R600: Add support for SET*_DX10 instructions

These instructions compare two floating point values and return an
integer true (-1) or false (0) value.

When compiling code generated by the Mesa GLSL frontend, the SET*_DX10
instructions save us four instructions for most branch decisions that
use floating-point comparisons.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174609 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 150 insertions, 15 deletions

diff --git a/test/CodeGen/R600/fcmp.ll b/test/CodeGen/R600/fcmp.ll
index 1dcd07c0b3..89f5e9e412 100644
--- a/test/CodeGen/R600/fcmp.ll
+++ b/test/CodeGen/R600/fcmp.ll
@@ -1,8 +1,6 @@
 ;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
 
-;CHECK: SETE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-;CHECK: MOV T{{[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
-;CHECK: FLT_TO_INT T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;CHECK: SETE_DX10 T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
 define void @test(i32 addrspace(1)* %out, float addrspace(1)* %in) {
 entry:
diff --git a/test/CodeGen/R600/set-dx10.ll b/test/CodeGen/R600/set-dx10.ll
new file mode 100644
index 0000000000..54febcf0e6
--- /dev/null
+++ b/test/CodeGen/R600/set-dx10.ll
@@ -0,0 +1,137 @@
+; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
+
+; These tests check that floating point comparisons which are used by select
+; to store integer true (-1) and false (0) values are lowered to one of the
+; SET*DX10 instructions.
+
+; CHECK: @fcmp_une_select_fptosi
+; CHECK: SETNE_DX10 T{{[0-9]+\.[XYZW]}}, T{{[0-9]+\.[XYZW]}}, literal.x, 1084227584(5.000000e+00)
+define void @fcmp_une_select_fptosi(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp une float %in, 5.0
+  %1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
+  %2 = fsub float -0.000000e+00, %1
+  %3 = fptosi float %2 to i32
+  store i32 %3, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_une_select_i32
+; CHECK: SETNE_DX10 T{{[0-9]+\.[XYZW]}}, T{{[0-9]+\.[XYZW]}}, literal.x, 1084227584(5.000000e+00)
+define void @fcmp_une_select_i32(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp une float %in, 5.0
+  %1 = select i1 %0, i32 -1, i32 0
+  store i32 %1, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_ueq_select_fptosi
+; CHECK: SETE_DX10 T{{[0-9]+\.[XYZW]}}, T{{[0-9]+\.[XYZW]}}, literal.x, 1084227584(5.000000e+00)
+define void @fcmp_ueq_select_fptosi(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp ueq float %in, 5.0
+  %1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
+  %2 = fsub float -0.000000e+00, %1
+  %3 = fptosi float %2 to i32
+  store i32 %3, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_ueq_select_i32
+; CHECK: SETE_DX10 T{{[0-9]+\.[XYZW]}}, T{{[0-9]+\.[XYZW]}}, literal.x, 1084227584(5.000000e+00)
+define void @fcmp_ueq_select_i32(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp ueq float %in, 5.0
+  %1 = select i1 %0, i32 -1, i32 0
+  store i32 %1, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_ugt_select_fptosi
+; CHECK: SETGT_DX10 T{{[0-9]+\.[XYZW]}}, T{{[0-9]+\.[XYZW]}}, literal.x, 1084227584(5.000000e+00)
+define void @fcmp_ugt_select_fptosi(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp ugt float %in, 5.0
+  %1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
+  %2 = fsub float -0.000000e+00, %1
+  %3 = fptosi float %2 to i32
+  store i32 %3, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_ugt_select_i32
+; CHECK: SETGT_DX10 T{{[0-9]+\.[XYZW]}}, T{{[0-9]+\.[XYZW]}}, literal.x, 1084227584(5.000000e+00)
+define void @fcmp_ugt_select_i32(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp ugt float %in, 5.0
+  %1 = select i1 %0, i32 -1, i32 0
+  store i32 %1, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_uge_select_fptosi
+; CHECK: SETGE_DX10 T{{[0-9]+\.[XYZW]}}, T{{[0-9]+\.[XYZW]}}, literal.x, 1084227584(5.000000e+00)
+define void @fcmp_uge_select_fptosi(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp uge float %in, 5.0
+  %1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
+  %2 = fsub float -0.000000e+00, %1
+  %3 = fptosi float %2 to i32
+  store i32 %3, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_uge_select_i32
+; CHECK: SETGE_DX10 T{{[0-9]+\.[XYZW]}}, T{{[0-9]+\.[XYZW]}}, literal.x, 1084227584(5.000000e+00)
+define void @fcmp_uge_select_i32(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp uge float %in, 5.0
+  %1 = select i1 %0, i32 -1, i32 0
+  store i32 %1, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_ule_select_fptosi
+; CHECK: SETGE_DX10 T{{[0-9]+\.[XYZW]}}, literal.x, T{{[0-9]+\.[XYZW]}}, 1084227584(5.000000e+00)
+define void @fcmp_ule_select_fptosi(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp ule float %in, 5.0
+  %1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
+  %2 = fsub float -0.000000e+00, %1
+  %3 = fptosi float %2 to i32
+  store i32 %3, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_ule_select_i32
+; CHECK: SETGE_DX10 T{{[0-9]+\.[XYZW]}}, literal.x, T{{[0-9]+\.[XYZW]}}, 1084227584(5.000000e+00)
+define void @fcmp_ule_select_i32(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp ule float %in, 5.0
+  %1 = select i1 %0, i32 -1, i32 0
+  store i32 %1, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_ult_select_fptosi
+; CHECK: SETGT_DX10 T{{[0-9]+\.[XYZW]}}, literal.x, T{{[0-9]+\.[XYZW]}}, 1084227584(5.000000e+00)
+define void @fcmp_ult_select_fptosi(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp ult float %in, 5.0
+  %1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
+  %2 = fsub float -0.000000e+00, %1
+  %3 = fptosi float %2 to i32
+  store i32 %3, i32 addrspace(1)* %out
+  ret void
+}
+
+; CHECK: @fcmp_ult_select_i32
+; CHECK: SETGT_DX10 T{{[0-9]+\.[XYZW]}}, literal.x, T{{[0-9]+\.[XYZW]}}, 1084227584(5.000000e+00)
+define void @fcmp_ult_select_i32(i32 addrspace(1)* %out, float %in) {
+entry:
+  %0 = fcmp ult float %in, 5.0
+  %1 = select i1 %0, i32 -1, i32 0
+  store i32 %1, i32 addrspace(1)* %out
+  ret void
+}
diff --git a/test/CodeGen/R600/unsupported-cc.ll b/test/CodeGen/R600/unsupported-cc.ll
index 5d4c7827ed..b48c591518 100644
--- a/test/CodeGen/R600/unsupported-cc.ll
+++ b/test/CodeGen/R600/unsupported-cc.ll
@@ -24,21 +24,21 @@ entry:
 
