RE: [PATCH] RISC-V: Support RVV zvfh{min} vfloat16*_t mov and spill

["Li, Pan2" <pan2.li@intel.com>]

[-- Attachment #1: Type: text/plain, Size: 19295 bytes --]

Great! Thanks Juzhe and let’s wait kito’s approval.

Pan

From: 钟居哲 <juzhe.zhong@rivai.ai>
Sent: Sunday, June 4, 2023 7:36 AM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>
Cc: kito.cheng <kito.cheng@sifive.com>; Li, Pan2 <pan2.li@intel.com>; Wang, Yanzhang <yanzhang.wang@intel.com>
Subject: Re: [PATCH] RISC-V: Support RVV zvfh{min} vfloat16*_t mov and spill

LGTM. Hope FP16 vector can be committed soon.
Since I would like to wait for FP16 vector and then start to support FP16 FP32 FP64 autovec together.

Thanks.
________________________________
juzhe.zhong@rivai.ai<mailto:juzhe.zhong@rivai.ai>

From: pan2.li<mailto:pan2.li@intel.com>
Date: 2023-06-03 22:37
To: gcc-patches<mailto:gcc-patches@gcc.gnu.org>
CC: juzhe.zhong<mailto:juzhe.zhong@rivai.ai>; kito.cheng<mailto:kito.cheng@sifive.com>; pan2.li<mailto:pan2.li@intel.com>; yanzhang.wang<mailto:yanzhang.wang@intel.com>
Subject: [PATCH] RISC-V: Support RVV zvfh{min} vfloat16*_t mov and spill
From: Pan Li <pan2.li@intel.com<mailto:pan2.li@intel.com>>

This patch would like to allow the mov and spill operation for the RVV
vfloat16*_t types. The involved machine mode includes VNx1HF, VNx2HF,
VNx4HF, VNx8HF, VNx16HF, VNx32HF and VNx64HF.

Signed-off-by: Pan Li <pan2.li@intel.com<mailto:pan2.li@intel.com>>
Co-Authored by: Juzhe-Zhong <juzhe.zhong@rivai.ai<mailto:juzhe.zhong@rivai.ai>>

gcc/ChangeLog:

* config/riscv/riscv-vector-builtins-types.def
(vfloat16mf4_t): Add the float16 type to DEF_RVV_F_OPS.
(vfloat16mf2_t): Likewise.
(vfloat16m1_t): Likewise.
(vfloat16m2_t): Likewise.
(vfloat16m4_t): Likewise.
(vfloat16m8_t): Likewise.
* config/riscv/riscv.md: Add vfloat16*_t to attr mode.
* config/riscv/vector-iterators.md: Add vfloat16*_t machine mode
to V, V_WHOLE, V_FRACT, VINDEX, VM, VEL and sew.
* config/riscv/vector.md: Add vfloat16*_t machine mode to sew,
vlmul and ratio.

gcc/testsuite/ChangeLog:

* gcc.target/riscv/rvv/base/mov-14.c: New test.
* gcc.target/riscv/rvv/base/spill-13.c: New test.
---
.../riscv/riscv-vector-builtins-types.def     |   7 ++
gcc/config/riscv/riscv.md                     |   1 +
gcc/config/riscv/vector-iterators.md          |  25 ++++
gcc/config/riscv/vector.md                    |  35 ++++++
.../gcc.target/riscv/rvv/base/mov-14.c        |  81 +++++++++++++
.../gcc.target/riscv/rvv/base/spill-13.c      | 108 ++++++++++++++++++
6 files changed, 257 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/mov-14.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/spill-13.c

