https://gcc.gnu.org/g:d7d05824ae68da24908d97a10b9ec59d08f75a90
commit r14-9486-gd7d05824ae68da24908d97a10b9ec59d08f75a90 Author: Chenghui Pan <pancheng...@loongson.cn> Date: Thu Mar 14 09:26:54 2024 +0800 LoongArch: Remove masking process for operand 3 of xvpermi.q. The behavior of non-zero unused bits in xvpermi.q instruction's third operand is undefined on LoongArch, according to our discussion (https://github.com/llvm/llvm-project/pull/83540), we think that keeping original insn operand as unmodified state is better solution. This patch partially reverts 7b158e036a95b1ab40793dd53bed7dbd770ffdaf. gcc/ChangeLog: * config/loongarch/lasx.md (lasx_xvpermi_q_<LASX:mode>): Remove masking of operand 3. gcc/testsuite/ChangeLog: * gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c: Reposition operand 3's value into instruction's defined accept range. Diff: --- gcc/config/loongarch/lasx.md | 5 ----- gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c | 6 +++--- 2 files changed, 3 insertions(+), 8 deletions(-) diff --git a/gcc/config/loongarch/lasx.md b/gcc/config/loongarch/lasx.md index ac84db7f0ce..3f25c0c1756 100644 --- a/gcc/config/loongarch/lasx.md +++ b/gcc/config/loongarch/lasx.md @@ -640,8 +640,6 @@ (set_attr "mode" "<MODE>")]) ;; xvpermi.q -;; Unused bits in operands[3] need be set to 0 to avoid -;; causing undefined behavior on LA464. (define_insn "lasx_xvpermi_q_<LASX:mode>" [(set (match_operand:LASX 0 "register_operand" "=f") (unspec:LASX @@ -651,9 +649,6 @@ UNSPEC_LASX_XVPERMI_Q))] "ISA_HAS_LASX" { - int mask = 0x33; - mask &= INTVAL (operands[3]); - operands[3] = GEN_INT (mask); return "xvpermi.q\t%u0,%u2,%3"; } [(set_attr "type" "simd_splat") diff --git a/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c b/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c index dbc29d2fb22..f89dfc31120 100644 --- a/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c +++ b/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c @@ -27,7 +27,7 @@ main () *((unsigned long*)& __m256i_result[2]) = 0x7fff7fff7fff0000; *((unsigned long*)& __m256i_result[1]) = 0x7fe37fe3001d001d; *((unsigned long*)& __m256i_result[0]) = 0x7fff7fff7fff0000; - __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0x2a); + __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0x22); ASSERTEQ_64 (__LINE__, __m256i_result, __m256i_out); *((unsigned long*)& __m256i_op0[3]) = 0x0000000000000000; @@ -42,7 +42,7 @@ main () *((unsigned long*)& __m256i_result[2]) = 0x000000000019001c; *((unsigned long*)& __m256i_result[1]) = 0x0000000000000000; *((unsigned long*)& __m256i_result[0]) = 0x00000000000001fe; - __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0xb9); + __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0x31); ASSERTEQ_64 (__LINE__, __m256i_result, __m256i_out); *((unsigned long*)& __m256i_op0[3]) = 0x00ff00ff00ff00ff; @@ -57,7 +57,7 @@ main () *((unsigned long*)& __m256i_result[2]) = 0xffff0000ffff0000; *((unsigned long*)& __m256i_result[1]) = 0x00ff00ff00ff00ff; *((unsigned long*)& __m256i_result[0]) = 0x00ff00ff00ff00ff; - __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0xca); + __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0x02); ASSERTEQ_64 (__LINE__, __m256i_result, __m256i_out); return 0;