i, i")
(reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (any_reduc:VI_ZVE32
- (vec_duplicate:VI_ZVE32
- (vec_select:<VEL>
- (match_operand:<VLMUL1_ZVE32> 4 "register_operand" " vr, vr, vr, vr")
- (parallel [(const_int 0)])))
- (match_operand:VI_ZVE32 3 "register_operand" " vr, vr, vr, vr"))
- (match_operand:<VLMUL1_ZVE32> 2 "vector_merge_operand" " vu, 0, vu, 0")] UNSPEC_REDUC))]
- "TARGET_VECTOR && TARGET_MIN_VLEN == 32"
+ (reg:SI VTYPE_REGNUM)
+ ] UNSPEC_VPREDICATE
+ )
+ (any_reduc:VSI
+ (vec_duplicate:VSI
+ (vec_select:<VEL>
+ (match_operand:VSI_LMUL1 4 "register_operand" " vr, vr")
+ (parallel [(const_int 0)])
+ )
+ )
+ (match_operand:VSI 3 "register_operand" " vr, vr")
+ )
+ (match_operand:VSI_LMUL1 2 "vector_merge_operand" " vu, 0")
+ ] UNSPEC_REDUC
+ )
+ )
+ ]
+ "TARGET_VECTOR"
"vred<reduc>.vs\t%0,%3,%4%p1"
- [(set_attr "type" "vired")
- (set_attr "mode" "<MODE>")])
+ [
+ (set_attr "type" "vired")
+ (set_attr "mode" "<VSI:MODE>")
+ ]
+)
+
+;; Integer Reduction for DI
+(define_insn "@pred_reduc_<reduc><VDI:mode><VDI_LMUL1:mode>"
+ [
+ (set
+ (match_operand:VDI_LMUL1 0 "register_operand" "=vr, vr")
+ (unspec:VDI_LMUL1
+ [
+ (unspec:<VDI:VM>
+ [
+ (match_operand:<VDI:VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK")
+ (match_operand 6 "const_int_operand" " i, i")
+ (match_operand 7 "const_int_operand" " i, i")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)
+ ] UNSPEC_VPREDICATE
+ )
+ (any_reduc:VDI
+ (vec_duplicate:VDI
+ (vec_select:<VEL>
+ (match_operand:VDI_LMUL1 4 "register_operand" " vr, vr")
+ (parallel [(const_int 0)])
+ )
+ )
+ (match_operand:VDI 3 "register_operand" " vr, vr")
+ )
+ (match_operand:VDI_LMUL1 2 "vector_merge_operand" " vu, 0")
+ ] UNSPEC_REDUC
+ )
+ )
+ ]
+ "TARGET_VECTOR"
+ "vred<reduc>.vs\t%0,%3,%4%p1"
+ [
+ (set_attr "type" "vired")
+ (set_attr "mode" "<VDI:MODE>")
+ ]
+)
(define_insn "@pred_widen_reduc_plus<v_su><mode><vwlmul1>"
[(set (match_operand:<VWLMUL1> 0 "register_operand" "=&vr, &vr")
@@ -134,6 +134,10 @@ extern const unsigned char mode_class[NUM_MACHINE_MODES];
|| GET_MODE_CLASS (MODE) == MODE_VECTOR_ACCUM \
|| GET_MODE_CLASS (MODE) == MODE_VECTOR_UACCUM)
+/* Nonzero if MODE is a vector float mode. */
+#define VECTOR_FLOAT_MODE_P(MODE) \
+ (GET_MODE_CLASS (MODE) == MODE_VECTOR_FLOAT) \
+
/* Nonzero if MODE is a scalar integral mode. */
#define SCALAR_INT_MODE_P(MODE) \
(GET_MODE_CLASS (MODE) == MODE_INT \
new file mode 100644
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zve32f -mabi=ilp32f -O3 -Wno-psabi" } */
+
+#include "pr110265-1.h"
+
+/* { dg-final { scan-assembler-times {vredand\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredmax\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredmaxu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredmin\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredminu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredsum\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vredxor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 2 } } */
new file mode 100644
@@ -0,0 +1,65 @@
+#include "riscv_vector.h"
+
+vint8m1_t test_vredand_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredand_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredand_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredand_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredmax_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredmax_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vint32m1_t test_vredmax_vs_i32m8_i32m1(vint32m8_t vector, vint32m1_t scalar, size_t vl) {
+ return __riscv_vredmax_vs_i32m8_i32m1(vector, scalar, vl);
+}
+
+vuint8m1_t test_vredmaxu_vs_u8mf4_u8m1(vuint8mf4_t vector, vuint8m1_t scalar, size_t vl) {
+ return __riscv_vredmaxu_vs_u8mf4_u8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredmaxu_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredmaxu_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredmin_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredmin_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vint32m1_t test_vredmin_vs_i32m8_i32m1(vint32m8_t vector, vint32m1_t scalar, size_t vl) {
+ return __riscv_vredmin_vs_i32m8_i32m1(vector, scalar, vl);
+}
+
+vuint8m1_t test_vredminu_vs_u8mf4_u8m1(vuint8mf4_t vector, vuint8m1_t scalar, size_t vl) {
