RISC-V: Fix rawmemchr implementation.
Checks
Commit Message
Hi,
this fixes a bug in the rawmemchr implementation by incrementing the
source address by vl * element_size instead of just vl.
This is normally harmless as we will just scan the same region more than
once but, in combination with an older qemu version, would lead to
an execution failure in SPEC2017.
Regards
Robin
gcc/ChangeLog:
* config/riscv/riscv-string.cc (expand_rawmemchr): Increment
source address by vl * element_size.
---
gcc/config/riscv/riscv-string.cc | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
Comments
LGTM。
juzhe.zhong@rivai.ai
From: Robin Dapp
Date: 2023-12-01 23:20
To: gcc-patches; palmer; Kito Cheng; jeffreyalaw; juzhe.zhong@rivai.ai
CC: rdapp.gcc
Subject: [PATCH] RISC-V: Fix rawmemchr implementation.
Hi,
this fixes a bug in the rawmemchr implementation by incrementing the
source address by vl * element_size instead of just vl.
This is normally harmless as we will just scan the same region more than
once but, in combination with an older qemu version, would lead to
an execution failure in SPEC2017.
Regards
Robin
gcc/ChangeLog:
* config/riscv/riscv-string.cc (expand_rawmemchr): Increment
source address by vl * element_size.
---
gcc/config/riscv/riscv-string.cc | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/gcc/config/riscv/riscv-string.cc b/gcc/config/riscv/riscv-string.cc
index f3a4d3ddd47..594ff49fc5a 100644
--- a/gcc/config/riscv/riscv-string.cc
+++ b/gcc/config/riscv/riscv-string.cc
@@ -1017,6 +1017,8 @@ expand_rawmemchr (machine_mode mode, rtx dst, rtx src, rtx pat)
machine_mode mask_mode = riscv_vector::get_mask_mode (vmode);
rtx cnt = gen_reg_rtx (Pmode);
+ emit_move_insn (cnt, CONST0_RTX (Pmode));
+
rtx end = gen_reg_rtx (Pmode);
rtx vec = gen_reg_rtx (vmode);
rtx mask = gen_reg_rtx (mask_mode);
@@ -1033,6 +1035,11 @@ expand_rawmemchr (machine_mode mode, rtx dst, rtx src, rtx pat)
rtx vsrc = change_address (src, vmode, src_addr);
+ /* Bump the pointer. */
+ rtx step = gen_reg_rtx (Pmode);
+ emit_insn (gen_rtx_SET (step, gen_rtx_ASHIFT (Pmode, cnt, GEN_INT (shift))));
+ emit_insn (gen_rtx_SET (src_addr, gen_rtx_PLUS (Pmode, src_addr, step)));
+
/* Emit a first-fault load. */
rtx vlops[] = {vec, vsrc};
emit_vlmax_insn (code_for_pred_fault_load (vmode),
@@ -1055,16 +1062,10 @@ expand_rawmemchr (machine_mode mode, rtx dst, rtx src, rtx pat)
emit_nonvlmax_insn (code_for_pred_ffs (mask_mode, Pmode),
riscv_vector::CPOP_OP, vfops, cnt);
- /* Bump the pointer. */
- emit_insn (gen_rtx_SET (src_addr, gen_rtx_PLUS (Pmode, src_addr, cnt)));
-
/* Emit the loop condition. */
rtx test = gen_rtx_LT (VOIDmode, end, const0_rtx);
emit_jump_insn (gen_cbranch4 (Pmode, test, end, const0_rtx, loop));
- /* We overran by CNT, subtract it. */
- emit_insn (gen_rtx_SET (src_addr, gen_rtx_MINUS (Pmode, src_addr, cnt)));
-
/* We found something at SRC + END * [1,2,4,8]. */
emit_insn (gen_rtx_SET (end, gen_rtx_ASHIFT (Pmode, end, GEN_INT (shift))));
emit_insn (gen_rtx_SET (dst, gen_rtx_PLUS (Pmode, src_addr, end)));
--
2.43.0
@@ -1017,6 +1017,8 @@ expand_rawmemchr (machine_mode mode, rtx dst, rtx src, rtx pat)
machine_mode mask_mode = riscv_vector::get_mask_mode (vmode);
rtx cnt = gen_reg_rtx (Pmode);
+ emit_move_insn (cnt, CONST0_RTX (Pmode));
+
rtx end = gen_reg_rtx (Pmode);
rtx vec = gen_reg_rtx (vmode);
rtx mask = gen_reg_rtx (mask_mode);
@@ -1033,6 +1035,11 @@ expand_rawmemchr (machine_mode mode, rtx dst, rtx src, rtx pat)
rtx vsrc = change_address (src, vmode, src_addr);
+ /* Bump the pointer. */
+ rtx step = gen_reg_rtx (Pmode);
+ emit_insn (gen_rtx_SET (step, gen_rtx_ASHIFT (Pmode, cnt, GEN_INT (shift))));
+ emit_insn (gen_rtx_SET (src_addr, gen_rtx_PLUS (Pmode, src_addr, step)));
+
/* Emit a first-fault load. */
rtx vlops[] = {vec, vsrc};
emit_vlmax_insn (code_for_pred_fault_load (vmode),
@@ -1055,16 +1062,10 @@ expand_rawmemchr (machine_mode mode, rtx dst, rtx src, rtx pat)
emit_nonvlmax_insn (code_for_pred_ffs (mask_mode, Pmode),
riscv_vector::CPOP_OP, vfops, cnt);
- /* Bump the pointer. */
- emit_insn (gen_rtx_SET (src_addr, gen_rtx_PLUS (Pmode, src_addr, cnt)));
-
/* Emit the loop condition. */
rtx test = gen_rtx_LT (VOIDmode, end, const0_rtx);
emit_jump_insn (gen_cbranch4 (Pmode, test, end, const0_rtx, loop));
- /* We overran by CNT, subtract it. */
- emit_insn (gen_rtx_SET (src_addr, gen_rtx_MINUS (Pmode, src_addr, cnt)));
-
/* We found something at SRC + END * [1,2,4,8]. */
emit_insn (gen_rtx_SET (end, gen_rtx_ASHIFT (Pmode, end, GEN_INT (shift))));
emit_insn (gen_rtx_SET (dst, gen_rtx_PLUS (Pmode, src_addr, end)));