diff --git a/gcc/config/riscv/riscv-vector-builtins-types.def b/gcc/config/riscv/riscv-vector-builtins-types.def
index f7f650f7e95..65716b8c637 100644
--- a/gcc/config/riscv/riscv-vector-builtins-types.def
+++ b/gcc/config/riscv/riscv-vector-builtins-types.def
@@ -385,6 +385,13 @@ DEF_RVV_U_OPS (vuint64m2_t, RVV_REQUIRE_ELEN_64)
DEF_RVV_U_OPS (vuint64m4_t, RVV_REQUIRE_ELEN_64)
DEF_RVV_U_OPS (vuint64m8_t, RVV_REQUIRE_ELEN_64)
+DEF_RVV_F_OPS (vfloat16mf4_t, RVV_REQUIRE_ELEN_FP_16 | RVV_REQUIRE_MIN_VLEN_64)
+DEF_RVV_F_OPS (vfloat16mf2_t, RVV_REQUIRE_ELEN_FP_16)
+DEF_RVV_F_OPS (vfloat16m1_t, RVV_REQUIRE_ELEN_FP_16)
+DEF_RVV_F_OPS (vfloat16m2_t, RVV_REQUIRE_ELEN_FP_16)
+DEF_RVV_F_OPS (vfloat16m4_t, RVV_REQUIRE_ELEN_FP_16)
+DEF_RVV_F_OPS (vfloat16m8_t, RVV_REQUIRE_ELEN_FP_16)
+
DEF_RVV_F_OPS (vfloat32mf2_t, RVV_REQUIRE_ELEN_FP_32 | RVV_REQUIRE_MIN_VLEN_64)
DEF_RVV_F_OPS (vfloat32m1_t, RVV_REQUIRE_ELEN_FP_32)
DEF_RVV_F_OPS (vfloat32m2_t, RVV_REQUIRE_ELEN_FP_32)
diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index f545874edc1..be960583101 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -175,6 +175,7 @@ (define_attr "mode" "unknown,none,QI,HI,SI,DI,TI,HF,SF,DF,TF,
   VNx1HI,VNx2HI,VNx4HI,VNx8HI,VNx16HI,VNx32HI,VNx64HI,
   VNx1SI,VNx2SI,VNx4SI,VNx8SI,VNx16SI,VNx32SI,
   VNx1DI,VNx2DI,VNx4DI,VNx8DI,VNx16DI,
+  VNx1HF,VNx2HF,VNx4HF,VNx8HF,VNx16HF,VNx32HF,VNx64HF,
   VNx1SF,VNx2SF,VNx4SF,VNx8SF,VNx16SF,VNx32SF,
   VNx1DF,VNx2DF,VNx4DF,VNx8DF,VNx16DF,
   VNx2x64QI,VNx2x32QI,VNx3x32QI,VNx4x32QI,
diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md
index 937ec3c7f67..5fbaef89566 100644
--- a/gcc/config/riscv/vector-iterators.md
+++ b/gcc/config/riscv/vector-iterators.md
@@ -90,6 +90,15 @@ (define_mode_iterator V [
   (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128")
   (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")
+
+  (VNx1HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN < 128")
+  (VNx2HF "TARGET_VECTOR_ELEN_FP_16")
+  (VNx4HF "TARGET_VECTOR_ELEN_FP_16")
+  (VNx8HF "TARGET_VECTOR_ELEN_FP_16")
+  (VNx16HF "TARGET_VECTOR_ELEN_FP_16")
+  (VNx32HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32")
+  (VNx64HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN >= 128")
+
   (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128")
   (VNx2SF "TARGET_VECTOR_ELEN_FP_32")
   (VNx4SF "TARGET_VECTOR_ELEN_FP_32")
@@ -427,6 +436,15 @@ (define_mode_iterator V_WHOLE [
   (VNx1SI "TARGET_MIN_VLEN == 32") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128")
   (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_MIN_VLEN >= 128")
+
+  (VNx1HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN < 128")
+  (VNx2HF "TARGET_VECTOR_ELEN_FP_16")
+  (VNx4HF "TARGET_VECTOR_ELEN_FP_16")
+  (VNx8HF "TARGET_VECTOR_ELEN_FP_16")
+  (VNx16HF "TARGET_VECTOR_ELEN_FP_16")
+  (VNx32HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32")
+  (VNx64HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN >= 128")
+
   (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN == 32")
