From 550a456a2c0c3e569a20a0088cdd42305eea8f0b Mon Sep 17 00:00:00 2001 From: Xan Date: Wed, 25 Apr 2018 11:59:59 +0100 Subject: [PATCH] --- ...RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn | 151 ++++++++++-------- 1 file changed, 82 insertions(+), 69 deletions(-) diff --git a/Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn b/Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn index da038b714..bd1a74781 100644 --- a/Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn +++ b/Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn @@ -47,16 +47,16 @@ The harmonised RVP register file is divided into a lower bank of Vector[INT8] an | Andes Mnemonic | 16-bit Instruction | Harmonised RVP Equivalent | | ------------------ | ------------------------- | ------------------- | -| ADD16 rt, ra, rb | Add | VADD (r16 <= rt,ra,rb <= r29), mm=00| -| RADD16 rt, ra, rb | Signed Halving add | RADD (r16 <= rt,ra,rb <= r23), mm=00| -| URADD16 rt, ra, rb | Unsigned Halving add | RADD (r24 <= rt,ra,rb <= r29), mm=00| -| KADD16 rt, ra, rb | Signed Saturating add | VADD (r16 <= rt,ra,rb <= r23), mm=01| -| UKADD16 rt, ra, rb | Unsigned Saturating add | VADD (r24 <= rt,ra,rb <= r29), mm=01| -| SUB16 rt, ra, rb | Subtract | VSUB (r16 <= rt,ra,rb <= r29), mm=00| -| RSUB16 rt, ra, rb | Signed Halving sub | RSUB (r16 <= rt,ra,rb <= r23), mm=00| -| URSUB16 rt, ra, rb | Unsigned Halving sub | RSUB (r24 <= rt,ra,rb <= r29), mm=00| -| KSUB16 rt, ra, rb | Signed Saturating sub | VSUB (r16 <= rt,ra,rb <= r23), mm=01| -| UKSUB16 rt, ra, rb | Unsigned Saturating sub | VSUB (r24 <= rt,ra,rb <= r29), mm=01| +| ADD16 rt, ra, rb | Add | VADD (v16 <= rt,ra,rb <= v29), mm=00| +| RADD16 rt, ra, rb | Signed Halving add | RADD (v16 <= rt,ra,rb <= v23), mm=00| +| URADD16 rt, ra, rb | Unsigned Halving add | RADD (v24 <= rt,ra,rb <= v29), mm=00| +| KADD16 rt, ra, rb | Signed Saturating add | VADD (v16 <= rt,ra,rb <= v23), mm=01| +| UKADD16 rt, ra, rb | Unsigned Saturating add | VADD (v24 <= rt,ra,rb <= v29), mm=01| +| SUB16 rt, ra, rb | Subtract | VSUB (v16 <= rt,ra,rb <= v29), mm=00| +| RSUB16 rt, ra, rb | Signed Halving sub | RSUB (v16 <= rt,ra,rb <= v23), mm=00| +| URSUB16 rt, ra, rb | Unsigned Halving sub | RSUB (v24 <= rt,ra,rb <= v29), mm=00| +| KSUB16 rt, ra, rb | Signed Saturating sub | VSUB (v16 <= rt,ra,rb <= v23), mm=01| +| UKSUB16 rt, ra, rb | Unsigned Saturating sub | VSUB (v24 <= rt,ra,rb <= v29), mm=01| | CRAS16 rt, ra, rb | Cross Add & Sub | | | RCRAS16 rt, ra, rb | Signed Halving Cross Add & Sub | | | URCRAS16 rt, ra, rb| Unsigned Halving Cross Add & Sub | | @@ -72,16 +72,16 @@ The harmonised RVP register file is divided into a lower bank of Vector[INT8] an | Andes Mnemonic | 8-bit Instruction | Harmonised RVP Equivalent | | ------------------ | ------------------------- | ------------------- | -| ADD8 rt, ra, rb | Add | VADD (r2 <= rt,ra,rb <= r15), mm=00 | -| RADD8 rt, ra, rb | Signed Halving add | RADD (r2 <= rt,ra,rb <= r7), mm=00 | -| URADD8 rt, ra, rb | Unsigned Halving add | RADD (r8 <= rt,ra,rb <= r15), mm=00 | -| KADD8 rt, ra, rb | Signed Saturating add | VADD (r2 <= rt,ra,rb <= r7), mm=01 | -| UKADD8 rt, ra, rb | Unsigned Saturating add | VADD (r8 <= rt,ra,rb <= r15), mm=01 | -| SUB8 rt, ra, rb | Subtract | VSUB (r2 <= rt,ra,rb <= r15), mm=00 | -| RSUB8 rt, ra, rb | Signed Halving sub | RSUB (r2 <= rt,ra,rb <= r7), mm=00 | -| URSUB8 rt, ra, rb | Unsigned Halving sub | RSUB (r8 <= rt,ra,rb <= r15), mm=00 | -| KSUB8 rt, ra, rb | Signed Saturating sub | VSUB (r2 <= rt,ra,rb <= r7), mm=01 | -| UKSUB8 rt, ra, rb | Unsigned Saturating sub | VSUB (r8 <= rt,ra,rb <= r15), mm=01 | +| ADD8 rt, ra, rb | Add | VADD (v2 <= rt,ra,rb <= v15), mm=00 | +| RADD8 rt, ra, rb | Signed Halving add | RADD (v2 <= rt,ra,rb <= v7), mm=00 | +| URADD8 rt, ra, rb | Unsigned Halving add | RADD (v8 <= rt,ra,rb <= v15), mm=00 | +| KADD8 rt, ra, rb | Signed Saturating add | VADD (v2 <= rt,ra,rb <= v7), mm=01 | +| UKADD8 rt, ra, rb | Unsigned Saturating add | VADD (v8 <= rt,ra,rb <= v15), mm=01 | +| SUB8 rt, ra, rb | Subtract | VSUB (v2 <= rt,ra,rb <= v15), mm=00 | +| RSUB8 rt, ra, rb | Signed Halving sub | RSUB (v2 <= rt,ra,rb <= v7), mm=00 | +| URSUB8 rt, ra, rb | Unsigned Halving sub | RSUB (v8 <= rt,ra,rb <= v15), mm=00 | +| KSUB8 rt, ra, rb | Signed Saturating sub | VSUB (v2 <= rt,ra,rb <= v7), mm=01 | +| UKSUB8 rt, ra, rb | Unsigned Saturating sub | VSUB (v8 <= rt,ra,rb <= v15), mm=01 | ## 16-bit Shifts @@ -91,18 +91,18 @@ The “K” (Saturation) and “u” (Rounding) variants could be encoded using | Andes Mnemonic | 16-bit Instruction | Harmonised RVP Equivalent | | ------------------ | ------------------------- | ------------------- | -| SRA16 rt, ra, rb | Shift right arithmetic | VSRA (r16 <= rt,ra,rb <= r29), mm=00| -| SRAI16 rt, ra, im | Shift right arithmetic imm | VSRAI (r16 <= rt,ra <= r29), mm=00| -| SRA16.u rt, ra, rb | Rounding Shift right arithmetic | VSRA (r16 <= rt,ra,rb <= r29), mm=01| -| SRAI16.u rt, ra, im | Rounding Shift right arithmetic imm | VSRAI (r16 <= rt,ra <= r29), mm=01| -| SRL16 rt, ra, rb | Shift right logical | VSRL (r16 <= rt,ra,rb <= r29), mm=00| -| SRLI16 rt, ra, im | Shift right logical imm | VSRLI (r16 <= rt,ra <= r29), mm=00| -| SRL16.u rt, ra, rb | Rounding Shift right logical | VSRL (r16 <= rt,ra,rb <= r29), mm=01| -| SRLI16.u rt, ra, im | Rounding Shift right logical imm | VSLRI (r16 <= rt,ra <= r29), mm=01| -| SLL16 rt, ra, rb | Shift left logical | VSLL (r16 <= rt,ra,rb <= r29), mm=00| -| SLLI16 rt, ra, im | Shift left logical imm | VSLLI (r16 <= rt,ra <= r29), mm=00| -| KSLL16 rt, ra, rb | Saturating Shift left logical | VSLL (r16 <= rt,ra,rb <= r29), mm=01| -| KSLLI16 rt, ra, im | Saturating Shift left logical imm | VSLLI (r16 <= rt,ra <= r29), mm=01| +| SRA16 rt, ra, rb | Shift right arithmetic | VSRA (v16 <= rt,ra,rb <= v29), mm=00| +| SRAI16 rt, ra, im | Shift right arithmetic imm | VSRAI (v16 <= rt,ra <= v29), mm=00| +| SRA16.u rt, ra, rb | Rounding Shift right