[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 ROCm#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

Change-Id: I79f792d30210974acbd67ae0c5eaff3094263281

Author: foad

lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp

@@ -385,26 +385,24 @@ void AMDGPUAtomicOptimizer::optimizeAtomic(Instruction &I,
     CallInst *const SetInactive =
         B.CreateIntrinsic(Intrinsic::amdgcn_set_inactive, Ty, {V, Identity});
 
-    CallInst *const FirstDPP =
+    ExclScan =
         B.CreateIntrinsic(Intrinsic::amdgcn_update_dpp, Ty,
                           {Identity, SetInactive, B.getInt32(DPP_WF_SR1),
                            B.getInt32(0xf), B.getInt32(0xf), B.getFalse()});
-    ExclScan = FirstDPP;
 
-    const unsigned Iters = 7;
-    const unsigned DPPCtrl[Iters] = {
-        DPP_ROW_SR1, DPP_ROW_SR2,     DPP_ROW_SR3,    DPP_ROW_SR4,
-        DPP_ROW_SR8, DPP_ROW_BCAST15, DPP_ROW_BCAST31};
-    const unsigned RowMask[Iters] = {0xf, 0xf, 0xf, 0xf, 0xf, 0xa, 0xc};
-    const unsigned BankMask[Iters] = {0xf, 0xf, 0xf, 0xe, 0xc, 0xf, 0xf};
+    const unsigned Iters = 6;
+    const unsigned DPPCtrl[Iters] = {DPP_ROW_SR1,     DPP_ROW_SR2,
+                                     DPP_ROW_SR4,     DPP_ROW_SR8,
+                                     DPP_ROW_BCAST15, DPP_ROW_BCAST31};
+    const unsigned RowMask[Iters] = {0xf, 0xf, 0xf, 0xf, 0xa, 0xc};
+    const unsigned BankMask[Iters] = {0xf, 0xf, 0xe, 0xc, 0xf, 0xf};
 
     // This loop performs an exclusive scan across the wavefront, with all lanes
     // active (by using the WWM intrinsic).
     for (unsigned Idx = 0; Idx < Iters; Idx++) {
-      Value *const UpdateValue = Idx < 3 ? FirstDPP : ExclScan;
       CallInst *const DPP = B.CreateIntrinsic(
           Intrinsic::amdgcn_update_dpp, Ty,
-          {Identity, UpdateValue, B.getInt32(DPPCtrl[Idx]),
+          {Identity, ExclScan, B.getInt32(DPPCtrl[Idx]),
            B.getInt32(RowMask[Idx]), B.getInt32(BankMask[Idx]), B.getFalse()});
 
       ExclScan = buildNonAtomicBinOp(B, Op, ExclScan, DPP);

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