   (VNx2SF "TARGET_VECTOR_ELEN_FP_32")
   (VNx4SF "TARGET_VECTOR_ELEN_FP_32")
@@ -443,6 +461,7 @@ (define_mode_iterator V_WHOLE [
(define_mode_iterator V_FRACT [
   (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI (VNx4QI "TARGET_MIN_VLEN > 32") (VNx8QI "TARGET_MIN_VLEN >= 128")
   (VNx1HI "TARGET_MIN_VLEN < 128") (VNx2HI "TARGET_MIN_VLEN > 32") (VNx4HI "TARGET_MIN_VLEN >= 128")
+  (VNx1HF "TARGET_MIN_VLEN < 128") (VNx2HF "TARGET_MIN_VLEN > 32") (VNx4HF "TARGET_MIN_VLEN >= 128")
   (VNx1SI "TARGET_MIN_VLEN > 32 && TARGET_MIN_VLEN < 128") (VNx2SI "TARGET_MIN_VLEN >= 128")
   (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32")
   (VNx2SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128")
@@ -925,6 +944,7 @@ (define_mode_attr VINDEX [
   (VNx1SI "VNx1SI") (VNx2SI "VNx2SI") (VNx4SI "VNx4SI") (VNx8SI "VNx8SI")
   (VNx16SI "VNx16SI") (VNx32SI "VNx32SI")
   (VNx1DI "VNx1DI") (VNx2DI "VNx2DI") (VNx4DI "VNx4DI") (VNx8DI "VNx8DI") (VNx16DI "VNx16DI")
+  (VNx1HF "VNx1HI") (VNx2HF "VNx2HI") (VNx4HF "VNx4HI") (VNx8HF "VNx8HI") (VNx16HF "VNx16HI") (VNx32HF "VNx32HI") (VNx64HF "VNx64HI")
   (VNx1SF "VNx1SI") (VNx2SF "VNx2SI") (VNx4SF "VNx4SI") (VNx8SF "VNx8SI")
   (VNx16SF "VNx16SI") (VNx32SF "VNx32SI")
   (VNx1DF "VNx1DI") (VNx2DF "VNx2DI") (VNx4DF "VNx4DI") (VNx8DF "VNx8DI") (VNx16DF "VNx16DI")
@@ -948,6 +968,7 @@ (define_mode_attr VM [
   (VNx1HI "VNx1BI") (VNx2HI "VNx2BI") (VNx4HI "VNx4BI") (VNx8HI "VNx8BI") (VNx16HI "VNx16BI") (VNx32HI "VNx32BI") (VNx64HI "VNx64BI")
   (VNx1SI "VNx1BI") (VNx2SI "VNx2BI") (VNx4SI "VNx4BI") (VNx8SI "VNx8BI") (VNx16SI "VNx16BI") (VNx32SI "VNx32BI")
   (VNx1DI "VNx1BI") (VNx2DI "VNx2BI") (VNx4DI "VNx4BI") (VNx8DI "VNx8BI") (VNx16DI "VNx16BI")
+  (VNx1HF "VNx1BI") (VNx2HF "VNx2BI") (VNx4HF "VNx4BI") (VNx8HF "VNx8BI") (VNx16HF "VNx16BI") (VNx32HF "VNx32BI") (VNx64HF "VNx64BI")
   (VNx1SF "VNx1BI") (VNx2SF "VNx2BI") (VNx4SF "VNx4BI") (VNx8SF "VNx8BI") (VNx16SF "VNx16BI") (VNx32SF "VNx32BI")
   (VNx1DF "VNx1BI") (VNx2DF "VNx2BI") (VNx4DF "VNx4BI") (VNx8DF "VNx8BI") (VNx16DF "VNx16BI")
   (VNx2x64QI "VNx64BI") (VNx2x32QI "VNx32BI") (VNx3x32QI "VNx32BI") (VNx4x32QI "VNx32BI")
@@ -983,6 +1004,7 @@ (define_mode_attr vm [
   (VNx1HI "vnx1bi") (VNx2HI "vnx2bi") (VNx4HI "vnx4bi") (VNx8HI "vnx8bi") (VNx16HI "vnx16bi") (VNx32HI "vnx32bi") (VNx64HI "vnx64bi")
   (VNx1SI "vnx1bi") (VNx2SI "vnx2bi") (VNx4SI "vnx4bi") (VNx8SI "vnx8bi") (VNx16SI "vnx16bi") (VNx32SI "vnx32bi")
   (VNx1DI "vnx1bi") (VNx2DI "vnx2bi") (VNx4DI "vnx4bi") (VNx8DI "vnx8bi") (VNx16DI "vnx16bi")
+  (VNx1HF "vnx1bi") (VNx2HF "vnx2bi") (VNx4HF "vnx4bi") (VNx8HF "vnx8bi") (VNx16HF "vnx16bi") (VNx32HF "vnx32bi") (VNx64HF "vnx64bi")
   (VNx1SF "vnx1bi") (VNx2SF "vnx2bi") (VNx4SF "vnx4bi") (VNx8SF "vnx8bi") (VNx16SF "vnx16bi") (VNx32SF "vnx32bi")
   (VNx1DF "vnx1bi") (VNx2DF "vnx2bi") (VNx4DF "vnx4bi") (VNx8DF "vnx8bi") (VNx16DF "vnx16bi")
])
@@ -992,6 +1014,7 @@ (define_mode_attr VEL [
   (VNx1HI "HI") (VNx2HI "HI") (VNx4HI "HI") (VNx8HI "HI") (VNx16HI "HI") (VNx32HI "HI") (VNx64HI "HI")
   (VNx1SI "SI") (VNx2SI "SI") (VNx4SI "SI") (VNx8SI "SI") (VNx16SI "SI") (VNx32SI "SI")
