From 3f8e3c2bd8f54ae6817f7496be47f4e1a8860d9c Mon Sep 17 00:00:00 2001 From: Marek Olšák Date: Sun, 22 Oct 2017 15:54:23 +0200 Subject: radeonsi: add a workaround for weird s_buffer_load_dword behavior on SI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit See my LLVM patch which fixes the root cause. Users have to apply this patch and then they have 2 choices: - Downgrade to LLVM 5.0 - Update to LLVM git after my LLVM patch is pushed. It won't be possible to use current and earlier development version of LLVM 6.0. Reviewed-by: Nicolai Hähnle Cc: 17.3 --- src/gallium/drivers/radeonsi/si_shader.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'src/gallium/drivers/radeonsi/si_shader.c') diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c index 4bf2a45eebd..4456026ac81 100644 --- a/src/gallium/drivers/radeonsi/si_shader.c +++ b/src/gallium/drivers/radeonsi/si_shader.c @@ -2013,14 +2013,21 @@ static LLVMValueRef fetch_constant( * code reducing SIMD wave occupancy from 8 to 2 in many cases. * * Using s_buffer_load_dword (x1) seems to be the best option right now. + * + * LLVM 5.0 on SI doesn't insert a required s_nop between SALU setting + * a descriptor and s_buffer_load_dword using it, so we can't expand + * the pointer into a full descriptor like below. We have to use + * s_load_dword instead. The only case when LLVM 5.0 would select + * s_buffer_load_dword (that we have to prevent) is when we use use + * a literal offset where we don't need bounds checking. */ -#if 0 /* keep this codepath disabled */ - if (!reg->Register.Indirect) { + if (ctx->screen->b.chip_class == SI && + HAVE_LLVM < 0x0600 && + !reg->Register.Indirect) { addr = LLVMBuildLShr(ctx->ac.builder, addr, LLVMConstInt(ctx->i32, 2, 0), ""); LLVMValueRef result = ac_build_load_invariant(&ctx->ac, ptr, addr); return bitcast(bld_base, type, result); } -#endif /* Do the bounds checking with a descriptor, because * doing computation and manual bounds checking of 64-bit -- cgit v1.2.3