[PowerPC] Add DMF basic builtins (#145372)

Add support for PPC Dense Math basic builtins dmsetdmrz, dmmr, dmxor.

Author: RolandF77

clang/include/clang/Basic/BuiltinsPPC.def

@@ -1092,6 +1092,12 @@ UNALIASED_CUSTOM_BUILTIN(mma_dmxvi8gerx4spp, "vW1024*W256V", true,
                          "mma,paired-vector-memops")
 UNALIASED_CUSTOM_BUILTIN(mma_pmdmxvi8gerx4spp, "vW1024*W256Vi255i15i15", true,
                          "mma,paired-vector-memops")
+UNALIASED_CUSTOM_BUILTIN(mma_dmsetdmrz, "vW1024*", false,
+                         "mma,isa-future-instructions")
+UNALIASED_CUSTOM_BUILTIN(mma_dmmr, "vW1024*W1024*", false,
+                         "mma,isa-future-instructions")
+UNALIASED_CUSTOM_BUILTIN(mma_dmxor, "vW1024*W1024*", true,
+                         "mma,isa-future-instructions")
 
 // MMA builtins with positive/negative multiply/accumulate.
 UNALIASED_CUSTOM_MMA_BUILTIN(mma_xvf16ger2, "vW512*VV",

clang/lib/CodeGen/TargetBuiltins/PPC.cpp

@@ -1151,6 +1151,11 @@ Value *CodeGenFunction::EmitPPCBuiltinExpr(unsigned BuiltinID,
       Value *Acc = Builder.CreateLoad(Addr);
       CallOps.push_back(Acc);
     }
+    if (BuiltinID == PPC::BI__builtin_mma_dmmr ||
+        BuiltinID == PPC::BI__builtin_mma_dmxor) {
+      Address Addr = EmitPointerWithAlignment(E->getArg(1));
+      Ops[1] = Builder.CreateLoad(Addr);
+    }
     for (unsigned i=1; i<Ops.size(); i++)
       CallOps.push_back(Ops[i]);
     llvm::Function *F = CGM.getIntrinsic(ID);

clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c

@@ -92,3 +92,19 @@ void test_pmdmxvi8gerx4spp(unsigned char *vdmrp, unsigned char *vpp, vector unsi
   __builtin_mma_pmdmxvi8gerx4spp(&vdmr, vp, vc, 0, 0, 0);
   *((__dmr1024 *)resp) = vdmr;
 }
+
+// CHECK-LABEL: @test_dmf_basic
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmsetdmrz()
+// CHECK-NEXT: [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmmr(<1024 x i1> [[TMP0]])
+// CHECK-NEXT: store <1024 x i1> [[TMP1]], ptr %res1, align 128
+// CHECK-NEXT: [[TMP2:%.*]] = load <1024 x i1>, ptr %res2, align 128
+// CHECK-NEXT: [[TMP3:%.*]] = load <1024 x i1>, ptr %p, align 128
+// CHECK-NEXT: [[TMP4:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxor(<1024 x i1> [[TMP2]], <1024 x i1> [[TMP3]])
+// CHECK-NEXT: store <1024 x i1> [[TMP4]], ptr %res2, align 128
+void test_dmf_basic(char *p, char *res1, char *res2) {
+  __dmr1024 x[2];
+  __builtin_mma_dmsetdmrz(&x[0]);
+  __builtin_mma_dmmr((__dmr1024*)res1, &x[0]);
+  __builtin_mma_dmxor((__dmr1024*)res2, (__dmr1024*)p);
+}

clang/test/CodeGen/PowerPC/ppc-dmf-future-builtin-err.c

@@ -0,0 +1,15 @@
+// RUN: not %clang_cc1 -triple powerpc64le-unknown-linux-gnu -target-cpu pwr10 \
+// RUN:   %s -emit-llvm-only 2>&1 | FileCheck %s
+
+__attribute__((target("no-mma")))
+void test_mma(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmsetdmrz(&vdmr);
+  __builtin_mma_dmmr(&vdmr, (__dmr1024*)vpp);
+  __builtin_mma_dmxor(&vdmr, (__dmr1024*)vpp);
+
+// CHECK: error: '__builtin_mma_dmsetdmrz' needs target feature mma,isa-future-instructions
+// CHECK: error: '__builtin_mma_dmmr' needs target feature mma,isa-future-instructions
+// CHECK: error: '__builtin_mma_dmxor' needs target feature mma,isa-future-instructions
+}

clang/test/CodeGen/PowerPC/ppc-future-mma-builtin-err.c renamed to clang/test/CodeGen/PowerPC/ppc-dmf-mma-builtin-err.c

@@ -11,11 +11,17 @@ void test_mma(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc)
   __builtin_mma_pmdmxvi8gerx4pp(&vdmr, vp, vc, 0, 0, 0);
   __builtin_mma_dmxvi8gerx4spp(&vdmr, vp, vc);
   __builtin_mma_pmdmxvi8gerx4spp(&vdmr, vp, vc, 0, 0, 0);
+  __builtin_mma_dmsetdmrz(&vdmr);
+  __builtin_mma_dmmr(&vdmr, (__dmr1024*)vpp);
+  __builtin_mma_dmxor(&vdmr, (__dmr1024*)vpp);
 
 // CHECK: error: '__builtin_mma_dmxvi8gerx4' needs target feature mma,paired-vector-memops
 // CHECK: error: '__builtin_mma_pmdmxvi8gerx4' needs target feature mma,paired-vector-memops
 // CHECK: error: '__builtin_mma_dmxvi8gerx4pp' needs target feature mma,paired-vector-memops
 // CHECK: error: '__builtin_mma_pmdmxvi8gerx4pp' needs target feature mma,paired-vector-memops
 // CHECK: error: '__builtin_mma_dmxvi8gerx4spp' needs target feature mma,paired-vector-memops
 // CHECK: error: '__builtin_mma_pmdmxvi8gerx4spp' needs target feature mma,paired-vector-memops
+// CHECK: error: '__builtin_mma_dmsetdmrz' needs target feature mma,isa-future-instructions
+// CHECK: error: '__builtin_mma_dmmr' needs target feature mma,isa-future-instructions
+// CHECK: error: '__builtin_mma_dmxor' needs target feature mma,isa-future-instructions
 }