   (VNx1DI "DI") (VNx2DI "DI") (VNx4DI "DI") (VNx8DI "DI") (VNx16DI "DI")
+  (VNx1HF "HF") (VNx2HF "HF") (VNx4HF "HF") (VNx8HF "HF") (VNx16HF "HF") (VNx32HF "HF") (VNx64HF "HF")
   (VNx1SF "SF") (VNx2SF "SF") (VNx4SF "SF") (VNx8SF "SF") (VNx16SF "SF") (VNx32SF "SF")
   (VNx1DF "DF") (VNx2DF "DF") (VNx4DF "DF") (VNx8DF "DF") (VNx16DF "DF")
])
@@ -1001,6 +1024,7 @@ (define_mode_attr vel [
   (VNx1HI "hi") (VNx2HI "hi") (VNx4HI "hi") (VNx8HI "hi") (VNx16HI "hi") (VNx32HI "hi") (VNx64HI "hi")
   (VNx1SI "si") (VNx2SI "si") (VNx4SI "si") (VNx8SI "si") (VNx16SI "si") (VNx32SI "si")
   (VNx1DI "di") (VNx2DI "di") (VNx4DI "di") (VNx8DI "di") (VNx16DI "di")
+  (VNx1HF "hf") (VNx2HF "hf") (VNx4HF "hf") (VNx8HF "hf") (VNx16HF "hf") (VNx32HF "hf") (VNx64HF "hf")
   (VNx1SF "sf") (VNx2SF "sf") (VNx4SF "sf") (VNx8SF "sf") (VNx16SF "sf") (VNx32SF "sf")
   (VNx1DF "df") (VNx2DF "df") (VNx4DF "df") (VNx8DF "df") (VNx16DF "df")
])
@@ -1047,6 +1071,7 @@ (define_mode_attr sew [
   (VNx1HI "16") (VNx2HI "16") (VNx4HI "16") (VNx8HI "16") (VNx16HI "16") (VNx32HI "16") (VNx64HI "16")
   (VNx1SI "32") (VNx2SI "32") (VNx4SI "32") (VNx8SI "32") (VNx16SI "32") (VNx32SI "32")
   (VNx1DI "64") (VNx2DI "64") (VNx4DI "64") (VNx8DI "64") (VNx16DI "64")
+  (VNx1HF "16") (VNx2HF "16") (VNx4HF "16") (VNx8HF "16") (VNx16HF "16") (VNx32HF "16") (VNx64HF "16")
   (VNx1SF "32") (VNx2SF "32") (VNx4SF "32") (VNx8SF "32") (VNx16SF "32") (VNx32SF "32")
   (VNx1DF "64") (VNx2DF "64") (VNx4DF "64") (VNx8DF "64") (VNx16DF "64")
   (VNx2x64QI "8") (VNx2x32QI "8") (VNx3x32QI "8") (VNx4x32QI "8")
diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md
index 419853a93c1..79f1644732a 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -93,6 +93,7 @@ (define_attr "sew" ""
  VNx2x1QI,VNx3x1QI,VNx4x1QI,VNx5x1QI,VNx6x1QI,VNx7x1QI,VNx8x1QI")
(const_int 8)
(eq_attr "mode" "VNx1HI,VNx2HI,VNx4HI,VNx8HI,VNx16HI,VNx32HI,VNx64HI,\
+   VNx1HF,VNx2HF,VNx4HF,VNx8HF,VNx16HF,VNx32HF,VNx64HF,\
  VNx2x32HI,VNx2x16HI,VNx3x16HI,VNx4x16HI,\
  VNx2x8HI,VNx3x8HI,VNx4x8HI,VNx5x8HI,VNx6x8HI,VNx7x8HI,VNx8x8HI,\
  VNx2x4HI,VNx3x4HI,VNx4x4HI,VNx5x4HI,VNx6x4HI,VNx7x4HI,VNx8x4HI,\
@@ -153,6 +154,23 @@ (define_attr "vlmul" ""
   (symbol_ref "riscv_vector::get_vlmul(E_VNx32HImode)")
(eq_attr "mode" "VNx64HI")
   (symbol_ref "riscv_vector::get_vlmul(E_VNx64HImode)")
+
+ ; Half float point
+ (eq_attr "mode" "VNx1HF")
+    (symbol_ref "riscv_vector::get_vlmul(E_VNx1HFmode)")
+ (eq_attr "mode" "VNx2HF")
+    (symbol_ref "riscv_vector::get_vlmul(E_VNx2HFmode)")
+ (eq_attr "mode" "VNx4HF")
+    (symbol_ref "riscv_vector::get_vlmul(E_VNx4HFmode)")
+ (eq_attr "mode" "VNx8HF")
+    (symbol_ref "riscv_vector::get_vlmul(E_VNx8HFmode)")
+ (eq_attr "mode" "VNx16HF")
+    (symbol_ref "riscv_vector::get_vlmul(E_VNx16HFmode)")
+ (eq_attr "mode" "VNx32HF")
+    (symbol_ref "riscv_vector::get_vlmul(E_VNx32HFmode)")
+ (eq_attr "mode" "VNx64HF")
+    (symbol_ref "riscv_vector::get_vlmul(E_VNx64HFmode)")
+
(eq_attr "mode" "VNx1SI,VNx1SF,VNx2x1SI,VNx3x1SI,VNx4x1SI,VNx5x1SI,VNx6x1SI,VNx7x1SI,VNx8x1SI,\