+ return __riscv_vredminu_vs_u8mf4_u8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredminu_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredminu_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredor_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredor_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredor_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredor_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredsum_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredsum_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredsum_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredsum_vs_u32m8_u32m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredxor_vs_i8mf4_i8m1(vint8mf4_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredxor_vs_i8mf4_i8m1(vector, scalar, vl);
+}
+
+vuint32m1_t test_vredxor_vs_u32m8_u32m1(vuint32m8_t vector, vuint32m1_t scalar, size_t vl) {
+ return __riscv_vredxor_vs_u32m8_u32m1(vector, scalar, vl);
+}
new file mode 100644
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zve64d -mabi=ilp32d -O3 -Wno-psabi" } */
+
+#include "pr110265-1.h"
+#include "pr110265-2.h"
+
+/* { dg-final { scan-assembler-times {vredand\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredmax\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vredmaxu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredmin\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vredminu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredsum\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredxor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
new file mode 100644
@@ -0,0 +1,57 @@
+#include "riscv_vector.h"
+
+vint8m1_t test_vredand_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredand_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredmax_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredmax_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vuint8m1_t test_vredmaxu_vs_u8mf8_u8m1(vuint8mf8_t vector, vuint8m1_t scalar, size_t vl) {
+ return __riscv_vredmaxu_vs_u8mf8_u8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredmin_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredmin_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vuint8m1_t test_vredminu_vs_u8mf8_u8m1(vuint8mf8_t vector, vuint8m1_t scalar, size_t vl) {
+ return __riscv_vredminu_vs_u8mf8_u8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredor_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredor_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredsum_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredsum_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vint8m1_t test_vredxor_vs_i8mf8_i8m1(vint8mf8_t vector, vint8m1_t scalar, size_t vl) {
+ return __riscv_vredxor_vs_i8mf8_i8m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredand_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredand_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredmaxu_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredmaxu_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredminu_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredminu_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredor_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredor_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredsum_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredsum_vs_u64m8_u64m1(vector, scalar, vl);
+}
+
+vuint64m1_t test_vredxor_vs_u64m8_u64m1(vuint64m8_t vector, vuint64m1_t scalar, size_t vl) {
+ return __riscv_vredxor_vs_u64m8_u64m1(vector, scalar, vl);
+}
new file mode 100644
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zve64f -mabi=ilp32f -O3 -Wno-psabi" } */
+
+#include "pr110265-1.h"
+#include "pr110265-2.h"
+
+/* { dg-final { scan-assembler-times {vredand\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredmax\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vredmaxu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredmin\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vredminu\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredsum\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {vredxor\.vs\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 4 } } */