[PATCH] D23460: [NVPTX] Use untyped (.b) integer registers in PTX.

Artem Belevich via llvm-commits llvm-commits at lists.llvm.org
Fri Aug 12 11:31:03 PDT 2016


tra created this revision.
tra added reviewers: jholewinski, jlebar.
tra added a subscriber: llvm-commits.
Herald added a subscriber: jholewinski.

This brings LLVM-generated PTX closer to what nvcc generates and avoids
triggering issues in ptxas.

For instance, ptxas does not accept .s16 (or .u16) registers as operands
for .fp16 instructions.

https://reviews.llvm.org/D23460

Files:
  lib/Target/NVPTX/NVPTXRegisterInfo.cpp
  test/CodeGen/NVPTX/reg-types.ll

Index: test/CodeGen/NVPTX/reg-types.ll
===================================================================
--- /dev/null
+++ test/CodeGen/NVPTX/reg-types.ll
@@ -0,0 +1,64 @@
+; Verify register types we generate in PTX.
+; RUN: llc -O0 < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
+; RUN: llc -O0 < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s
+
+; CHECK-LABEL: .visible .func func()
+define void @func() {
+entry:
+  %s8 = alloca i8, align 1
+  %u8 = alloca i8, align 1
+  %s16 = alloca i16, align 2
+  %u16 = alloca i16, align 2
+; Both 8- and 16-bit integers are packed into 16-bit registers.
+; CHECK-DAG .reg .b16 %rs<
+  %s32 = alloca i32, align 4
+  %u32 = alloca i32, align 4
+; CHECK-DAG: .reg .b32 %r<
+  %s64 = alloca i64, align 8
+  %u64 = alloca i64, align 8
+; CHECK-DAG: .reg .b64 %rd<
+  %f32 = alloca float, align 4
+; CHECK-DAG: .reg .f32 %f<
+  %f64 = alloca double, align 8
+; CHECK-DAG: .reg .f64 %fd<
+
+; It's hard to check that we *didn't* generate .reg .b8 above.
+; We'll check that we use 16-bit registers for 8-bit stores.
+  store i8 1, i8* %s8, align 1
+; CHECK: mov.u16 [[R1:%rs[0-9]]], 1;
+; CHECK-NEXT: st.u8 {{.*}}, [[R1]]
+  store i8 2, i8* %u8, align 1
+; CHECK: mov.u16 [[R2:%rs[0-9]]], 2;
+; CHECK-NEXT: st.u8 {{.*}}, [[R2]]
+  store i16 3, i16* %s16, align 2
+; CHECK: mov.u16 [[R3:%rs[0-9]]], 3;
+; CHECK-NEXT: st.u16 {{.*}}, [[R3]]
+  store i16 4, i16* %u16, align 2
+; CHECK: mov.u16 [[R4:%rs[0-9]]], 4;
+; CHECK-NEXT: st.u16 {{.*}}, [[R4]]
+  store i32 5, i32* %s32, align 4
+; CHECK: mov.u32 [[R5:%r[0-9]]], 5;
+; CHECK-NEXT: st.u32 {{.*}}, [[R5]]
+  store i32 6, i32* %u32, align 4
+; CHECK: mov.u32 [[R6:%r[0-9]]], 6;
+; CHECK-NEXT: st.u32 {{.*}}, [[R6]]
+  store i64 7, i64* %s64, align 8
+; CHECK: mov.u64 [[R7:%rd[0-9]]], 7;
+; CHECK-NEXT: st.u64 {{.*}}, [[R7]]
+  store i64 8, i64* %u64, align 8
+; CHECK: mov.u64 [[R8:%rd[0-9]]], 8;
+; CHECK-NEXT: st.u64 {{.*}}, [[R8]]
+
+; FP constants are stored via integer registers, but that's an
+; implementation detail that's irrelevant here.
+  store float 9.000000e+00, float* %f32, align 4
+  store double 1.000000e+01, double* %f64, align 8
+; Instead, we force a load into a register and then verify register type.
+  %f32v = load volatile float, float* %f32, align 4
+; CHECK: ld.volatile.f32         %f{{[0-9]+}}
+  %f64v = load volatile double, double* %f64, align 8
+; CHECK: ld.volatile.f64         %fd{{[0-9]+}}
+  ret void
+; CHECK: ret;
+}
+
Index: lib/Target/NVPTX/NVPTXRegisterInfo.cpp
===================================================================
--- lib/Target/NVPTX/NVPTXRegisterInfo.cpp
+++ lib/Target/NVPTX/NVPTXRegisterInfo.cpp
@@ -33,11 +33,11 @@
   if (RC == &NVPTX::Float64RegsRegClass) {
     return ".f64";
   } else if (RC == &NVPTX::Int64RegsRegClass) {
-    return ".s64";
+    return ".b64";
   } else if (RC == &NVPTX::Int32RegsRegClass) {
-    return ".s32";
+    return ".b32";
   } else if (RC == &NVPTX::Int16RegsRegClass) {
-    return ".s16";
+    return ".b16";
   } else if (RC == &NVPTX::Int1RegsRegClass) {
     return ".pred";
   } else if (RC == &NVPTX::SpecialRegsRegClass) {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D23460.67869.patch
Type: text/x-patch
Size: 3118 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160812/d73c5573/attachment.bin>


More information about the llvm-commits mailing list