From 7d06ffff466d50ba7e65c154749bc4aea120a907 Mon Sep 17 00:00:00 2001 From: Jay Foad Date: Fri, 19 Jul 2019 08:40:37 +0000 Subject: [AMDGPU] Simplify the exclusive scan used for optimized atomics Summary: Change the scan algorithm to use only power-of-two shifts (1, 2, 4, 8, 16, 32) instead of starting off shifting by 1, 2 and 3 and then doing a 3-way ADD, because: 1. It simplifies the compiler a little. 2. It minimizes vgpr pressure because each instruction is now of the form vn = vn + vn << c. 3. It is more friendly to the DPP combiner, which currently can't combine into an ADD3 instruction. Because of #2 and #3 the end result is improved from this: v_add_u32_dpp v4, v3, v3 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 v_mov_b32_dpp v5, v3 row_shr:2 row_mask:0xf bank_mask:0xf v_mov_b32_dpp v1, v3 row_shr:3 row_mask:0xf bank_mask:0xf v_add3_u32 v1, v4, v5, v1 s_nop 1 v_add_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xe s_nop 1 v_add_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xc s_nop 1 v_add_u32_dpp v1, v1, v1 row_bcast:15 row_mask:0xa bank_mask:0xf s_nop 1 v_add_u32_dpp v1, v1, v1 row_bcast:31 row_mask:0xc bank_mask:0xf To this: v_add_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 s_nop 1 v_add_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 s_nop 1 v_add_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xe s_nop 1 v_add_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xc s_nop 1 v_add_u32_dpp v1, v1, v1 row_bcast:15 row_mask:0xa bank_mask:0xf s_nop 1 v_add_u32_dpp v1, v1, v1 row_bcast:31 row_mask:0xc bank_mask:0xf I.e. two fewer computational instructions, one extra nop where we could schedule something else. Reviewers: arsenm, sheredom, critson, rampitec, vpykhtin Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D64411 llvm-svn: 366543 --- llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll | 2 -- 1 file changed, 2 deletions(-) (limited to 'llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll') diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll index 88824aa64ee..41240344493 100644 --- a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll +++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll @@ -47,7 +47,6 @@ entry: ; GFX8MORE: v_mov_b32_dpp v[[wave_shr1:[0-9]+]], v{{[0-9]+}} wave_shr:1 row_mask:0xf bank_mask:0xf ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:1 row_mask:0xf bank_mask:0xf ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:2 row_mask:0xf bank_mask:0xf -; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:3 row_mask:0xf bank_mask:0xf ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:4 row_mask:0xf bank_mask:0xe ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:8 row_mask:0xf bank_mask:0xc ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_bcast:15 row_mask:0xa bank_mask:0xf @@ -115,7 +114,6 @@ entry: ; GFX8MORE: v_mov_b32_dpp v[[wave_shr1:[0-9]+]], v{{[0-9]+}} wave_shr:1 row_mask:0xf bank_mask:0xf ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:1 row_mask:0xf bank_mask:0xf ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:2 row_mask:0xf bank_mask:0xf -; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:3 row_mask:0xf bank_mask:0xf ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:4 row_mask:0xf bank_mask:0xe ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:8 row_mask:0xf bank_mask:0xc ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_bcast:15 row_mask:0xa bank_mask:0xf -- cgit v1.2.3