Address a problem we were having where we were missing on detecting uses of vctp_vpr_generated in the analysis for 'arm_attempt_dlstp_transform' because the use was inside a SUBREG and rtx_equal_p does not catch that. Using reg_overlap_mentioned_p is much more robust.
gcc/ChangeLog: * gcc/config/arm/arm.cc (arm_attempt_dlstp_transform): Use reg_overlap_mentioned_p instead of rtx_equal_p to detect uses of vctp_vpr_generated inside subregs. gcc/testsuite/ChangeLog: * gcc.target/arm/mve/dlstp-invalid-asm.c (test10): Renamed to... (test10a): ... this. (test10b): Variation of test10a with a small change to trigger wrong codegen. --- gcc/config/arm/arm.cc | 3 ++- .../gcc.target/arm/mve/dlstp-invalid-asm.c | 20 ++++++++++++++++++- 2 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/gcc/config/arm/arm.cc b/gcc/config/arm/arm.cc index 7292fddef80..7f82fb94a56 100644 --- a/gcc/config/arm/arm.cc +++ b/gcc/config/arm/arm.cc @@ -35847,7 +35847,8 @@ arm_attempt_dlstp_transform (rtx label) df_ref insn_uses = NULL; FOR_EACH_INSN_USE (insn_uses, insn) { - if (rtx_equal_p (vctp_vpr_generated, DF_REF_REG (insn_uses))) + if (reg_overlap_mentioned_p (vctp_vpr_generated, + DF_REF_REG (insn_uses))) { end_sequence (); return 1; diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-invalid-asm.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-invalid-asm.c index 26df2d30523..f26754cc482 100644 --- a/gcc/testsuite/gcc.target/arm/mve/dlstp-invalid-asm.c +++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-invalid-asm.c @@ -128,7 +128,7 @@ void test9 (int32_t *a, int32_t *b, int32_t *c, int n) } /* Using a VPR that gets re-generated within the loop. */ -void test10 (int32_t *a, int32_t *b, int32_t *c, int n) +void test10a (int32_t *a, int32_t *b, int32_t *c, int n) { mve_pred16_t p = vctp32q (n); while (n > 0) @@ -145,6 +145,24 @@ void test10 (int32_t *a, int32_t *b, int32_t *c, int n) } } +/* Using a VPR that gets re-generated within the loop. */ +void test10b (int32_t *a, int32_t *b, int32_t *c, int n) +{ + mve_pred16_t p = vctp32q (n-4); + while (n > 0) + { + int32x4_t va = vldrwq_z_s32 (a, p); + p = vctp32q (n); + int32x4_t vb = vldrwq_z_s32 (b, p); + int32x4_t vc = vaddq_x_s32 (va, vb, p); + vstrwq_p_s32 (c, vc, p); + c += 4; + a += 4; + b += 4; + n -= 4; + } +} + /* Using vctp32q_m instead of vctp32q. */ void test11 (int32_t *a, int32_t *b, int32_t *c, int n, mve_pred16_t p0) {