arithmetic | VSRA (v16 <= rt,ra,rb <= v29), mm=01| +| SRAI16.u rt, ra, im | Rounding Shift right arithmetic imm | VSRAI (v16 <= rt,ra <= v29), mm=01| +| SRL16 rt, ra, rb | Shift right logical | VSRL (v16 <= rt,ra,rb <= v29), mm=00| +| SRLI16 rt, ra, im | Shift right logical imm | VSRLI (v16 <= rt,ra <= v29), mm=00| +| SRL16.u rt, ra, rb | Rounding Shift right logical | VSRL (v16 <= rt,ra,rb <= v29), mm=01| +| SRLI16.u rt, ra, im | Rounding Shift right logical imm | VSLRI (v16 <= rt,ra <= v29), mm=01| +| SLL16 rt, ra, rb | Shift left logical | VSLL (v16 <= rt,ra,rb <= v29), mm=00| +| SLLI16 rt, ra, im | Shift left logical imm | VSLLI (v16 <= rt,ra <= v29), mm=00| +| KSLL16 rt, ra, rb | Saturating Shift left logical | VSLL (v16 <= rt,ra,rb <= v29), mm=01| +| KSLLI16 rt, ra, im | Saturating Shift left logical imm | VSLLI (v16 <= rt,ra <= v29), mm=01| | KSLRA16 rt, ra, rb | Saturating Shift left logical or Shift right arithmetic || | KSLRA16.u rt, ra, rb | Saturating Shift left logical or Rounding Shift right arithmetic || @@ -113,63 +113,76 @@ Andes SIMD Packed ISA omits 8 bit shifts, but these can be encoded in Harmonised | Andes Mnemonic | 8-bit Instruction | Harmonised RVP Equivalent | | ------------------ | ------------------------- | ------------------- | -| n/a | Shift right arithmetic | VSRA (r2 <= rt,ra,rb <= r15), mm=00| -| n/a | Shift right arithmetic imm | VSRAI (r2 <= rt,ra <= r15), mm=00| -| n/a | Rounding Shift right arithmetic | VSRA (r2 <= rt,ra,rb <= r15), mm=01| -| n/a | Rounding Shift right arithmetic imm | VSRAI (r2 <= rt,ra <= r15), mm=01| -| n/a | Shift right logical | VSRL (r2 <= rt,ra,rb <= r15), mm=00| -| n/a | Shift right logical imm | VSRLI (r2 <= rt,ra <= r15), mm=00| -| n/a | Rounding Shift right logical | VSRL (r2 <= rt,ra,rb <= r15), mm=01| -| n/a | Rounding Shift right logical imm | VSLRI (r2 <= rt,ra <= r15), mm=01| -| n/a | Shift left logical | VSLL (r2 <= rt,ra,rb <= r15), mm=00| -| n/a | Shift left logical imm | VSLLI (r2 <= rt,ra <= r15), mm=00| -| n/a | Saturating Shift left logical | VSLL (r2 <= rt,ra,rb <= r15), mm=01| -| n/a | Saturating Shift left logical imm | VSLLI (r2 <= rt,ra <= r15), mm=01| +| n/a | Shift right arithmetic | VSRA (v2 <= rt,ra,rb <= v15), mm=00| +| n/a | Shift right arithmetic imm | VSRAI (v2 <= rt,ra <= v15), mm=00| +| n/a | Rounding Shift right arithmetic | VSRA (v2 <= rt,ra,rb <= v15), mm=01| +| n/a | Rounding Shift right arithmetic imm | VSRAI (v2 <= rt,ra <= v15), mm=01| +| n/a | Shift right logical | VSRL (v2 <= rt,ra,rb <= v15), mm=00| +| n/a | Shift right logical imm | VSRLI (v2 <= rt,ra <= v15), mm=00| +| n/a | Rounding Shift right logical | VSRL (v2 <= rt,ra,rb <= v15), mm=01| +| n/a | Rounding Shift right logical imm | VSLRI (v2 <= rt,ra <= v15), mm=01| +| n/a | Shift left logical | VSLL (v2 <= rt,ra,rb <= v15), mm=00| +| n/a | Shift left logical imm | VSLLI (v2 <= rt,ra <= v15), mm=00| +| n/a | Saturating Shift left logical | VSLL (v2 <= rt,ra,rb <= v15), mm=01| +| n/a | Saturating Shift left logical imm | VSLLI (v2 <= rt,ra <= v15), mm=01| ## 16-bit Comparison instructions | Andes Mnemonic | 16-bit Instruction | Harmonised RVP Equivalent | | ------------------ | ------------------------- | ------------------- | -| CMPEQ16 rt, ra, rb | Compare equal | VSEQ (r16 <= rt,ra,rb <= r29), mm=00| -| SCMPLT16 rt, ra, rb | Signed Compare less than | !VSGT (r16 <= rt,ra,rb <= r23), mm=00| -| SCMPLE16 rt, ra, rb | Signed Compare less or equal | VSLE (r16 <= rt,ra,rb <= r23), mm=00| -| UCMPLT16 rt, ra, rb | Unsigned Compare less than | !VSGT (r24 <= rt,ra,rb <= r29), mm=00| -| UCMPLE16 rt, ra, rb | Unsigned Compare less or equal | VSLE (r24 <= rt,ra,rb <= r29), mm=00| +| CMPEQ16 rt, ra, rb | Compare equal | VSEQ (v16 <= rt,ra,rb <= v29), mm=00| +| SCMPLT16 rt, ra, rb | Signed Compare less than | !VSGT (v16 <= rt,ra,rb <= v23), mm=00| +| SCMPLE16 rt, ra, rb | Signed Compare less or equal | VSLE (v16 <= rt,ra,rb <= v23), mm=00| +| UCMPLT16 rt, ra, rb | Unsigned Compare less than | !VSGT (v24 <= rt,ra,rb <= v29), mm=00| +| UCMPLE16 rt, ra, rb | Unsigned Compare less or equal | VSLE (v24 <= rt,ra,rb <= v29), mm=00| ## 8-bit Comparison instructions | Andes Mnemonic | 8-bit Instruction | Harmonised RVP Equivalent | | ------------------ | ------------------------- | ------------------- | -| CMPEQ8 rt, ra, rb | Compare equal | VSEQ (r2 <= rt,ra,rb <= r7), mm=00| -| SCMPLT8 rt, ra, rb | Signed Compare less than | !VSGT (r2 <= rt,ra,rb <= r7), mm=00| -| SCMPLE8 rt, ra, rb | Signed Compare less or equal | VSLE (r2 <= rt,ra,rb <= r7), mm=00| -| UCMPLT8 rt, ra, rb | Unsigned Compare less than | !VSGT (r8 <= rt,ra,rb <= r15), mm=00| -| UCMPLE8 rt, ra, rb | Unsigned Compare less or equal | VSLE (r8 <= rt,ra,rb <= r15), mm=00| +| CMPEQ8 rt, ra, rb | Compare equal | VSEQ (v2 <= rt,ra,rb <= v7), mm=00| +| SCMPLT8 rt, ra, rb | Signed Compare less than | !VSGT (v2 <= rt,ra,rb <= v7), mm=00| +| SCMPLE8 rt, ra, rb | Signed Compare less or equal | VSLE (v2 <= rt,ra,rb <= v7), mm=00| +| UCMPLT8 rt, ra, rb | Unsigned Compare less than | !VSGT (v8 <= rt,ra,rb <= v15), mm=00| +| UCMPLE8 rt, ra, rb | Unsigned Compare less or equal | VSLE (v8 <= rt,ra,rb <= v15), mm=00| ## 16-bit Miscellaneous instructions | Andes Mnemonic | 16-bit Instruction | Harmonised RVP Equivalent | | ------------------ | ------------------------ | ------------------- | -| SMIN16 rt, ra, rb | Signed minimum | VMIN (r16 <= rt,ra,rb <= r23), mm=00| -| UMIN16 rt, ra, rb | Unsigned minimum | VMIN (r24 <= rt,ra,rb <= r29), mm=00| -| SMAX16 rt, ra, rb | Signed maximum | VMAX (r16 <= rt,ra,rb <= r23), mm=00| -| UMAX16 rt, ra, rb | Unsigned maximum | VMAX (r24 <= rt,ra,rb <= r29), mm=00| -| SCLIP16 rt, ra, rb | Signed clip | ?VCLIP (r16 <= rt,ra,rb <= r23), mm=01| -| UCLIP16 rt, ra, rb | Unsigned clip | ?VCLIP (r24 <= rt,ra,rb <= r29), mm=01| -| KMUL16 rt, ra, rb | Signed multiply 16x16->16 | VMUL (r16 <= rt,ra,rb <= r23), mm=01| +| SMIN16 rt, ra, rb | Signed minimum | VMIN (v16 <= rt,ra,rb <= v23), mm=00| +| UMIN16 rt, ra, rb | Unsigned minimum | VMIN (v24 <= rt,ra,rb <= v29), mm=00| +| SMAX16 rt, ra, rb | Signed maximum | VMAX (v16 <= rt,ra,rb <= v23), mm=00| +| UMAX16 rt, ra, rb | Unsigned maximum | VMAX (v24 <= rt,ra,rb <= v29), mm=00| +| SCLIP16 rt, ra, im | Signed clip | ?VCLIP (v16 <= rt,ra,rb <= v23), mm=01| +| UCLIP16 rt, ra, im | Unsigned clip | ?VCLIP (v24 <= rt,ra,rb <= v29), mm=01| +| KMUL16 rt, ra, rb | Signed multiply 16x16->16 | VMUL (v16 <= rt,ra,rb <= v23), mm=01| | KMULX16 rt, ra, rb | Signed crossed multiply 16x16->16 | | -| SMUL16 rt, ra, rb | Signed multiply 16x16->32 | VMUL (30 <= rt <= 31, r16 <= ra,rb <= r23), mm=00| +| SMUL16 rt, ra, rb | Signed multiply 16x16->32 | VMUL (30 <= rt <= 31, v16 <= ra,rb <= v23), mm=00| | SMULX16 rt, ra, rb | Signed crossed multiply 16x16->32 | | -| UMUL16 rt, ra, rb | Signed multiply 16x16->32 | VMUL (30 <= rt <= 31, r24 <= ra,rb <= r31), mm=00| +| UMUL16 rt, ra, rb | Signed multiply 16x16->32 | VMUL (30 <= rt <= 31, v24 <= ra,rb <= r31), mm=00| | UMULX16 rt, ra, rb | Signed crossed multiply 16x16->32 | | -| KABS16 rt, ra, rb | Saturated absolute value | VSGNX (r16 <= rt <= r29, r16 <= ra,rb <= r23, mm=01) | +| KABS16 rt, ra | Saturated absolute value | VSGNX (v16 <= rt <= v29, v16 <= ra,rb <= v23, mm=01) | ## 8-bit Miscellaneous instructions | Andes Mnemonic | 8-bit Instruction | Harmonised RVP Equivalent | | ------------------ | ------------------------- | ------------------- | -| SMIN8 rt, ra, rb | Signed minimum | VMIN (r2 <= rt,ra,rb <= r7), mm=00| -| UMIN8 rt, ra, rb | Unsigned minimum | VMIN (r8 <= rt,ra,rb <= r15), mm=00| -| SMAX8 rt, ra, rb | Signed maximum | VMAX (r2 <= rt,ra,rb <= r7), mm=00| -| UMAX8 rt, ra, rb | Unsigned maximum | VMAX (r8 <= rt,ra,rb <= r15), mm=00| -| KABS8 rt, ra, rb | Saturated absolute value | VSGNX (r2 <= rt <= r15, r2 <= ra,rb <= r8, mm=01) | +| SMIN8 rt, ra, rb | Signed minimum | VMIN (v2 <= rt,ra,rb <= v7), mm=00| +| UMIN8 rt, ra, rb | Unsigned minimum | VMIN (v8 <= rt,ra,rb <= v15), mm=00| +| SMAX8 rt, ra, rb | Signed maximum | VMAX (v2 <= rt,ra,rb <= v7), mm=00| +| UMAX8 rt, ra, rb | Unsigned maximum | VMAX (v8 <= rt,ra,rb <= v15), mm=00| +| KABS8 rt, ra | Saturated absolute value | VSGNX (v2 <= rt <= v15, v2 <= ra,rb <= v8, mm=01) | + +## 8-bit Unpacking instructions + +| Andes Mnemonic | 8-bit Instruction | Harmonised RVP Equivalent | +| ------------------ | ------------------------- | ------------------- | +| SUNPKD810 rt, ra | Signed unpack bytes 1 & 0 | VMV (v16<= rt <= 23, v2 <= ra <= v7), mm=00| +| SUNPKD820 rt, ra | Signed unpack bytes 2 & 0 | | +| SUNPKD830 rt, ra | Signed unpack bytes 3 & 0 | | +| SUNPKD831 rt, ra | Signed unpack bytes 3 & 1 | | +| ZUNPKD810 rt, ra | Unsigned unpack bytes 1 & 0 | VMV (v24<= rt <= 31, v8 <= ra <= v15), mm=00| +| ZUNPKD820 rt, ra | Unsigned unpack bytes 2 & 0 | | +| ZUNPKD830 rt, ra | Unsigned unpack bytes 3 & 0 | | +| ZUNPKD831 rt, ra | Unsigned unpack bytes 3 & 1 | | -- 2.30.2