From d45cd836ba675e99e3ae4f4a82185ea1cae546bb Mon Sep 17 00:00:00 2001 From: Luke Kenneth Casson Leighton Date: Thu, 7 Jul 2022 19:11:05 +0100 Subject: [PATCH] replace rs1 rs2 rd with FRA FRB FRT --- openpower/transcendentals.mdwn | 84 +++++++++++++++++----------------- 1 file changed, 42 insertions(+), 42 deletions(-) diff --git a/openpower/transcendentals.mdwn b/openpower/transcendentals.mdwn index 6464700f2..233c3202d 100644 --- a/openpower/transcendentals.mdwn +++ b/openpower/transcendentals.mdwn @@ -184,56 +184,56 @@ software emulation | opcode | Description | pseudocode | Extension | | ------ | ---------------- | ---------------- | ----------- | -| FATAN2 | atan2 arc tangent | rd = atan2(rs2, rs1) | Zarctrignpi | -| FATAN2PI | atan2 arc tangent / pi | rd = atan2(rs2, rs1) / pi | Zarctrigpi | -| FPOW | x power of y | rd = pow(rs1, rs2) | ZftransAdv | -| FPOWN | x power of n (n int) | rd = pow(rs1, rs2) | ZftransAdv | -| FPOWR | x power of y (x +ve) | rd = exp(rs1 log(rs2)) | ZftransAdv | -| FROOTN | x power 1/n (n integer)| rd = pow(rs1, 1/rs2) | ZftransAdv | -| FHYPOT | hypotenuse | rd = sqrt(rs1^2 + rs2^2) | ZftransAdv | +| FATAN2 | atan2 arc tangent | FRT = atan2(FRB, FRA) | Zarctrignpi | +| FATAN2PI | atan2 arc tangent / pi | FRT = atan2(FRB, FRA) / pi | Zarctrigpi | +| FPOW | x power of y | FRT = pow(FRA, FRB) | ZftransAdv | +| FPOWN | x power of n (n int) | FRT = pow(FRA, FRB) | ZftransAdv | +| FPOWR | x power of y (x +ve) | FRT = exp(FRA log(FRB)) | ZftransAdv | +| FROOTN | x power 1/n (n integer)| FRT = pow(FRA, 1/FRB) | ZftransAdv | +| FHYPOT | hypotenuse | FRT = sqrt(FRA^2 + FRB^2) | ZftransAdv | ## List of 1-arg transcendental opcodes | opcode | Description | pseudocode | Extension | | ------ | ---------------- | ---------------- | ----------- | -| FRSQRT | Reciprocal Square-root | rd = sqrt(rs1) | Zfrsqrt | -| FCBRT | Cube Root | rd = pow(rs1, 1.0 / 3) | ZftransAdv | -| FRECIP | Reciprocal | rd = 1.0 / rs1 | Zftrans | -| FEXP2M1 | power-2 minus 1 | rd = pow(2, rs1) - 1.0 | ZftransExt | -| FLOG2P1 | log2 plus 1 | rd = log(2, 1 + rs1) | ZftransExt | -| FEXP2 | power-of-2 | rd = pow(2, rs1) | Zftrans | -| FLOG2 | log2 | rd = log(2. rs1) | Zftrans | -| FEXPM1 | exponential minus 1 | rd = pow(e, rs1) - 1.0 | ZftransExt | -| FLOG1P | log plus 1 | rd = log(e, 1 + rs1) | ZftransExt | -| FEXP | exponential | rd = pow(e, rs1) | ZftransExt | -| FLOG | natural log (base e) | rd = log(e, rs1) | ZftransExt | -| FEXP10M1 | power-10 minus 1 | rd = pow(10, rs1) - 1.0 | ZftransExt | -| FLOG10P1 | log10 plus 1 | rd = log(10, 1 + rs1) | ZftransExt | -| FEXP10 | power-of-10 | rd = pow(10, rs1) | ZftransExt | -| FLOG10 | log base 10 | rd = log(10, rs1) | ZftransExt | +| FRSQRT | Reciprocal Square-root | FRT = sqrt(FRA) | Zfrsqrt | +| FCBRT | Cube Root | FRT = pow(FRA, 1.0 / 3) | ZftransAdv | +| FRECIP | Reciprocal | FRT = 1.0 / FRA | Zftrans | +| FEXP2M1 | power-2 minus 1 | FRT = pow(2, FRA) - 1.0 | ZftransExt | +| FLOG2P1 | log2 plus 1 | FRT = log(2, 1 + FRA) | ZftransExt | +| FEXP2 | power-of-2 | FRT = pow(2, FRA) | Zftrans | +| FLOG2 | log2 | FRT = log(2. FRA) | Zftrans | +| FEXPM1 | exponential minus 1 | FRT = pow(e, FRA) - 1.0 | ZftransExt | +| FLOG1P | log plus 1 | FRT = log(e, 1 + FRA) | ZftransExt | +| FEXP | exponential | FRT = pow(e, FRA) | ZftransExt | +| FLOG | natural log (base e) | FRT = log(e, FRA) | ZftransExt | +| FEXP10M1 | power-10 minus 1 | FRT = pow(10, FRA) - 1.0 | ZftransExt | +| FLOG10P1 | log10 plus 1 | FRT = log(10, 1 + FRA) | ZftransExt | +| FEXP10 | power-of-10 | FRT = pow(10, FRA) | ZftransExt | +| FLOG10 | log base 10 | FRT = log(10, FRA) | ZftransExt | ## List of 1-arg trigonometric opcodes | opcode | Description | pseudocode | Extension | | ------ | ---------------- | ---------------- | ----------- | -| FSIN | sin (radians) | rd = sin(rs1) | Ztrignpi | -| FCOS | cos (radians) | rd = cos(rs1) | Ztrignpi | -| FTAN | tan (radians) | rd = tan(rs1) | Ztrignpi | -| FASIN | arcsin (radians) | rd = asin(rs1) | Zarctrignpi | -| FACOS | arccos (radians) | rd = acos(rs1) | Zarctrignpi | -| FATAN | arctan (radians) | rd = atan(rs1) | Zarctrignpi | -| FSINPI | sin times pi | rd = sin(pi * rs1) | Ztrigpi | -| FCOSPI | cos times pi | rd = cos(pi * rs1) | Ztrigpi | -| FTANPI | tan times pi | rd = tan(pi * rs1) | Ztrigpi | -| FASINPI | arcsin / pi | rd = asin(rs1) / pi | Zarctrigpi | -| FACOSPI | arccos / pi | rd = acos(rs1) / pi | Zarctrigpi | -| FATANPI | arctan / pi | rd = atan(rs1) / pi | Zarctrigpi | -| FSINH | hyperbolic sin (radians) | rd = sinh(rs1) | Zfhyp | -| FCOSH | hyperbolic cos (radians) | rd = cosh(rs1) | Zfhyp | -| FTANH | hyperbolic tan (radians) | rd = tanh(rs1) | Zfhyp | -| FASINH | inverse hyperbolic sin | rd = asinh(rs1) | Zfhyp | -| FACOSH | inverse hyperbolic cos | rd = acosh(rs1) | Zfhyp | -| FATANH | inverse hyperbolic tan | rd = atanh(rs1) | Zfhyp | +| FSIN | sin (radians) | FRT = sin(FRA) | Ztrignpi | +| FCOS | cos (radians) | FRT = cos(FRA) | Ztrignpi | +| FTAN | tan (radians) | FRT = tan(FRA) | Ztrignpi | +| FASIN | arcsin (radians) | FRT = asin(FRA) | Zarctrignpi | +| FACOS | arccos (radians) | FRT = acos(FRA) | Zarctrignpi | +| FATAN | arctan (radians) | FRT = atan(FRA) | Zarctrignpi | +| FSINPI | sin times pi | FRT = sin(pi * FRA) | Ztrigpi | +| FCOSPI | cos times pi | FRT = cos(pi * FRA) | Ztrigpi | +| FTANPI | tan times pi | FRT = tan(pi * FRA) | Ztrigpi | +| FASINPI | arcsin / pi | FRT = asin(FRA) / pi | Zarctrigpi | +| FACOSPI | arccos / pi | FRT = acos(FRA) / pi | Zarctrigpi | +| FATANPI | arctan / pi | FRT = atan(FRA) / pi | Zarctrigpi | +| FSINH | hyperbolic sin (radians) | FRT = sinh(FRA) | Zfhyp | +| FCOSH | hyperbolic cos (radians) | FRT = cosh(FRA) | Zfhyp | +| FTANH | hyperbolic tan (radians) | FRT = tanh(FRA) | Zfhyp | +| FASINH | inverse hyperbolic sin | FRT = asinh(FRA) | Zfhyp | +| FACOSH | inverse hyperbolic cos | FRT = acosh(FRA) | Zfhyp | +| FATANH | inverse hyperbolic tan | FRT = atanh(FRA) | Zfhyp | [[!inline pages="openpower/power_trans_ops" raw=yes ]] @@ -322,8 +322,8 @@ needed for 3D, however for Numerical Computation they may be useful. Although they can be synthesised using Ztrans (LOG2 multiplied by a constant), there is both a performance penalty as well as an accuracy penalty towards the limits, which for IEEE754 compliance is -unacceptable. In particular, LOG(1+rs1) in hardware may give much better -accuracy at the lower end (very small rs1) than LOG(rs1). +unacceptable. In particular, LOG(1+FRA) in hardware may give much better +accuracy at the lower end (very small FRA) than LOG(FRA). Their forced inclusion would be inappropriate as it would penalise embedded systems with tight power and area budgets. However if they -- 2.30.2