[PowerPC] Add DMF basic builtins #145372
Open
[PowerPC] Add DMF basic builtins #145372
+27
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
llvmbot
added
clang
|
@llvm/pr-subscribers-clang @llvm/pr-subscribers-backend-powerpc Author: None (RolandF77) ChangesAdd support for PPC Dense Math basic builtins dmsetdmrz, dmmr, dmxor. Full diff: https://github.com/llvm/llvm-project/pull/145372.diff 3 Files Affected:
diff --git a/clang/include/clang/Basic/BuiltinsPPC.def b/clang/include/clang/Basic/BuiltinsPPC.def
index 099500754a0e0..7f4dc9fe4f719 100644
--- a/clang/include/clang/Basic/BuiltinsPPC.def
+++ b/clang/include/clang/Basic/BuiltinsPPC.def
@@ -1146,6 +1146,12 @@ 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,paired-vector-memops")
+UNALIASED_CUSTOM_BUILTIN(mma_dmmr, "vW1024*W1024*", false,
+ "mma,paired-vector-memops")
+UNALIASED_CUSTOM_BUILTIN(mma_dmxor, "vW1024*W1024*", true,
+ "mma,paired-vector-memops")
// FIXME: Obviously incomplete.
diff --git a/clang/lib/CodeGen/TargetBuiltins/PPC.cpp b/clang/lib/CodeGen/TargetBuiltins/PPC.cpp
index f9890285f0aab..270e9fc976f23 100644
--- a/clang/lib/CodeGen/TargetBuiltins/PPC.cpp
+++ b/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);
diff --git a/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c b/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c
index 41f13155847ba..4aafc09602228 100644
--- a/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c
+++ b/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);
+}
|
|
@llvm/pr-subscribers-clang-codegen Author: None (RolandF77) ChangesAdd support for PPC Dense Math basic builtins dmsetdmrz, dmmr, dmxor. Full diff: https://github.com/llvm/llvm-project/pull/145372.diff 3 Files Affected:
diff --git a/clang/include/clang/Basic/BuiltinsPPC.def b/clang/include/clang/Basic/BuiltinsPPC.def
index 099500754a0e0..7f4dc9fe4f719 100644
--- a/clang/include/clang/Basic/BuiltinsPPC.def
+++ b/clang/include/clang/Basic/BuiltinsPPC.def
@@ -1146,6 +1146,12 @@ 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,paired-vector-memops")
+UNALIASED_CUSTOM_BUILTIN(mma_dmmr, "vW1024*W1024*", false,
+ "mma,paired-vector-memops")
+UNALIASED_CUSTOM_BUILTIN(mma_dmxor, "vW1024*W1024*", true,
+ "mma,paired-vector-memops")
// FIXME: Obviously incomplete.
diff --git a/clang/lib/CodeGen/TargetBuiltins/PPC.cpp b/clang/lib/CodeGen/TargetBuiltins/PPC.cpp
index f9890285f0aab..270e9fc976f23 100644
--- a/clang/lib/CodeGen/TargetBuiltins/PPC.cpp
+++ b/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);
diff --git a/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c b/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c
index 41f13155847ba..4aafc09602228 100644
--- a/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c
+++ b/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);
+}
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add support for PPC Dense Math basic builtins dmsetdmrz, dmmr, dmxor.