diff options
| -rw-r--r-- | src/intel/compiler/brw_eu_emit.c | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/src/intel/compiler/brw_eu_emit.c b/src/intel/compiler/brw_eu_emit.c index e10b1432b5e..a18cfa4239f 100644 --- a/src/intel/compiler/brw_eu_emit.c +++ b/src/intel/compiler/brw_eu_emit.c @@ -3404,7 +3404,7 @@ brw_broadcast(struct brw_codegen *p, if (align1) { const struct brw_reg addr = retype(brw_address_reg(0), BRW_REGISTER_TYPE_UD); - const unsigned offset = src.nr * REG_SIZE + src.subnr; + unsigned offset = src.nr * REG_SIZE + src.subnr; /* Limit in bytes of the signed indirect addressing immediate. */ const unsigned limit = 512; @@ -3422,15 +3422,16 @@ brw_broadcast(struct brw_codegen *p, * addressing immediate, account for the difference if the source * register is above this limit. */ - if (offset >= limit) + if (offset >= limit) { brw_ADD(p, addr, addr, brw_imm_ud(offset - offset % limit)); + offset = offset % limit; + } brw_pop_insn_state(p); /* Use indirect addressing to fetch the specified component. */ brw_MOV(p, dst, - retype(brw_vec1_indirect(addr.subnr, offset % limit), - src.type)); + retype(brw_vec1_indirect(addr.subnr, offset), src.type)); } else { /* In SIMD4x2 mode the index can be either zero or one, replicate it * to all bits of a flag register, |