Intel Ready With A Big Improvement For Battlemage With Linux 7.4

Sent out on Thursday was the last round of planned Intel Xe kernel driver improvements targeting the upcoming Linux 7.4 cycle. There is one big improvement that is set to benefit Intel discrete GPUs with at least Battlemage benefiting nicely. The major addition for the Intel Xe driver this round is implementing CPU binds and ULLS on the migration queue. While it may not sound like some enticing feature, it does come with some rather sizable performance benefits. Intel engineer Matthew Brost explained in the patch series cover letter: "On BMG, measurements show that when the GPU is continuously processing faults, copy jobs run approximately 30–40µs faster (depending on the test case) with ULLS compared to traditional GuC submission with SLPC enabled on the migration queue. Startup from a cold GPU shows an even larger speedup. Given the critical nature of fault performance, ULLS appears to be a worthwhile feature. In addition to driver telemetry, UMD compute benchmarks consistently show multiple GB/s improvement in pagefault benchmarks with ULLS enabled. ULLS will consume more power (not yet measured) due to a continuously running batch on the paging engine. However, compute UMDs already do this on engines exposed to users, so this seems like a worthwhile tradeoff. To mitigate power concerns, ULLS will exit after a period of time in which no faults have been processed. CPU binds are required for ULLS to function, as the migration queue needs exclusive access to the paging hardware engine. Thus, CPU binds are included here. Beyond being a requirement for ULLS, CPU binds should also reduce VM-bind latency, provide clearer multi-tile and TLB-invalidation layering, reduce pressure on GuC during fault storms as it is bypassed, and decouple kernel binds from unrelated copy/clear jobs—especially beneficial when faults are serviced in parallel. In a parallel-faulting test case, average bind time was reduced by approximately 15µs. In the worst case, 2MB copy time (~60–140µs) × (number of pagefault threads − 1) of latency would otherwise be added to a single fault. Reducing this latency increases overall throughput of the fault handler." Overall this ULLS for the migration queue plus CPU binds appears to be a nice win in the end. ULLS in this context is the Ultra Low Latency Scheduling. This new Xe pull request also includes a fix for ULLS for Crescent Island. The pull also includes a new Panther Lake device ID of 0xB0A1. The pull is on its way to DRM-Next for queuing ahead of the Linux 7.4 merge window later in October. Linux 7.4 stable in turn should be out around late December.