mirror/gmsm
1
0
Fork 0
mirror of https://github.com/emmansun/gmsm.git synced 2025-04-26 12:16:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

sm9/bn256: amd64 support MULX for mul & Sqr

Browse Source
This commit is contained in:
emmansun 2023-06-22 18:54:09 +08:00
parent f95cce434f
commit b84bd335dc
1 changed files with 397 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

398
sm9/bn256/gfp_amd64.s
View File

@ -122,6 +122,213 @@ TEXT ·gfpMul(SB),0,$0-24
MOVQ res+0(FP), res_ptr
MOVQ in1+8(FP), x_ptr
MOVQ in2+16(FP), y_ptr
CMPB ·hasBMI2(SB), $0
JE nobmi2Mul
// x * y[0]
MOVQ (8*0)(y_ptr), DX
MULXQ (8*0)(x_ptr), acc0, acc1
MULXQ (8*1)(x_ptr), AX, acc2
ADDQ AX, acc1
ADCQ $0, acc2
MULXQ (8*2)(x_ptr), AX, acc3
ADDQ AX, acc2
ADCQ $0, acc3
MULXQ (8*3)(x_ptr), AX, acc4
ADDQ AX, acc3
ADCQ $0, acc4
XORQ acc5, acc5
// First reduction step
MOVQ acc0, DX
MULXQ ·np+0x00(SB), DX, AX
MULXQ ·p2+0x00(SB), AX, t1
ADDQ AX, acc0
ADCQ t1, acc1
MULXQ ·p2+0x08(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc1
ADCQ t1, acc2
MULXQ ·p2+0x10(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc2
ADCQ t1, acc3
MULXQ ·p2+0x18(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc3
ADCQ t1, acc4
ADCQ $0, acc5
// x * y[1]
MOVQ (8*1)(y_ptr), DX
MULXQ (8*0)(x_ptr), AX, t1
ADDQ AX, acc1
ADCQ t1, acc2
MULXQ (8*1)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc2
ADCQ t1, acc3
MULXQ (8*2)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc3
ADCQ t1, acc4
MULXQ (8*3)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc4
ADCQ t1, acc5
ADCQ $0, acc0
// Second reduction step
MOVQ acc1, DX
MULXQ ·np+0x00(SB), DX, AX
MULXQ ·p2+0x00(SB), AX, t1
ADDQ AX, acc1
ADCQ t1, acc2
MULXQ ·p2+0x08(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc2
ADCQ t1, acc3
MULXQ ·p2+0x10(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc3
ADCQ t1, acc4
MULXQ ·p2+0x18(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc4
ADCQ t1, acc5
ADCQ $0, acc0
// x * y[2]
MOVQ (8*2)(y_ptr), DX
MULXQ (8*0)(x_ptr), AX, t1
ADDQ AX, acc2
ADCQ t1, acc3
MULXQ (8*1)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc3
ADCQ t1, acc4
MULXQ (8*2)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc4
ADCQ t1, acc5
MULXQ (8*3)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc5
ADCQ t1, acc0
ADCQ $0, acc1
// Third reduction step
MOVQ acc2, DX
MULXQ ·np+0x00(SB), DX, AX
MULXQ ·p2+0x00(SB), AX, t1
ADDQ AX, acc2
ADCQ t1, acc3
MULXQ ·p2+0x08(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc3
ADCQ t1, acc4
MULXQ ·p2+0x10(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc4
ADCQ t1, acc5
MULXQ ·p2+0x18(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc5
ADCQ t1, acc0
ADCQ $0, acc1
// x * y[3]
MOVQ (8*3)(y_ptr), DX
MULXQ (8*0)(x_ptr), AX, t1
ADDQ AX, acc3
ADCQ t1, acc4
MULXQ (8*1)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc4
ADCQ t1, acc5
MULXQ (8*2)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc5
ADCQ t1, acc0
MULXQ (8*3)(x_ptr), AX, t1
ADCQ $0, t1
ADDQ AX, acc0
ADCQ t1, acc1
ADCQ $0, acc2
// Last reduction step
MOVQ acc3, DX
MULXQ ·np+0x00(SB), DX, AX
MULXQ ·p2+0x00(SB), AX, t1
ADDQ AX, acc3
ADCQ t1, acc4
MULXQ ·p2+0x08(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc4
ADCQ t1, acc5
MULXQ ·p2+0x10(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc5
ADCQ t1, acc0
MULXQ ·p2+0x18(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc0
ADCQ t1, acc1
ADCQ $0, acc2
// Copy result [255:0]
MOVQ acc4, x_ptr
MOVQ acc5, acc3
MOVQ acc0, t0
MOVQ acc1, t1
// Subtract p2
