Llama 3.1 8B F16 Non-Decomposed prefill fails to compile

[aviator19941]

Llama 3.1 8B F16 Non-Decomposed prefill fails to compile, but it was able to compile last week. It seems like the IR changed quite a bit, so I'm not sure if that has something to do with it.

IR from last week (COMPILES): https://gist.github.com/aviator19941/3443ef2f383a18f11659f979879ac4d7

IR from yesterday (FAILS): https://gist.github.com/aviator19941/e67f9c479400654596571cd50d905fda

compile command:
iree-compile f16_torch_prefill.mlir --iree-hip-target=gfx942 --iree-hal-target-backends=rocm -o=f16_torch_prefill.vmfb --iree-hal-dump-executable-files-to=files --iree-dispatch-creation-enable-aggressive-fusion=true --iree-global-opt-propagate-transposes=true --iree-opt-aggressively-propagate-transposes=true --iree-opt-data-tiling=false --iree-preprocessing-pass-pipeline='builtin.module(util.func(iree-preprocessing-generalize-linalg-matmul-experimental))' --iree-hal-force-indirect-command-buffers=true --iree-stream-resource-memory-model=discrete --iree-hip-legacy-sync=false