AMDGPU: Add baseline test for split/widen invariant loads

[arsenm]

This works fine on main, but broke after a future patch.

[arsenm]

• AMDGPU: Fix treating unknown mem operands as uniform #168980
• AMDGPU: Use ConstantPool as source value for DAG lowered kernarg loads #168917
• AMDGPU: Handle invariant when lowering global loads #168914
• AMDGPU: Add baseline test for split/widen invariant loads #168913 👈 (View in Graphite)
• AMDGPU: Handle invariant loads when considering if a load can be scalar #168787
• Reapply "DAG: Allow select ptr combine for non-0 address spaces" (#168292) #168786
• AMDGPU: Fix treating divergent loads as uniform #168785
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[llvmbot]

@llvm/pr-subscribers-backend-amdgpu

Author: Matt Arsenault (arsenm)

Changes

---

Full diff: https://github.com/llvm/llvm-project/pull/168913.diff

1 Files Affected:

• (added) llvm/test/CodeGen/AMDGPU/load-global-invariant.ll (+70)

diff --git a/llvm/test/CodeGen/AMDGPU/load-global-invariant.ll b/llvm/test/CodeGen/AMDGPU/load-global-invariant.ll
new file mode 100644
index 0000000000000..b881edde0f448
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/load-global-invariant.ll
@@ -0,0 +1,70 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s
+
+; Check that invariant global loads are treated like constant
+; loads. The optnone disables the annotation of of amdgpu.noclobber.
+
+define amdgpu_kernel void @load_constant_v3i64(ptr addrspace(1) %dst, ptr addrspace(4) %src) #0 {
+; CHECK-LABEL: load_constant_v3i64:
+; CHECK:       ; %bb.0:
+; CHECK-NEXT:    v_mov_b32_e32 v4, 0
+; CHECK-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x0
+; CHECK-NEXT:    s_load_dwordx2 s[6:7], s[8:9], 0x8
+; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
+; CHECK-NEXT:    s_load_dwordx4 s[0:3], s[6:7], 0x0
+; CHECK-NEXT:    s_nop 0
+; CHECK-NEXT:    s_load_dwordx2 s[6:7], s[6:7], 0x10
+; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
+; CHECK-NEXT:    v_mov_b32_e32 v0, s6
+; CHECK-NEXT:    v_mov_b32_e32 v1, s7
+; CHECK-NEXT:    global_store_dwordx2 v4, v[0:1], s[4:5] offset:16
+; CHECK-NEXT:    v_mov_b32_e32 v0, s0
+; CHECK-NEXT:    v_mov_b32_e32 v1, s1
+; CHECK-NEXT:    v_mov_b32_e32 v2, s2
+; CHECK-NEXT:    v_mov_b32_e32 v3, s3
+; CHECK-NEXT:    global_store_dwordx4 v4, v[0:3], s[4:5]
+; CHECK-NEXT:    s_endpgm
+  %ld = load <3 x i64>, ptr addrspace(4) %src, align 32
+  store <3 x i64> %ld, ptr addrspace(1) %dst, align 32
+  ret void
+}
+
+define amdgpu_kernel void @load_global_v3i64(ptr addrspace(1) %dst, ptr addrspace(1) %src) #0 {
+; CHECK-LABEL: load_global_v3i64:
+; CHECK:       ; %bb.0:
+; CHECK-NEXT:    v_mov_b32_e32 v6, 0
+; CHECK-NEXT:    s_load_dwordx2 s[0:1], s[8:9], 0x0
+; CHECK-NEXT:    s_load_dwordx2 s[2:3], s[8:9], 0x8
+; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
+; CHECK-NEXT:    global_load_dwordx4 v[0:3], v6, s[2:3]
+; CHECK-NEXT:    global_load_dwordx2 v[4:5], v6, s[2:3] offset:16
+; CHECK-NEXT:    s_waitcnt vmcnt(0)
+; CHECK-NEXT:    global_store_dwordx2 v6, v[4:5], s[0:1] offset:16
+; CHECK-NEXT:    global_store_dwordx4 v6, v[0:3], s[0:1]
+; CHECK-NEXT:    s_endpgm
+  %ld = load <3 x i64>, ptr addrspace(1) %src, align 32
+  store <3 x i64> %ld, ptr addrspace(1) %dst, align 32
+  ret void
+}
+
+define amdgpu_kernel void @load_global_v3i64_invariant(ptr addrspace(1) %dst, ptr addrspace(1) %src) #0 {
+; CHECK-LABEL: load_global_v3i64_invariant:
+; CHECK:       ; %bb.0:
+; CHECK-NEXT:    v_mov_b32_e32 v6, 0
+; CHECK-NEXT:    s_load_dwordx2 s[0:1], s[8:9], 0x0
+; CHECK-NEXT:    s_load_dwordx2 s[2:3], s[8:9], 0x8
+; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
+; CHECK-NEXT:    global_load_dwordx4 v[0:3], v6, s[2:3]
+; CHECK-NEXT:    global_load_dwordx2 v[4:5], v6, s[2:3] offset:16
+; CHECK-NEXT:    s_waitcnt vmcnt(0)
+; CHECK-NEXT:    global_store_dwordx2 v6, v[4:5], s[0:1] offset:16
+; CHECK-NEXT:    global_store_dwordx4 v6, v[0:3], s[0:1]
+; CHECK-NEXT:    s_endpgm
+  %ld = load <3 x i64>, ptr addrspace(1) %src, align 32, !invariant.load !0
+  store <3 x i64> %ld, ptr addrspace(1) %dst, align 32
+  ret void
+}
+
+attributes #0 = { noinline nounwind optnone }
+
+!0 = !{}

[github-actions]

🐧 Linux x64 Test Results

• 186428 tests passed
• 4868 tests skipped