[clang] [llvm] [AMDGPU] Add GFX12 WMMA and SWMMAC instructions (PR #77795)

[Mirko Brkušanin via llvm-commits]

================
@@ -423,6 +423,67 @@ TARGET_BUILTIN(__builtin_amdgcn_s_wakeup_barrier, "vi", "n", "gfx12-insts")
 TARGET_BUILTIN(__builtin_amdgcn_s_barrier_leave, "b", "n", "gfx12-insts")
 TARGET_BUILTIN(__builtin_amdgcn_s_get_barrier_state, "Uii", "n", "gfx12-insts")
 
+//===----------------------------------------------------------------------===//
+// WMMA builtins.
+// Postfix w32 indicates the builtin requires wavefront size of 32.
+// Postfix w64 indicates the builtin requires wavefront size of 64.
+//
+// Some of these are very similar to their GFX11 counterparts, but they don't
+// require replication of the A,B matrices, so they use fewer vector elements.
+// Therefore, we add an "_gfx12" suffix to distinguish them from the existing
+// builtins.
+//===----------------------------------------------------------------------===//
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f32_16x16x16_f16_w32_gfx12, "V8fV8hV8hV8f", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f32_16x16x16_bf16_w32_gfx12, "V8fV8sV8sV8f", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f16_16x16x16_f16_w32_gfx12, "V8hV8hV8hV8h", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_bf16_16x16x16_bf16_w32_gfx12, "V8sV8sV8sV8s", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_i32_16x16x16_iu8_w32_gfx12, "V8iIbV2iIbV2iV8iIb", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_i32_16x16x16_iu4_w32_gfx12, "V8iIbiIbiV8iIb", "nc", "gfx12-insts,wavefrontsize32")
+// These are gfx12-only, but for consistency with the other WMMA variants we're
+// keeping the "_gfx12" suffix.
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f32_16x16x16_fp8_fp8_w32_gfx12, "V8fV2iV2iV8f", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f32_16x16x16_fp8_bf8_w32_gfx12, "V8fV2iV2iV8f", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f32_16x16x16_bf8_fp8_w32_gfx12, "V8fV2iV2iV8f", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f32_16x16x16_bf8_bf8_w32_gfx12, "V8fV2iV2iV8f", "nc", "gfx12-insts,wavefrontsize32")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_i32_16x16x32_iu4_w32_gfx12, "V8iIbV2iIbV2iV8iIb", "nc", "gfx12-insts,wavefrontsize32")
+
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f32_16x16x16_f16_w64_gfx12, "V4fV4hV4hV4f", "nc", "gfx12-insts,wavefrontsize64")
+TARGET_BUILTIN(__builtin_amdgcn_wmma_f32_16x16x16_bf16_w64_gfx12, "V4fV4sV4sV4f", "nc", "gfx12-insts,wavefrontsize64")
----------------
mbrkusanin wrote:

Updated to bfloat but GlobalISel does not handle it properly yet. Should we use i16 for now until we update GlobalISel?

https://github.com/llvm/llvm-project/pull/77795