  VNx2x1SF,VNx3x1SF,VNx4x1SF,VNx5x1SF,VNx6x1SF,VNx7x1SF,VNx8x1SF")
   (symbol_ref "riscv_vector::get_vlmul(E_VNx1SImode)")
@@ -229,6 +247,23 @@ (define_attr "ratio" ""
   (symbol_ref "riscv_vector::get_ratio(E_VNx32HImode)")
(eq_attr "mode" "VNx64HI")
   (symbol_ref "riscv_vector::get_ratio(E_VNx64HImode)")
+
+ ; Half float point.
+ (eq_attr "mode" "VNx1HF")
+    (symbol_ref "riscv_vector::get_ratio(E_VNx1HFmode)")
+ (eq_attr "mode" "VNx2HF")
+    (symbol_ref "riscv_vector::get_ratio(E_VNx2HFmode)")
+ (eq_attr "mode" "VNx4HF")
+    (symbol_ref "riscv_vector::get_ratio(E_VNx4HFmode)")
+ (eq_attr "mode" "VNx8HF")
+    (symbol_ref "riscv_vector::get_ratio(E_VNx8HFmode)")
+ (eq_attr "mode" "VNx16HF")
+    (symbol_ref "riscv_vector::get_ratio(E_VNx16HFmode)")
+ (eq_attr "mode" "VNx32HF")
+    (symbol_ref "riscv_vector::get_ratio(E_VNx32HFmode)")
+ (eq_attr "mode" "VNx64HF")
+    (symbol_ref "riscv_vector::get_ratio(E_VNx64HFmode)")
+
(eq_attr "mode" "VNx1SI,VNx1SF,VNx2x1SI,VNx3x1SI,VNx4x1SI,VNx5x1SI,VNx6x1SI,VNx7x1SI,VNx8x1SI,\
  VNx2x1SF,VNx3x1SF,VNx4x1SF,VNx5x1SF,VNx6x1SF,VNx7x1SF,VNx8x1SF")
   (symbol_ref "riscv_vector::get_ratio(E_VNx1SImode)")
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/mov-14.c b/gcc/testsuite/gcc.target/riscv/rvv/base/mov-14.c
new file mode 100644
index 00000000000..94c8d399f20
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/mov-14.c
@@ -0,0 +1,81 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcv_zvfhmin -mabi=ilp32d -O3" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "riscv_vector.h"
+
+typedef _Float16 float16_t;
+
+/*
+** mov_vf16_mf4:
+**   vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]
+**   vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vse16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ret
+*/
+void mov_vf16_mf4 (float16_t *in, float16_t *out)
+{
+  vfloat16mf4_t v = *(vfloat16mf4_t *)in;
+  * (vfloat16mf4_t *) out = v;
+}
+
+/*
+** mov_vf16_mf2:
+**   vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]
+**   vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vse16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ret
+*/
+void mov_vf16_mf2 (float16_t *in, float16_t *out)
+{
+  vfloat16mf2_t v = *(vfloat16mf2_t *)in;
+  * (vfloat16mf2_t *) out = v;
+}
+
+/*
+** mov_vf16_m1:
+**   vl1re16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vs1r\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ret
+*/
+void mov_vf16_m1 (float16_t *in, float16_t *out)
+{
+  vfloat16m1_t v = *(vfloat16m1_t *)in;
+  * (vfloat16m1_t *) out = v;
+}
+
+/*
+** mov_vf16_m2:
+**   vl2re16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vs2r\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ret
+*/
+void mov_vf16_m2 (float16_t *in, float16_t *out)
+{
+  vfloat16m2_t v = *(vfloat16m2_t *)in;
+  * (vfloat16m2_t *) out = v;
+}
+
+/*
+** mov_vf16_m4:
+**   vl4re16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vs4r\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ret
+*/
+void mov_vf16_m4 (float16_t *in, float16_t *out)
