cmd/compile: intrinsify math/bits.Mul

Add SSA rules to intrinsify Mul/Mul64 (AMD64 and ARM64).
SSA rules for other functions and architectures are left as a future
optimization.  Benchmark results on AMD64/ARM64 before and after SSA
implementation are below.

amd64
name     old time/op  new time/op  delta
Add-4    1.78ns ± 0%  1.85ns ±12%     ~     (p=0.397 n=4+5)
Add32-4  1.71ns ± 1%  1.70ns ± 0%     ~     (p=0.683 n=5+5)
Add64-4  1.80ns ± 2%  1.77ns ± 0%   -1.22%  (p=0.048 n=5+5)
Sub-4    1.78ns ± 0%  1.78ns ± 0%     ~     (all equal)
Sub32-4  1.78ns ± 1%  1.78ns ± 0%     ~     (p=1.000 n=5+5)
Sub64-4  1.78ns ± 1%  1.78ns ± 0%     ~     (p=0.968 n=5+4)
Mul-4    11.5ns ± 1%   1.8ns ± 2%  -84.39%  (p=0.008 n=5+5)
Mul32-4  1.39ns ± 0%  1.38ns ± 3%     ~     (p=0.175 n=5+5)
Mul64-4  6.85ns ± 1%  1.78ns ± 1%  -73.97%  (p=0.008 n=5+5)
Div-4    57.1ns ± 1%  56.7ns ± 0%     ~     (p=0.087 n=5+5)
Div32-4  18.0ns ± 0%  18.0ns ± 0%     ~     (all equal)
Div64-4  56.4ns ±10%  53.6ns ± 1%     ~     (p=0.071 n=5+5)

arm64
name      old time/op  new time/op  delta
Add-96    5.51ns ± 0%  5.51ns ± 0%     ~     (all equal)
Add32-96  5.51ns ± 0%  5.51ns ± 0%     ~     (all equal)
Add64-96  5.52ns ± 0%  5.51ns ± 0%     ~     (p=0.444 n=5+5)
Sub-96    5.51ns ± 0%  5.51ns ± 0%     ~     (all equal)
Sub32-96  5.51ns ± 0%  5.51ns ± 0%     ~     (all equal)
Sub64-96  5.51ns ± 0%  5.51ns ± 0%     ~     (all equal)
Mul-96    34.6ns ± 0%   5.0ns ± 0%  -85.52%  (p=0.008 n=5+5)
Mul32-96  4.51ns ± 0%  4.51ns ± 0%     ~     (all equal)
Mul64-96  21.1ns ± 0%   5.0ns ± 0%  -76.26%  (p=0.008 n=5+5)
Div-96    64.7ns ± 0%  64.7ns ± 0%     ~     (all equal)
Div32-96  17.0ns ± 0%  17.0ns ± 0%     ~     (all equal)
Div64-96  53.1ns ± 0%  53.1ns ± 0%     ~     (all equal)

Updates #24813

Change-Id: I9bda6d2102f65cae3d436a2087b47ed8bafeb068
Reviewed-on: https://go-review.googlesource.com/129415
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>

diff --git a/src/cmd/compile/internal/gc/ssa.go b/src/cmd/compile/internal/gc/ssa.go
index 2ee966d890f85996c8f65685f5df1fabe8c34827..8df8023d18bec6d06b013c741bf6483fc7bcad43 100644 (file)
--- a/src/cmd/compile/internal/gc/ssa.go
+++ b/src/cmd/compile/internal/gc/ssa.go
@@ -3435,6 +3435,12 @@ func init() {
        addF("math/bits", "OnesCount",
                makeOnesCountAMD64(ssa.OpPopCount64, ssa.OpPopCount32),
                sys.AMD64)
+       alias("math/bits", "Mul", "math/bits", "Mul64", sys.ArchAMD64, sys.ArchARM64)
+       addF("math/bits", "Mul64",
+               func(s *state, n *Node, args []*ssa.Value) *ssa.Value {
+                       return s.newValue2(ssa.OpMul64uhilo, types.NewTuple(types.Types[TUINT64], types.Types[TUINT64]), args[0], args[1])
+               },
+               sys.AMD64, sys.ARM64)
 
        /******** sync/atomic ********/
 

diff --git a/test/codegen/mathbits.go b/test/codegen/mathbits.go
index 28354ed65175ccb6e07fa1a127f9ae72d59637b8..834b08f1015b099ff1e5233e7d2338fd5c08fc17 100644 (file)
--- a/test/codegen/mathbits.go
+++ b/test/codegen/mathbits.go
@@ -302,3 +302,19 @@ func IterateBits8(n uint8) int {
        }
        return i
 }
+
+// --------------- //
+//    bits.Mul*    //
+// --------------- //
+
+func Mul(x, y uint) (hi, lo uint) {
+       // amd64:"MULQ"
+       // arm64:"UMULH","MUL"
+       return bits.Mul(x, y)
+}
+
+func Mul64(x, y uint64) (hi, lo uint64) {
+       // amd64:"MULQ"
+       // arm64:"UMULH","MUL"
+       return bits.Mul64(x, y)
+}