aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/NVPTX
diff options
context:
space:
mode:
authorJustin Holewinski <jholewinski@nvidia.com>2013-08-06 14:13:34 +0000
committerJustin Holewinski <jholewinski@nvidia.com>2013-08-06 14:13:34 +0000
commitdf66ff09bcbdddf4ed6e3d162110a3d2b7978628 (patch)
tree6084781e7214d266537a7f0826486e27f8ddbbb3 /lib/Target/NVPTX
parenta3635eefc749389aed84d9791fab657297203e1b (diff)
downloadexternal_llvm-df66ff09bcbdddf4ed6e3d162110a3d2b7978628.zip
external_llvm-df66ff09bcbdddf4ed6e3d162110a3d2b7978628.tar.gz
external_llvm-df66ff09bcbdddf4ed6e3d162110a3d2b7978628.tar.bz2
[NVPTX] Add missing patterns for i1 [s,u]int_to_fp
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187800 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target/NVPTX')
-rw-r--r--lib/Target/NVPTX/NVPTXInstrInfo.td30
1 files changed, 19 insertions, 11 deletions
diff --git a/lib/Target/NVPTX/NVPTXInstrInfo.td b/lib/Target/NVPTX/NVPTXInstrInfo.td
index db91eb0..3e430bf 100644
--- a/lib/Target/NVPTX/NVPTXInstrInfo.td
+++ b/lib/Target/NVPTX/NVPTXInstrInfo.td
@@ -2208,6 +2208,17 @@ defm STV_f64 : ST_VEC<Float64Regs>;
//---- Conversion ----
+class F_BITCONVERT<string SzStr, NVPTXRegClass regclassIn,
+ NVPTXRegClass regclassOut> :
+ NVPTXInst<(outs regclassOut:$d), (ins regclassIn:$a),
+ !strconcat("mov.b", !strconcat(SzStr, " \t $d, $a;")),
+ [(set regclassOut:$d, (bitconvert regclassIn:$a))]>;
+
+def BITCONVERT_32_I2F : F_BITCONVERT<"32", Int32Regs, Float32Regs>;
+def BITCONVERT_32_F2I : F_BITCONVERT<"32", Float32Regs, Int32Regs>;
+def BITCONVERT_64_I2F : F_BITCONVERT<"64", Int64Regs, Float64Regs>;
+def BITCONVERT_64_F2I : F_BITCONVERT<"64", Float64Regs, Int64Regs>;
+
// NOTE: pred->fp are currently sub-optimal due to an issue in TableGen where
// we cannot specify floating-point literals in isel patterns. Therefore, we
// use an integer selp to select either 1 or 0 and then cvt to floating-point.
@@ -2254,6 +2265,8 @@ def : Pat<(f64 (uint_to_fp Int64Regs:$a)),
// f32 -> sint
+def : Pat<(i1 (fp_to_sint Float32Regs:$a)),
+ (SETP_b32ri (BITCONVERT_32_F2I Float32Regs:$a), 0, CmpEQ)>;
def : Pat<(i16 (fp_to_sint Float32Regs:$a)),
(CVT_s16_f32 Float32Regs:$a, CvtRZI_FTZ)>, Requires<[doF32FTZ]>;
def : Pat<(i16 (fp_to_sint Float32Regs:$a)),
@@ -2268,6 +2281,8 @@ def : Pat<(i64 (fp_to_sint Float32Regs:$a)),
(CVT_s64_f32 Float32Regs:$a, CvtRZI)>;
// f32 -> uint
+def : Pat<(i1 (fp_to_uint Float32Regs:$a)),
+ (SETP_b32ri (BITCONVERT_32_F2I Float32Regs:$a), 0, CmpEQ)>;
def : Pat<(i16 (fp_to_uint Float32Regs:$a)),
(CVT_u16_f32 Float32Regs:$a, CvtRZI_FTZ)>, Requires<[doF32FTZ]>;
def : Pat<(i16 (fp_to_uint Float32Regs:$a)),
@@ -2282,6 +2297,8 @@ def : Pat<(i64 (fp_to_uint Float32Regs:$a)),
(CVT_u64_f32 Float32Regs:$a, CvtRZI)>;
// f64 -> sint
+def : Pat<(i1 (fp_to_sint Float64Regs:$a)),
+ (SETP_b64ri (BITCONVERT_64_F2I Float64Regs:$a), 0, CmpEQ)>;
def : Pat<(i16 (fp_to_sint Float64Regs:$a)),
(CVT_s16_f64 Float64Regs:$a, CvtRZI)>;
def : Pat<(i32 (fp_to_sint Float64Regs:$a)),
@@ -2290,6 +2307,8 @@ def : Pat<(i64 (fp_to_sint Float64Regs:$a)),
(CVT_s64_f64 Float64Regs:$a, CvtRZI)>;
// f64 -> uint
+def : Pat<(i1 (fp_to_uint Float64Regs:$a)),
+ (SETP_b64ri (BITCONVERT_64_F2I Float64Regs:$a), 0, CmpEQ)>;
def : Pat<(i16 (fp_to_uint Float64Regs:$a)),
(CVT_u16_f64 Float64Regs:$a, CvtRZI)>;
def : Pat<(i32 (fp_to_uint Float64Regs:$a)),
@@ -2397,17 +2416,6 @@ def : Pat<(select Int32Regs:$pred, Float64Regs:$a, Float64Regs:$b),
(SETP_b32ri (ANDb32ri Int32Regs:$pred, 1), 1, CmpEQ))>;
-class F_BITCONVERT<string SzStr, NVPTXRegClass regclassIn,
- NVPTXRegClass regclassOut> :
- NVPTXInst<(outs regclassOut:$d), (ins regclassIn:$a),
- !strconcat("mov.b", !strconcat(SzStr, " \t $d, $a;")),
- [(set regclassOut:$d, (bitconvert regclassIn:$a))]>;
-
-def BITCONVERT_32_I2F : F_BITCONVERT<"32", Int32Regs, Float32Regs>;
-def BITCONVERT_32_F2I : F_BITCONVERT<"32", Float32Regs, Int32Regs>;
-def BITCONVERT_64_I2F : F_BITCONVERT<"64", Int64Regs, Float64Regs>;
-def BITCONVERT_64_F2I : F_BITCONVERT<"64", Float64Regs, Int64Regs>;
-
// pack a set of smaller int registers to a larger int register
def V4I16toI64 : NVPTXInst<(outs Int64Regs:$d),
(ins Int16Regs:$s1, Int16Regs:$s2,