+{
+  vfloat16m4_t v = *(vfloat16m4_t *)in;
+  * (vfloat16m4_t *) out = v;
+}
+
+/*
+** mov_vf16_m8:
+**   vl8re16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vs8r\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ret
+*/
+void mov_vf16_m8 (float16_t *in, float16_t *out)
+{
+  vfloat16m8_t v = *(vfloat16m8_t *)in;
+  * (vfloat16m8_t *) out = v;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-13.c b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-13.c
new file mode 100644
index 00000000000..2274b1784d3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-13.c
@@ -0,0 +1,108 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcv_zvfhmin -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "riscv_vector.h"
+#include "macro.h"
+
+typedef _Float16 float16_t;
+
+/*
+** spill_vf16_mf4:
+**   ...
+**   vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]
+**   vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   vse16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vse16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   jr\s+ra
+*/
+void spill_vf16_mf4 (float16_t *in, float16_t *out)
+{
+  vfloat16mf4_t v = *(vfloat16mf4_t *)in;
+  exhaust_vector_regs ();
+  * (vfloat16mf4_t *) out = v;
+}
+
+/*
+** spill_vf16_mf2:
+**   ...
+**   vsetvli\s+[a-x0-9]+,\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]
+**   vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   vse16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vse16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   jr\s+ra
+*/
+void spill_vf16_mf2 (float16_t *in, float16_t *out)
+{
+  vfloat16mf2_t v = *(vfloat16mf2_t *)in;
+  exhaust_vector_regs ();
+  * (vfloat16mf2_t *) out = v;
+}
+
+/*
+** spill_vf16_m1:
+**   ...
+**   vl1re16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vs1r\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   ret
+*/
+void spill_vf16_m1 (float16_t *in, float16_t *out)
+{
+  vfloat16m1_t v = *(vfloat16m1_t *)in;
+  exhaust_vector_regs ();
+  * (vfloat16m1_t *) out = v;
+}
+
+/*
+** spill_vf16_m2:
+**   ...
+**   vl2re16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vs2r\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   ret
+*/
+void spill_vf16_m2 (float16_t *in, float16_t *out)
+{
+  vfloat16m2_t v = *(vfloat16m2_t *)in;
+  exhaust_vector_regs ();
+  * (vfloat16m2_t *) out = v;
+}
+
+/*
+** spill_vf16_m4:
+**   ...
+**   vl4re16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vs4r\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   ret
+*/
+void spill_vf16_m4 (float16_t *in, float16_t *out)
+{
+  vfloat16m4_t v = *(vfloat16m4_t *)in;
+  exhaust_vector_regs ();
+  * (vfloat16m4_t *) out = v;
+}
+
+/*
+** spill_vf16_m8:
+**   ...
+**   vl8re16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   vs8r\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\([a-x0-9]+\)
+**   ...
+**   ret
+*/
+void spill_vf16_m8 (float16_t *in, float16_t *out)
+{
+  vfloat16m8_t v = *(vfloat16m8_t *)in;
+  exhaust_vector_regs ();
+  * (vfloat16m8_t *) out = v;
+}
--
2.34.1