AMDGPU: allow specifying a workgroup size that needs to fit in a compute unit

Summary:
For GL_ARB_compute_shader we need to support workgroup sizes of at least 1024. However, if we want to allow large workgroup sizes, we may need to use less registers, as we have to run more waves per SIMD.

This patch adds an attribute to specify the maximum work group size the compiled program needs to support. It defaults, to 256, as that has no wave restrictions.

Reducing the number of registers available is done similarly to how the registers were reserved for chips with the sgpr init bug.

Reviewers: mareko, arsenm, tstellarAMD, nhaehnle

Subscribers: FireBurn, kerberizer, llvm-commits, arsenm

Differential Revision: http://reviews.llvm.org/D18340

Patch By: Bas Nieuwenhuizen

llvm-svn: 266337

2 files changed, 113 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/large-work-group-promote-alloca.ll b/llvm/test/CodeGen/AMDGPU/large-work-group-promote-alloca.ll
new file mode 100644
index 00000000000..fefca0f0d4e
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/large-work-group-promote-alloca.ll
@@ -0,0 +1,72 @@
+; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-promote-alloca < %s | FileCheck %s
+
+; CHECK: @promote_alloca_size_63.stack = internal unnamed_addr addrspace(3) global [63 x [5 x i32]] undef, align 4
+
+define void @promote_alloca_size_63(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 {
+entry:
+  %stack = alloca [5 x i32], align 4
+  %0 = load i32, i32 addrspace(1)* %in, align 4
+  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
+  store i32 4, i32* %arrayidx1, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
+  %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
+  store i32 5, i32* %arrayidx3, align 4
+  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
+  %2 = load i32, i32* %arrayidx10, align 4
+  store i32 %2, i32 addrspace(1)* %out, align 4
+  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
+  %3 = load i32, i32* %arrayidx12
+  %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
+  store i32 %3, i32 addrspace(1)* %arrayidx13
+  ret void
+}
+
+; CHECK: @promote_alloca_size_256.stack = internal unnamed_addr addrspace(3) global [256 x [5 x i32]] undef, align 4
+
+define void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #1 {
+entry:
+  %stack = alloca [5 x i32], align 4
+  %0 = load i32, i32 addrspace(1)* %in, align 4
+  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
+  store i32 4, i32* %arrayidx1, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
+  %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
+  store i32 5, i32* %arrayidx3, align 4
+  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
+  %2 = load i32, i32* %arrayidx10, align 4
+  store i32 %2, i32 addrspace(1)* %out, align 4
+  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
+  %3 = load i32, i32* %arrayidx12
+  %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
+  store i32 %3, i32 addrspace(1)* %arrayidx13
+  ret void
+}
+
+; CHECK: @promote_alloca_size_1600.stack = internal unnamed_addr addrspace(3) global [1600 x [5 x i32]] undef, align 4
+
+define void @promote_alloca_size_1600(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #2 {
+entry:
+  %stack = alloca [5 x i32], align 4
+  %0 = load i32, i32 addrspace(1)* %in, align 4
+  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
+  store i32 4, i32* %arrayidx1, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
+  %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
+  store i32 5, i32* %arrayidx3, align 4
+  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
+  %2 = load i32, i32* %arrayidx10, align 4
+  store i32 %2, i32 addrspace(1)* %out, align 4
+  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
+  %3 = load i32, i32* %arrayidx12
+  %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
+  store i32 %3, i32 addrspace(1)* %arrayidx13
+  ret void
+}
+
+attributes #0 = { nounwind "amdgpu-max-work-group-size"="63" }
+attributes #1 = { nounwind "amdgpu-max-work-group-size"="256" }
+attributes #2 = { nounwind "amdgpu-max-work-group-size"="1600" }
+
diff --git a/llvm/test/CodeGen/AMDGPU/large-work-group-registers.ll b/llvm/test/CodeGen/AMDGPU/large-work-group-registers.ll
new file mode 100644
index 00000000000..8a2fcb70cb6
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/large-work-group-registers.ll
@@ -0,0 +1,41 @@
+; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck %s
+
+; CHECK: NumVgprs: 63
+define void @main([9 x <16 x i8>] addrspace(2)* byval, [17 x <16 x i8>] addrspace(2)* byval, [17 x <8 x i32>] addrspace(2)* byval, [16 x <8 x i32>] addrspace(2)* byval, [16 x <4 x i32>] addrspace(2)* byval, <3 x i32> inreg, <3 x i32> inreg, <3 x i32>) #0 {
+main_body:
+  %8 = getelementptr [16 x <4 x i32>], [16 x <4 x i32>] addrspace(2)* %4, i64 0, i64 8
+  %9 = load <4 x i32>, <4 x i32> addrspace(2)* %8, align 16, !tbaa !0
+  %10 = extractelement <3 x i32> %7, i32 0
+  %11 = extractelement <3 x i32> %7, i32 1
+  %12 = mul i32 %10, %11
+  %bc = bitcast <3 x i32> %7 to <3 x float>
+  %13 = extractelement <3 x float> %bc, i32 1
+  %14 = insertelement <512 x float> undef, float %13, i32 %12
+  call void @llvm.amdgcn.s.barrier()
+  %15 = extractelement <3 x i32> %6, i32 0
+  %16 = extractelement <3 x i32> %7, i32 0
+  %17 = shl i32 %15, 5
+  %18 = add i32 %17, %16
+  %19 = shl i32 %18, 4
+  %20 = extractelement <3 x i32> %7, i32 1
+  %21 = shl i32 %20, 2
+  %22 = sext i32 %21 to i64
+  %23 = getelementptr i8, i8 addrspace(3)* null, i64 %22
+  %24 = bitcast i8 addrspace(3)* %23 to i32 addrspace(3)*
+  %25 = load i32, i32 addrspace(3)* %24, align 4
+  %26 = extractelement <512 x float> %14, i32 %25
+  %27 = insertelement <4 x float> undef, float %26, i32 0
+  call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %27, <4 x i32> %9, i32 0, i32 %19, i1 false, i1 false)
+  ret void
+}
+
+declare void @llvm.amdgcn.s.barrier() #1
+
+declare void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float>, <4 x i32>, i32, i32, i1, i1) #2
+
+attributes #0 = { "amdgpu-max-work-group-size"="1024" }
+attributes #1 = { convergent nounwind }
+attributes #2 = { nounwind }
+
+!0 = !{!1, !1, i64 0, i32 1}
+!1 = !{!"const", null}