pitlit shader/fp-long-alu.c tests very long fragment programs and uses 16384 as max (native) ALU instructions. It fails on 965 in brw_eu_emit.c: next_insn: assert(p->nr_insn + 1 < BRW_EU_MAX_INSN) BRW_EU_MAX_INSN has been increased from 1200 to 4000 ( 2eacc4aa in 2009.3) to 10000 (5590798f in 2009.5). Is there a true limit? Here's the result of shader/fp-long-alu on 965: fp-long-alu: brw_eu_emit.c:488: next_insn: Assertion `p->nr_insn + 1 < 10000' failed. Output: Max (native) ALU instructions: 16384 Testing: alu_depth = 1 Testing: alu_depth = 2 Testing: alu_depth = 3 Testing: alu_depth = 4 Testing: alu_depth = 5 Testing: alu_depth = 6 Testing: alu_depth = 7 Testing: alu_depth = 8 Testing: alu_depth = 11 Testing: alu_depth = 17 Testing: alu_depth = 29 Testing: alu_depth = 53 Testing: alu_depth = 101 Testing: alu_depth = 197 Testing: alu_depth = 389 Testing: alu_depth = 773 Testing: alu_depth = 1541 Testing: alu_depth = 3077
*** This bug has been marked as a duplicate of bug 24355 ***
verified it passes now: Max (native) ALU instructions: 16384 Testing: alu_depth = 1 Testing: alu_depth = 2 Testing: alu_depth = 3 Testing: alu_depth = 4 Testing: alu_depth = 5 Testing: alu_depth = 6 Testing: alu_depth = 7 Testing: alu_depth = 8 Testing: alu_depth = 11 Testing: alu_depth = 17 Testing: alu_depth = 29 Testing: alu_depth = 53 Testing: alu_depth = 101 Testing: alu_depth = 197 Testing: alu_depth = 389 Testing: alu_depth = 773 Testing: alu_depth = 1541 Testing: alu_depth = 3077 Testing: alu_depth = 6149 Testing: alu_depth = 12293 PIGLIT: {'result': 'pass' }
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.