SUBQ ·p2+0x00(SB), acc4
SBBQ ·p2+0x08(SB) ,acc5
SBBQ ·p2+0x10(SB), acc0
SBBQ ·p2+0x18(SB), acc1
SBBQ $0, acc2
CMOVQCS x_ptr, acc4
CMOVQCS acc3, acc5
CMOVQCS t0, acc0
CMOVQCS t1, acc1
MOVQ acc4, (8*0)(res_ptr)
MOVQ acc5, (8*1)(res_ptr)
MOVQ acc0, (8*2)(res_ptr)
MOVQ acc1, (8*3)(res_ptr)
RET
nobmi2Mul:
// x * y[0]
MOVQ (8*0)(y_ptr), t0
@ -410,6 +617,195 @@ TEXT ·gfpSqr(SB),NOSPLIT,$0
MOVQ in+8(FP), x_ptr
MOVQ n+16(FP), BX
CMPB ·hasBMI2(SB), $0
JE gfpSqrLoop
gfpSqrLoopBMI2:
// y[1:] * y[0]
MOVQ (8*0)(x_ptr), DX
MULXQ (8*1)(x_ptr), acc1, acc2
MULXQ (8*2)(x_ptr), AX, acc3
ADDQ AX, acc2
ADCQ $0, acc3
MULXQ (8*3)(x_ptr), AX, acc4
ADDQ AX, acc3
ADCQ $0, acc4
// y[2:] * y[1]
MOVQ (8*1)(x_ptr), DX
MULXQ (8*2)(x_ptr), AX, t1
ADDQ AX, acc3
ADCQ t1, acc4
MULXQ (8*3)(x_ptr), AX, acc5
ADCQ $0, acc5
ADDQ AX, acc4
ADCQ $0, acc5
// y[3] * y[2]
MOVQ (8*2)(x_ptr), DX
MULXQ (8*3)(x_ptr), AX, y_ptr
ADDQ AX, acc5
ADCQ $0, y_ptr
XORQ t1, t1
// *2
ADDQ acc1, acc1
ADCQ acc2, acc2
ADCQ acc3, acc3
ADCQ acc4, acc4
ADCQ acc5, acc5
ADCQ y_ptr, y_ptr
ADCQ $0, t1
// Missing products
MOVQ (8*0)(x_ptr), DX
MULXQ DX, acc0, t0
ADDQ t0, acc1
MOVQ (8*1)(x_ptr), DX
MULXQ DX, AX, t0
ADCQ AX, acc2
ADCQ t0, acc3
MOVQ (8*2)(x_ptr), DX
MULXQ DX, AX, t0
ADCQ AX, acc4
ADCQ t0, acc5
MOVQ (8*3)(x_ptr), DX
MULXQ DX, AX, x_ptr
ADCQ AX, y_ptr
ADCQ t1, x_ptr
// First reduction step
MOVQ acc0, DX
MULXQ ·np+0x00(SB), DX, AX
MULXQ ·p2+0x00(SB), AX, t1
ADDQ AX, acc0 // (carry1, acc0) = acc0 + t0 * ord0
ADCQ t1, acc1
MULXQ ·p2+0x08(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc1
ADCQ t1, acc2
MULXQ ·p2+0x10(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc2
ADCQ t1, acc3
MULXQ ·p2+0x18(SB), AX, acc0
ADCQ $0, acc0
ADDQ AX, acc3
ADCQ $0, acc0
// Second reduction step
MOVQ acc1, DX
MULXQ ·np+0x00(SB), DX, AX
MULXQ ·p2+0x00(SB), AX, t1
ADDQ AX, acc1
ADCQ t1, acc2
MULXQ ·p2+0x08(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc2
ADCQ t1, acc3
MULXQ ·p2+0x10(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc3
ADCQ t1, acc0
MULXQ ·p2+0x18(SB), AX, acc1
ADCQ $0, acc1
ADDQ AX, acc0
ADCQ $0, acc1
// Third reduction step
MOVQ acc2, DX
MULXQ ·np+0x00(SB), DX, AX
MULXQ ·p2+0x00(SB), AX, t1
ADDQ AX, acc2
ADCQ t1, acc3
MULXQ ·p2+0x08(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc3
ADCQ t1, acc0
MULXQ ·p2+0x10(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc0
ADCQ t1, acc1
MULXQ ·p2+0x18(SB), AX, acc2
ADCQ $0, acc2
ADDQ AX, acc1
ADCQ $0, acc2
// Last reduction step
MOVQ acc3, DX
MULXQ ·np+0x00(SB), DX, AX
MULXQ ·p2+0x00(SB), AX, t1
ADDQ AX, acc3
ADCQ t1, acc0
MULXQ ·p2+0x08(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc0
ADCQ t1, acc1
MULXQ ·p2+0x10(SB), AX, t1
ADCQ $0, t1
ADDQ AX, acc1
ADCQ t1, acc2
MULXQ ·p2+0x18(SB), AX, acc3
ADCQ $0, acc3
ADDQ AX, acc2
ADCQ $0, acc3
XORQ t0, t0
// Add bits [511:256] of the sqr result
ADDQ acc4, acc0
ADCQ acc5, acc1
ADCQ y_ptr, acc2
ADCQ x_ptr, acc3
ADCQ $0, t0
MOVQ acc0, acc4
MOVQ acc1, acc5
MOVQ acc2, y_ptr
MOVQ acc3, t1
// Subtract p2
SUBQ ·p2+0x00(SB), acc0
SBBQ ·p2+0x08(SB) ,acc1
SBBQ ·p2+0x10(SB), acc2
SBBQ ·p2+0x18(SB), acc3
SBBQ $0, t0
CMOVQCS acc4, acc0
CMOVQCS acc5, acc1
CMOVQCS y_ptr, acc2
CMOVQCS t1, acc3
MOVQ acc0, (8*0)(res_ptr)
MOVQ acc1, (8*1)(res_ptr)
MOVQ acc2, (8*2)(res_ptr)
MOVQ acc3, (8*3)(res_ptr)
MOVQ res_ptr, x_ptr
DECQ BX
JNE gfpSqrLoopBMI2
RET
gfpSqrLoop:
// y[1:] * y[0]
@ -637,7 +1033,7 @@ gfpSqrLoop:
XORQ t0, t0
// Add bits [511:256] of the sqr result
ADCQ acc4, acc0
ADDQ acc4, acc0
ADCQ acc5, acc1
ADCQ y_ptr, acc2
ADCQ x_ptr, acc3