[PATCH] riscv: Skip vector code for zero length in RVV mem/str routines

Anton Blanchard antonb@tenstorrent.com
Wed Nov 18 01:47:10 GMT 2026


memcpy, memset, memcmp, memchr, memccpy, stpncpy and strncpy enter
their vector loop without checking the length, so a zero length call
executes vector loads and/or stores with VL=0. While these are no-ops
architecturally, they are expensive on some implementations including
Tenstorrent Ascalon.

Return early when the length is zero, as memmove and strncmp already
do. This resolves the performance issue on Ascalon, and a pass of the
glibc bench tests shows no regressions.

Signed-off-by: Anton Blanchard <antonb@tenstorrent.com>
---
 sysdeps/riscv/rvv/memccpy.S | 2 ++
 sysdeps/riscv/rvv/memchr.S  | 2 ++
 sysdeps/riscv/rvv/memcmp.S  | 2 ++
 sysdeps/riscv/rvv/memcpy.S  | 2 ++
 sysdeps/riscv/rvv/memset.S  | 2 ++
 sysdeps/riscv/rvv/stpncpy.S | 2 ++
 6 files changed, 12 insertions(+)

diff --git a/sysdeps/riscv/rvv/memccpy.S b/sysdeps/riscv/rvv/memccpy.S
index 5854d463c2..0bea8400cc 100644
--- a/sysdeps/riscv/rvv/memccpy.S
+++ b/sysdeps/riscv/rvv/memccpy.S
@@ -39,6 +39,7 @@
 ENTRY (MEMCCPY)
 .option push
 .option arch, +v
+    beqz num, L(not_found)
     mv dst_ptr, dst
 L(loop):
     vsetvli zero, num, e8, ELEM_LMUL_SETTING, ta, ma
@@ -54,6 +55,7 @@ L(loop):
     add src, src, ivl
     add dst_ptr, dst_ptr, ivl
     bnez num, L(loop)
+L(not_found):
     mv a0, zero
     ret
 L(found):
diff --git a/sysdeps/riscv/rvv/memchr.S b/sysdeps/riscv/rvv/memchr.S
index 609b2f94c1..04fe348c7d 100644
--- a/sysdeps/riscv/rvv/memchr.S
+++ b/sysdeps/riscv/rvv/memchr.S
@@ -39,6 +39,7 @@
 ENTRY (MEMCHR)
 .option push
 .option arch, +v
+    beqz num, L(not_found)
 L(loop):
     vsetvli zero, num, e8, ELEM_LMUL_SETTING, ta, ma
 
@@ -56,6 +57,7 @@ L(loop):
 
     bnez num, L(loop)
 
+L(not_found):
     li result, 0
     ret
 L(found):
diff --git a/sysdeps/riscv/rvv/memcmp.S b/sysdeps/riscv/rvv/memcmp.S
index 004bf538f0..20bfb4ef37 100644
--- a/sysdeps/riscv/rvv/memcmp.S
+++ b/sysdeps/riscv/rvv/memcmp.S
@@ -42,6 +42,7 @@
 ENTRY (MEMCMP)
 .option push
 .option arch, +v
+    beqz num, L(equal)
 L(loop):
     vsetvli ivl, num, e8, ELEM_LMUL_SETTING, ta, ma
 
@@ -59,6 +60,7 @@ L(loop):
 
     bnez num, L(loop)
 
+L(equal):
     li result, 0
     ret
 L(found):
diff --git a/sysdeps/riscv/rvv/memcpy.S b/sysdeps/riscv/rvv/memcpy.S
index b4d600c59d..dad7cb4a6c 100644
--- a/sysdeps/riscv/rvv/memcpy.S
+++ b/sysdeps/riscv/rvv/memcpy.S
@@ -36,6 +36,7 @@
 ENTRY (MEMCPY)
 .option push
 .option arch, +v
+    beqz num, L(done)
     mv dst_ptr, dst
 L(loop):
     vsetvli ivl, num, e8, ELEM_LMUL_SETTING, ta, ma
@@ -48,6 +49,7 @@ L(loop):
 
     bnez num, L(loop)
 
+L(done):
     ret
 .option pop
 END (MEMCPY)
diff --git a/sysdeps/riscv/rvv/memset.S b/sysdeps/riscv/rvv/memset.S
index fef507b090..30994bbebc 100644
--- a/sysdeps/riscv/rvv/memset.S
+++ b/sysdeps/riscv/rvv/memset.S
@@ -36,6 +36,7 @@
 ENTRY (MEMSET)
 .option push
 .option arch, +v
+    beqz num, L(done)
     mv dst_ptr, dst
 
     vsetvli ivl, num, e8, ELEM_LMUL_SETTING, ta, ma
@@ -47,6 +48,7 @@ L(loop):
     vsetvli ivl, num, e8, ELEM_LMUL_SETTING, ta, ma
     bnez num, L(loop)
 
+L(done):
     ret
 .option pop
 END (MEMSET)
diff --git a/sysdeps/riscv/rvv/stpncpy.S b/sysdeps/riscv/rvv/stpncpy.S
index 71bb46b04e..b038149728 100644
--- a/sysdeps/riscv/rvv/stpncpy.S
+++ b/sysdeps/riscv/rvv/stpncpy.S
@@ -55,6 +55,7 @@ weak_alias (__stpncpy, stpncpy)
 ENTRY (STPNCPY)
 .option push
 .option arch, +v
+    beqz length, L(done)
     mv dst_ptr, dst
     /* Copy src to dst_ptr.  */
 L(stpcpy_loop):
@@ -73,6 +74,7 @@ L(stpcpy_loop):
 #ifndef USE_AS_STRNCPY
     mv dst, dst_ptr
 #endif
+L(done):
     ret
 
     /* Fill the tail zero.  */
-- 
2.53.0



More information about the Libc-alpha mailing list