 ; CHECK: @ult_float
 ; CHECK: SETGT T{{[0-9]+\.[XYZW]}}, literal.x, {{T[0-9]+\.[XYZW]}}, 1084227584(5.000000e+00)
-define void @ult_float(i32 addrspace(1)* %out, float %in) {
+define void @ult_float(float addrspace(1)* %out, float %in) {
 entry:
   %0 = fcmp ult float %in, 5.0
-  %1 = select i1 %0, i32 -1, i32 0
-  store i32 %1, i32 addrspace(1)* %out
+  %1 = select i1 %0, float 1.0, float 0.0
+  store float %1, float addrspace(1)* %out
   ret void
 }
 
 ; CHECK: @olt
 ; CHECK: SETGT T{{[0-9]+\.[XYZW]}}, literal.x, {{T[0-9]+\.[XYZW]}}, 1084227584(5.000000e+00)
-define void @olt(i32 addrspace(1)* %out, float %in) {
+define void @olt(float addrspace(1)* %out, float %in) {
 entry:
   %0 = fcmp olt float %in, 5.0
-  %1 = select i1 %0, i32 -1, i32 0
-  store i32 %1, i32 addrspace(1)* %out
+  %1 = select i1 %0, float 1.0, float 0.0
+  store float %1, float addrspace(1)* %out
   ret void
 }
 
@@ -64,20 +64,20 @@ entry:
 
 ; CHECK: @ule_float
 ; CHECK: SETGE T{{[0-9]+\.[XYZW]}}, literal.x, {{T[0-9]+\.[XYZW]}}, 1084227584(5.000000e+00)
-define void @ule_float(i32 addrspace(1)* %out, float %in) {
+define void @ule_float(float addrspace(1)* %out, float %in) {
 entry:
   %0 = fcmp ule float %in, 5.0
-  %1 = select i1 %0, i32 -1, i32 0
-  store i32 %1, i32 addrspace(1)* %out
+  %1 = select i1 %0, float 1.0, float 0.0
+  store float %1, float addrspace(1)* %out
   ret void
 }
 
 ; CHECK: @ole
 ; CHECK: SETGE T{{[0-9]+\.[XYZW]}}, literal.x, {{T[0-9]+\.[XYZW]}}, 1084227584(5.000000e+00)
-define void @ole(i32 addrspace(1)* %out, float %in) {
+define void @ole(float addrspace(1)* %out, float %in) {
 entry:
   %0 = fcmp ole float %in, 5.0
-  %1 = select i1 %0, i32 -1, i32 0
-  store i32 %1, i32 addrspace(1)* %out
+  %1 = select i1 %0, float 1.0, float 0.0
+  store float %1, float addrspace(1)* %out
   ret void
 }